Dataset Card for Cats Vs. Dogs

  Dataset Summary

A large set of images of cats and dogs. There are 1738 corrupted images that are dropped. This dataset is part of a now-closed Kaggle competition and represents a subset of the so-called Asirra dataset. From the competition page:

The Asirra data set Web services are often protected with a challenge that's supposed to be easy for people to solve, but difficult for computers. Such a challenge is often called a CAPTCHA… See the full description on the dataset page: https://huggingface.co/datasets/microsoft/cats_vs_dogs.

Context:

This dataset contains survey responses to a survey that people could complete when they signed up for the 5-Day Data Challenge.

On December 12, 2017 survey responses for the second 5-Day Data Challenge were added. For this version of the challenge, participants could sign up for either an intro version or a more in-depth regression challenge.

Content:

The optional survey included four multiple-choice questions:

1. Have you ever taken a course in statistics?

• Yep
• Yes, but I've forgotten everything
• Nope

1. Do you have any previous experience with programming?

• Nope
• I have a little bit of experience
• I have quite a bit of experience
• I have a whole lot of experience

1. What's your interest in data science?

• Just curious
• It will help me in my current job
• I want to get a job where I use data science
• Other

1. Just for fun, do you prefer dogs or cat?

• Dogs 🐶
• Cats 🐱
• Both 🐱🐶
• Neither 🙅

In order to protect privacy, the data has been shuffled (so there’s no temporal order to the responses) and a random 2% of the data has been removed (so even if you know that someone completed the survey, you cannot be sure that their responses are included in this dataset). In addition, all incomplete responses have been removed, and any text entered in the “other” free response field has been replaced with the text “other”.

Acknowledgements:

Thanks to everyone who completed the survey! :)

Inspiration:

• Is there a relationship between how much programming experience someone has and why they’re interested in data science?
• Are more experienced programmers more likely to have taken statistics?
• Do people tend to prefer dogs, cats, both or neither? Is there a relationship between what people prefer and why they’re interested in data science?

Dataset used in the article "Does Visual Stimulation by Photographs of Cats and Dogs Make People Happier and More Optimistic?"ColumnsIDis_preview: true - response by the researcher to check the questionnaire, it should be removedremove: respondent checked that his/her responses are not valid and should not be used in future analysisfinished_proc: percentage of the questionnaire finisheddate_time: filing of the questionnaire started at this timeduration_formatted: duration of the filling of the questionnairebrowserbrowser_versionOS: operating systempriming: true - primed group, false - control groupcat_dog: objects on photos showngenderage: in yerssex_o: attraction to people of the opposite sex (scale 1 - 7)sex_s: attraction to people of the same sex (scale 1 - 7) orientation: computed as the difference of previous twomood: actual mood (scale 0 - 5)condition_phys: physical condition (scale 0 - 5)condition_psych: mental condition (scale 0 - 5)life_quality: life quality (scale 0 - 5)optimism: mean of previous threeoptimism_zskore: z-score of the previous children_own: how many children does respondent havewanted_sons: total number of sons which respondent would like to havewanted_daughters: total number of daughters which respondent would like to havewanted_children: a sum of previous twoliking_dogs: how much respondent likes dogs (scale 1 - 100)present_whenever_dog: respondent has ever kept a dogpresent_now_dog: respondent keeps dog nowpresent_Ndogs: how many dogs does respondent keep now liking_cats: how much respondent likes cats (scale 1 - 100)present_whenever_cat: respondent has ever kept a catpresent_now_cat: respondent keeps cat nowpresent_Ncats: how many cats does respondent keep now

In this competition, you'll write an algorithm to classify whether images contain either a dog or a cat. This is easy for humans, dogs, and cats. Your computer will find it a bit more difficult.

https://www.ethosvet.com/wp-content/uploads/cat-dog-625x375.png" alt="">

The Asirra data set

Web services are often protected with a challenge that's supposed to be easy for people to solve, but difficult for computers. Such a challenge is often called a CAPTCHA (Completely Automated Public Turing test to tell Computers and Humans Apart) or HIP (Human Interactive Proof). HIPs are used for many purposes, such as to reduce email and blog spam and prevent brute-force attacks on web site passwords.

Asirra (Animal Species Image Recognition for Restricting Access) is a HIP that works by asking users to identify photographs of cats and dogs. This task is difficult for computers, but studies have shown that people can accomplish it quickly and accurately. Many even think it's fun! Here is an example of the Asirra interface:

Asirra is unique because of its partnership with Petfinder.com, the world's largest site devoted to finding homes for homeless pets. They've provided Microsoft Research with over three million images of cats and dogs, manually classified by people at thousands of animal shelters across the United States. Kaggle is fortunate to offer a subset of this data for fun and research. Image recognition attacks

While random guessing is the easiest form of attack, various forms of image recognition can allow an attacker to make guesses that are better than random. There is enormous diversity in the photo database (a wide variety of backgrounds, angles, poses, lighting, etc.), making accurate automatic classification difficult. In an informal poll conducted many years ago, computer vision experts posited that a classifier with better than 60% accuracy would be difficult without a major advance in the state of the art. For reference, a 60% classifier improves the guessing probability of a 12-image HIP from 1/4096 to 1/459. State of the art

The current literature suggests machine classifiers can score above 80% accuracy on this task [1]. Therfore, Asirra is no longer considered safe from attack. We have created this contest to benchmark the latest computer vision and deep learning approaches to this problem. Can you crack the CAPTCHA? Can you improve the state of the art? Can you create lasting peace between cats and dogs?

Submission Format

Your submission should have a header. For each image in the test set, predict a label for its id (1 = dog, 0 = cat):

id,label 1,0 2,0 3,0 etc...

Dogs and cats have become the most important and successful pets through long-term domestication. People keep them for various reasons, such as their functional roles or for physical or psychological support. However, why humans are so attached to dogs and cats remains unclear. A comprehensive understanding of the current state of human preferences for dogs and cats and the potential influential factors behind it is required. Here, we investigate this question using two independent online datasets and anonymous questionnaires in China. We find that current human preferences for dog and cat videos are relatively higher than for most other interests, with video plays ranking among the top three out of fifteen interests. We also find genetic variations, gender, age, and economic development levels notably influence human preferences for dogs and cats. Specifically, dog and cat ownership are significantly associated with parents’ pet ownership of dogs and cats (Spearman’s rank correlation c..., , , # Human preferences for dogs and cats in China: the current situation and influencing factors of watching online videos and pet ownership

https://doi.org/10.5061/dryad.qfttdz0rr

This dataset contains three CSV data files, each corresponding to one of the three parts described in the study.

Description of the data and file structure

**“1, bilibili.csv†**: contains data extracted from the Bilibili website. Each row in the dataset represents yearly data for each popular channel. Missing data are indicated with NA.

• ID:Â The serial number for each video, ranging from 1 to 167368.
• year: The year the video was published on the website, from 2009 to 2021.
• Videourl:Â The URL of the video.
• plays:Â The total number of plays for the video.
• likes: The total number of likes for the video.
• sort: The ranking of the video in terms of play count among all popular videos in its channel for that year.
• channelID: The I...

Context

This dataset consists of 2000 transformed images (1000 each of cat and dog). It can be directly used with CNN models without the need for any transformation

Content

As this is beginner's competition, we do lot of trial and error to understand how computer vision problems are solved. Hence, I feel the training on 25000 images would be time consuming. I have reduced it to 2000 images (1000 per category) by randomly shuffling from the original. Following transforms are applied: data_transform = transforms.Compose([ transforms.Resize(256), transforms.ColorJitter(), transforms.RandomCrop(224), transforms.RandomHorizontalFlip(), # transforms.Resize(128), transforms.ToTensor() ])

Inspiration

Save some time when learning on this dataset

Cat&dog&people

## Overview

Cat&dog&people is a dataset for object detection tasks - it contains Cats annotations for 612 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

People who feed cats that they do not perceive they own (sometimes called semi-owners) are thought to make a considerable contribution to unwanted cat numbers because the cats they support are generally not sterilized. Understanding people’s perception of cat ownership and the psychology underlying cat semi-ownership could inform approaches to mitigate the negative effects of cat semi-ownership. The primary aims of this study were to investigate cat ownership perception and to examine its association with human-cat interactions and caretaking behaviours. A secondary aim was to evaluate a definition of cat semi-ownership (including an association time of ≥1 month and frequent feeding), revised from a previous definition proposed in the literature to distinguish cat semi-ownership from casual interactions with unowned cats. Cat owners and semi-owners displayed similar types of interactions and caretaking behaviours. Nevertheless, caretaking behaviours were more commonly displayed towards owned cats than semi-owned cats, and semi-owned cats were more likely to have produced kittens (p

Dog Person

## Overview

Dog Person is a dataset for object detection tasks - it contains Dogs Cats Person annotations for 2,574 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

Introduction: Diminishing cognitive and physical functions, worsening psychological symptoms, and increased mortality risk and morbidity typically accompany aging. The aging population's health needs will continue to increase as the proportion of the population aged > 50 years increases. Pet ownership (PO) has been linked to better health outcomes in older adults, particularly those with chronic conditions. Much of the evidence is weak. Little is known about PO patterns as people age or the contribution of PO to successful aging in community-dwelling older adults. This study examines PO patterns among healthy community-dwelling older adults and the relationship of PO to cognitive and physical functions and psychological status.Methods: Participants in the Baltimore Longitudinal Study of Aging (> 50 years old, N = 378) completed a battery of cognitive, physical function, and psychological tests, as well as a PO questionnaire. Descriptive and non-parametric or general/generalized linear model analyses were conducted for separate outcomes.Results: Most participants (82%) had kept pets and 24% have pets: 14% dogs, 12% cats, 3% other pets. The most frequent reasons for having pets included enjoyment (80%) and companionship (66%). Most owners had kept the pet they had the longest for over 10 years (70%). PO was lower in older decades (p < 0.001). Pet owners were more likely to live in single-family homes and reside with others (p = 0.001) than non-owners. Controlling for age, PO was associated independently with better cognitive function (verbal leaning/memory p = 0.041), dog ownership predicted better physical function (daily energy expenditure, p = 0.018), and cat ownership predicted better cognitive functioning (verbal learning/memory, p = 0.035). Many older adults who did not own pets (37%) had regular contact with pets, which was also related to health outcomes.Conclusion: PO is lower at older ages, which mirrors the general pattern of poorer cognitive and physical function, and psychological status at older ages. PO and regular contact with pets (including PO) are associated with better cognitive status compared with those who did not own pets or had no regular contact with pets independent of age. Dog ownership was related to better physical function. Longitudinal analysis is required to evaluate the association of PO and/or regular contact with maintenance of health status over time.

This dataset is comprised of variables coded/extracted from popular press articles about domestic cats (Felis catus), which were evaluated as part of a media-content analysis. Our focus was understanding how a number of issues surrounding free-roaming (feral) cats are presented and discussed in the popular press, including: - The messengers who are quoted or referenced (e.g., cat advocates, veterinarians, naturalists, researchers) - The risks and threats to which feral cats are exposed (e.g., diseases, vehicles, predation)- The impacts feral cats have on the environment, native wildlife (e.g., via predation), and threats they pose to human health (e.g., via disease transmission)- The potential strategies and tools used to manage feral cat populations and their impacts (e.g., trap-neuter-release, bylaws, public education)We used the Lexis Nexus search engine to conduct a systemic search for English-language popular print media, including news articles and bulletins, opinion-editorials, and other public notices (e.g., classifieds) published between 1990 and 2018 (see Search Terms in READ_ME file and Methods: Search in the referenced article). Using a code book we developed (see Questions Coded From Articles in READ_ME), we evaluated each article based on whether they conveyed a variety of different messages. In total, the dataset is comprised of 796 articles, with the bulk (~95%) of articles from the United States and Canada. Most of the people interviewed ("messengers") were from non-governmental organizations, mainly from cat-welfare or cat-rights groups. Researchers, shelter organizations, veterinarians, and groups that differ on how to resolve issues surrounding free-roaming cats were rarely interviewed. Most articles focused on cat welfare issues and the management strategies of euthanasia or trap-neuter-release (TNR), whereas less than one-third of the articles acknowledged that cats have any impact on wildlife or the broader environment.See READ_ME file for a full list of variable definitions.

Non†native predators can cause great harm to natural ecosystems through competition for resources and by directly predating on native species. Domestic cats (Felis catus) predate on wild prey throughout the world and have been implicated in a number of species declines. However, in the UK, long†term, widespread research is lacking. The data provided here relate to prey returned home by pet cats in the UK over a total period of 3.5 years (ranging from one month to 3.5 years per cat). These data were collected by cat owners across the UK, noting details of the prey returned home by their cats monthly. Data were gathered upon registration regarding the age, sex, and body condition of participating cats, allowing for the analysis of the potential influence of such factors. While most cats returned 0–1 prey per month, a small minority (n = 3 cats) returned over 15 individuals monthly. It is important that true predation rates (in addition to the return rates found here) are further exp..., , , # Title of Dataset: Quantifying prey return rates of domestic cats in the UK

[Access this dataset on Dryad](DOI: 10.5061/dryad.31zcrjdv9)

Description of the data and file structure

Data are presented in two files: 'Data1_prey' and 'Data2_cats'.

Data1_prey. This file contains details of all prey returned home by the cats monitored (n=553) over a total period of 3.5 years. Cat_ID is a unique identifier for each cat and Prey_ID is as given by owners or as verified by researchers thanks to photographs provided. Taxonomic group is then given, along with whether prey were dead or alive (or not recorded), what happened to the prey which were returned alive (for example, released), and whether returned whole, part-eaten, or witnessed by owners to be eaten. Age and sex were not required, but some participants gave this information in the related 'notes' section of the data return form. As such, there are many 'NA' datapoints for age and sex fields.

Data2_cats. This file contains data re...,

Context

The Austin Animal Center is the largest no-kill animal shelter in the United States that provides care and shelter to over 18,000 animals each year. As part of the AAC's efforts to help and care for animals in need, the organization makes available its accumulated data and statistics as part of the city of Austin's Open Data Initiative.

Content

The data contains intakes and outcomes of animals entering the Austin Animal Center from the beginning of October 2013 to the present day. The datasets are also freely available on the Socrata Open Data Access API and are updated daily.

The following are links to the datasets hosted on Socrata's Open Data:

• Austin Animal Center Intakes
• Austin Animal Center Outcomes

The data contained in this dataset is the outcomes and intakes data as noted above, as well as a combined dataset. The merging of the outcomes and intakes data was done on a unique key that is a combination of the given Animal ID and the intake number. Several of the animals in the dataset have been taken into the shelter multiple times, which creates duplicate Animal IDs that causes problems when merging the two datasets.

Copied from the description of the Shelter Outcomes dataset, here are some definitions of the outcome types:

• Adoption
  • the animal was adopted to a home
• Barn Adoption
  • the animal was adopted to live in a barn
• Offsite Missing
  • the animal went missing for unknown reasons at an offsite partner location
• In-Foster Missing
  • the animal is missing after being placed in a foster home
• In-Kennel Missing
  • the animal is missing after being transferred to a kennel facility
• Possible Theft
  • Although not confirmed, the animal went missing as a result of theft from the facility
• Barn Transfer
  • The animal was transferred to a facility for adoption into a barn environment
• SNR
  • SNR refers to the city of Austin's Shelter-Neuter-Release program. I believe the outcome is representative of the animal being released.

Acknowledgements

The data presented here is only possible through the hard work and dedication of the Austin Animal Center in saving and caring for animal lives.

Inspiration

Following from the first dataset I posted to Kaggle, Austin Animal Shelter Outcomes, which was initially filtered for just cats as part of an analysis I was performing, I wanted to post the complete outcome and complementing intake datasets. My hope is the great users of Kaggle will find this data interesting and want to explore shelter animal statistics further and perhaps get more involved in the animal welfare community. The analysis of this data and other shelter animal provided datasets helps uncover useful insights that have the potential to save lives directly.

https://i.imgur.com/RDJPnbd.png" alt="Credit: Carlos Ruas">

About this dataset

Ah, yes. Finally a good, relevant question!!! The human race has managed to reach for the stars, however it still struggles to understand our feline friends. With this dataset you can contribute to this relevant task and perhaps one day we'll be able to translate their meows - so that they can officially tell us that we are in fact their pets.

This dataset, composed of 440 sound recordings, contains meows emitted by cats in different contexts. Specifically, 21 cats belonging to 2 breeds (Maine Coon and European Shorthair) have been repeatedly exposed to three different stimuli that act as labels for prediction: - Waiting for food; - Isolation in unfamiliar environment; - Brushing (being brushed affectionately by the owner).

File naming conventions

Files containing meows are in the "dataset" folder. They are PCM streams (.wav). Naming conventions follow the pattern L[label]_CID[Cat ID]_BB[Cat Breed]_SS[Sex]_OID[Owner ID]_R[Recording Session]XX[Meow counter]. The unique values are available in the 'dataset' folder description.

Extra content

The "extra" folder contains excluded recordings (sounds other than meows emitted by cats) and uncut sequences of close vocalizations. It can be used as a 4th class.

How to use this dataset

• Create an audio classifier for Meow Classification
• Explore the audio spectrograms and tabular variables

Highlighted Notebooks

• Your kernel can be featured here!
• More datasets

Acknowledgements

If you use this wonderful dataset in your research, please credit the authors, or the next cat you see will scratch you.

Citation

Ntalampiras, S., Ludovico, L.A., Presti, G., Prato Previde, E., Battini, M., Cannas, S., Palestrini, C., Mattiello, S.: Automatic Classification of Cat Vocalizations Emitted in Different Contexts. Animals, vol. 9(8), pp. 543.1–543.14. MDPI (2019). ISSN: 2076-2615

Ludovico, L.A., Ntalampiras, S., Presti, G., Cannas, S., Battini, M., Mattiello, S.: CatMeows: A Publicly-Available Dataset of Cat Vocalizations. In: Li, X., Lokoč, J., Mezaris, V., Patras, I., Schoeffmann, K., Skopal, T., Vrochidis, S. (eds.) MultiMedia Modeling. 27th International Conference, MMM 2021, Prague, Czech Republic, June 22–24, 2021, Proceedings, Part II, LNCS, vol. 12573, pp. 230–243. Springer International Publishing, Cham (2021). ISBN: 978-3-030-67834-0 (print), 978-3-030-67835-7 (online) ISSN: 0302-9743 (print), 1611-3349 (online)

License

CC BY NC 4.0

Splash banner

Icon by Freepik on FlatIcon. Comic by Carlos Ruas at caesegatos_oficial.

Started out as a pumpkin detector to test training YOLOv5. Now suffering from extensive feature creep and probably ending up as a cat/dog/spider/pumpkin/randomobjects-detector. Or as a desaster.

The dataset does not fit https://docs.ultralytics.com/tutorials/training-tips-best-results/ well. There are no background images and the labeling is often only partial. Especially in the humans and pumpkin category where there are often lots of objects in one photo people apparently (and understandably) got bored and did not labe everything. And of course the images from the cat-category don't have the humans in it labeled since they come from a cat-identification model which ignored humans. It will need a lot of time to fixt that.

Dataset used: - Cat and Dog Data: Cat / Dog Tutorial NVIDIA Jetson https://github.com/dusty-nv/jetson-inference/blob/master/docs/pytorch-cat-dog.md © 2016-2019 NVIDIA according to bottom of linked page - Spider Data: Kaggle Animal 10 image set https://www.kaggle.com/datasets/alessiocorrado99/animals10 Animal pictures of 10 different categories taken from google images Kaggle project licensed GPL 2 - Pumpkin Data: Kaggle "Vegetable Images" https://www.researchgate.net/publication/352846889_DCNN-Based_Vegetable_Image_Classification_Using_Transfer_Learning_A_Comparative_Study https://www.kaggle.com/datasets/misrakahmed/vegetable-image-dataset Kaggle project licensed CC BY-SA 4.0 - Some pumpkin images manually copied from google image search - https://universe.roboflow.com/chess-project/chess-sample-rzbmc Provided by a Roboflow user License: CC BY 4.0 - https://universe.roboflow.com/steve-pamer-cvmbg/pumpkins-gfjw5 Provided by a Roboflow user License: CC BY 4.0 - https://universe.roboflow.com/nbduy/pumpkin-ryavl Provided by a Roboflow user License: CC BY 4.0 - https://universe.roboflow.com/homeworktest-wbx8v/cat_test-1x0bl/dataset/2 - https://universe.roboflow.com/220616nishikura/catdetector - https://universe.roboflow.com/atoany/cats-s4d4i/dataset/2 - https://universe.roboflow.com/personal-vruc2/agricultured-ioth22 - https://universe.roboflow.com/sreyoshiworkspace-radu9/pet_detection - https://universe.roboflow.com/artyom-hystt/my-dogs-lcpqe - license: Public Domain url: https://universe.roboflow.com/dolazy7-gmail-com-3vj05/sweetpumpkin/dataset/2 - https://universe.roboflow.com/tristram-dacayan/social-distancing-g4pbu - https://universe.roboflow.com/fyp-3edkl/social-distancing-2ygx5 License MIT - Spiders: https://universe.roboflow.com/lucas-lins-souza/animals-train-yruka

Currently I can't guarantee it's all correctly licenced. Checks are in progress. Inform me if you see one of your pictures and want it to be removed!

Data_total_draft1

## Overview

Data_total_draft1 is a dataset for object detection tasks - it contains Racoon Cats People Deer Dog Cats annotations for 1,857 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

These questionnaires correspond to one of the methodological phases of the research project "Resilient children, youth and communities: identifying and analysing social and educational practices from a multidimensional and intersectional perspective to address the pandemic”. The purpose of quizzes is to know about the experiences or programs that were carried out in the town or city to help children and young people face the COVID pandemic, especially during the time of confinement, and also, if they participated in helping other people. The questionnaires had questions corresponding to the 5 dimensions of resilience analysis Community education derived from the theoretical framework of research. They are the instrument to analyse the intersectionality between groups and the cross-cutting nature of resilience. This dataset includes: (1) Youngsters and children questionnaires (26 and 27 questions). There are closed (dichotomous, multiple choice, Likert scale according to or frequency and a satisfaction scale of 11 points) and open questions recoded to enter them in the spss (RE). There are adapted versions of them in order to make them accessible, both versions can be found in this dataset in pdf format, all of them are in catalan and the questionnaires for elder than 18 can be found also in spanish. (2) The data frame in spss (statistic program) format, with the children's answers to the questionnaire (a total of 1216 answers) and the youngsters' answers to the questionnaire (a total of 115 answers).

The present dataset contains (meta) information extracted from the materials preserved in the archival funds of the International Institute of Intellectual Cooperation (IIIC), which was recently digitized [available at https://atom.archives.unesco.org/iiic ]. More precisely, the dataset focuses on subseries A and F from the Series Correspondence. Using machine learning and natural language processing (NLP) techniques, we have parsed scanned documents and extracted from them meta-information like: people and location mentions, language (e.g., French), nature of material (e.g., letter vs. attached document), formal aspects (e.g., handwritten vs. typewritten), and -- if possible -- its year of publication. Moreover, we have associated these entities (e.g., a given person) and information to the specific document(s) where they appear. We have divided the dataset in three files: one focused on people and two on locations (one for countries and another for cities). This dataset has been generated within the ERC-StG project named "Social Networks of the Past: Mapping Hispanic and Lusophone Literary Modernity, 1898-1959".

In many areas, domestic cats are the most abundant predators of small vertebrates. Due to the potential impact on prey populations by cats, there are calls to investigate the effectiveness of visual and acoustic cues as measures to reduce the cat’s hunting efficiency. In this study, we complement previous studies on the efficacy of Birdsbesafe collar-covers (BBScc) in a so far not investigated Continental European setting and explore the effectiveness in combination with a bell. We also evaluate the tolerability of these devices by the cat and the acceptance by their owners. With a randomized and comparative citizen science-based approach we collected data from 26 households with 31 study cats, which were wearing either a BBScc or both a BBScc and a bell. The BBScc reduced the number of birds brought home by 37% (probability of reduction of 88%). The number of mammals brought home was reduced by 54–62%, but only with the additional bell (probability of reduction of >99%). About one fourth of the birds that could be dissected were found to have collided with a hard object prior to having been brought home by the cats. Our results are in line with previous findings from Australia, the United States, and the United Kingdom and highlight the great potential of visual and acoustic cues in reducing hunting success in domestic cats also in Continental Europe. On the other hand, our result show that the number of prey brought home by cats overestimates their hunting bag, if scavenging is not considered. The majority of cat owners reported that their cats habituated quickly to the BBScc. However, frequent scratching in some cats indicates that some individuals may not habituate. Most participating cat owners had a positive attitude toward the BBScc and said that they were willing to use it after the study. However, cat owners reported that their social environment (e.g., neighbors, family, friends) was relatively skeptical, which indicates a need for communication. To conclude, commercially available devices with visual and acoustic stimuli are straightforward and effective ways to mitigate the potentially harmful effect of domestic cats on wildlife.

https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F12294787%2F4217b8c4192757a5c54a0d2fe44b8441%2Foverview.png?generation=1741620902943282&alt=media" alt="">

WildlifeReID-10k is a wildlife re-identification dataset with more than 140k images of 10k individual animals. It is a collection of 37 existing wildlife re-identification datasets with additional processing steps. WildlifeReID-10k contains diverse animals such as marine turtles, primates, birds, African herbivores, marine mammals, and domestic animals. We provide a Jupyter notebook with introduction to the dataset, a way to evaluate developed algorithms and a baseline performance. WildlifeReID-10k has two primary uses: - Design an algorithm to classify individual animals in images. This is a much more complicated task (with 10k fine-grained classes) and the intended use of the dataset. - Design an algorithm to classify species of animals. This is a simpler task (with 20 coarse-grained classes) requiring fewer resources. It is intended for researchers or the interested public who want to develop their first methods on an interesting dataset.

Dataset creation:

WildlifeReID-10k was created by the Python library wildlife-datasets by combining 37 existing wildlife re-identification datasets. We claim no rights to these datasets besides SeaTurtleID2022. When publishing results on WildlifeReID-10k, all individual datasets should be attributed (see below). An accompanying paper containing a better dataset description is currently under review.

The dataset may be used under the following requirements:

The user of this dataset must follow the provided license file. In particular, it prohibits commercial applications and being re-uploaded. Moreover, this work and all the consisting datasets must be properly attributed. We provide the pdf file and the LaTex files in a separate folder citation for the attribution. The license files of the individual datasets must be followed. For simplicity, we provide license files of the individual datasets: - CC BY 4.0: AAUZebraFish, CatIndividualImages, Chicks4FreeID, CowDataset, DogFaceNet, MPDD, PolarBearVidID, SealID; - CC BY-NC-SA 4.0: ATRW, NDD20; - CC BY-SA 3.0: StripeSpotter; - CC BY-SA 4.0: ZindiTurtleRecall; - CDLA-Permissive-1.0: BelugaID, GiraffeZebraID, HyenaID2022, LeopardID2022, SeaStarReID2023, WhaleSharkID; - MIT: SMALST; - NC-Government: AerialCattle2017, Cows2021, FriesianCattle2015, FriesianCattle2017, MultiCamCows2024, OpenCows2020; - None: BirdIndividualID, Giraffes, IPanda50, NyalaData; - Other: AmvrakikosTurtles, CTai, CZoo, PrimFace, [ReunionTurtles](https://www.kaggle.com/datasets/wildlifedatasets/reu...