Powered by the ImageNet dataset, unsupervised learning on large-scale data has made significant advances for classification tasks. There are two major challenges to allowing such an attractive learning modality for segmentation tasks: i) a large-scale benchmark for assessing algorithms is missing; ii) unsupervised shape representation learning is difficult. We propose a new problem of large-scale unsupervised semantic segmentation (LUSS) with a newly created benchmark dataset to track the research progress. Based on the ImageNet dataset, we propose the ImageNet-S dataset with 1.2 million training images and 50k high-quality semantic segmentation annotations for evaluation. Our benchmark has a high data diversity and a clear task objective. We also present a simple yet effective baseline method that works surprisingly well for LUSS. In addition, we benchmark related un/weakly/fully supervised methods accordingly, identifying the challenges and possible directions of LUSS.

PartImageNet is a large, high-quality dataset with part segmentation annotations. It consists of 158 classes from ImageNet with approximately 24′000 images. The classes are grouped into 11 super-categories and the parts split are designed according to the super-category as shown below. The number in the brackets after the category name indicates the total number of classes of the category.

CSWin Transformer (the name CSWin stands for Cross-Shaped Window) is introduced in arxiv, which is a new general-purpose backbone for computer vision. It is a hierarchical Transformer and replaces the traditional full attention with our newly proposed cross-shaped window self-attention. The cross-shaped window self-attention mechanism computes self-attention in the horizontal and vertical stripes in parallel that from a cross-shaped window, with each stripe obtained by splitting the input feature into stripes of equal width. With CSWin, we could realize global attention with a limited computation cost. CSWin Transformer achieves strong performance on ImageNet classification (87.5 on val with only 97G flops) and ADE20K semantic segmentation (55.7 mIoU on val), surpassing previous models by a large margin.

Main Results on ImageNet

This dataset contains Model weights for the Blurred Border FPN model pre-trained with ImageNet.

This dataset contains Model weights for the Distance Map FPN model pre-trained with ImageNet.

BigDatasetGAN is a dataset for pixel-wise ImageNet segmentation. It consists of large synthetic datasets from BigGAN & VQGAN.

Introduction The main goal of this challenge is to recognize objects from a number of visual object classes in realistic scenes (i.e. not pre-segmented objects). It is fundamentally a supervised learning learning problem in that a training set of labelled images is provided. The twenty object classes that have been selected are: * Person: person * Animal: bird, cat, cow, dog, horse, sheep * Vehicle: aeroplane, bicycle, boat, bus, car, motorbike, train * Indoor: bottle, chair, dining table, potted plant, sofa, tv/monitor There are three main object recognition competitions: classification, detection, and segmentation, a competition on action classification, and a competition on large scale recognition run by ImageNet. In addition there is a "taster" competition on person layout. ##Classification/Detection Competitions Classification: For each of the twenty classes, predicting presence/absence of an example of that class in the test image. Detection: Predicting the bounding b

BackgroundIn medical imaging, the integration of deep-learning-based semantic segmentation algorithms with preprocessing techniques can reduce the need for human annotation and advance disease classification. Among established preprocessing techniques, Contrast Limited Adaptive Histogram Equalization (CLAHE) has demonstrated efficacy in improving segmentation algorithms across various modalities, such as X-rays and CT. However, there remains a demand for improved contrast enhancement methods considering the heterogeneity of datasets and the various contrasts across different anatomic structures.MethodThis study proposes a novel preprocessing technique, ps-KDE, to investigate its impact on deep learning algorithms to segment major organs in posterior-anterior chest X-rays. Ps-KDE augments image contrast by substituting pixel values based on their normalized frequency across all images. We evaluate our approach on a U-Net architecture with ResNet34 backbone pre-trained on ImageNet. Five separate models are trained to segment the heart, left lung, right lung, left clavicle, and right clavicle.ResultsThe model trained to segment the left lung using ps-KDE achieved a Dice score of 0.780 (SD = 0.13), while that of trained on CLAHE achieved a Dice score of 0.717 (SD = 0.19), p

Authors introduce DUTS, a significant contribution to the field of saliency detection, which originally relied on unsupervised computational models with heuristic priors but has recently seen remarkable progress with deep neural networks (DNNs). DUTS is a large-scale dataset comprising 10,553 train images and 5,019 test images. The training images are sourced from the ImageNet DET training/val sets, while the test images are drawn from the ImageNet DET test set and the SUN dataset, encompassing challenging scenarios for salient_object detection. What sets DUTS apart is its meticulously annotated pixel-level ground truths by 50 subjects and the explicit training/test evaluation protocol, making it the largest saliency detection benchmark to date, enabling fair and consistent comparisons in future research endeavors, with the training set serving as an ideal resource for DNN learning and the test set for evaluation purposes.

Abstract: The strong scientific interest and the accompanying rapid development of machine learning, in particular deep learning, has led to a significant improvement in automatic image interpretation in recent years. Research generally focuses on classification or segmentation of optical images, but there are already several successful approaches that apply deep learning techniques to the analysis of PolSAR or Pol-InSAR images. While the success of learning-based methods for the analysis of optical images has been strongly driven by public benchmark datasets such as ImageNet and Cityscapes, which contain a large number of annotated training and test data, comparable datasets for the PolSAR and especially the Pol-InSAR domain are almost non-existent. This conclusion and the demand for large and representative expert-annotated benchmark datasets for the SAR community is also reached by Zhu et al. (2021) in their analysis of the current state of deep learning-based SAR image analysis. To fill this gap, this work presents a new multi-frequency Pol-InSAR benchmark dataset for training and testing learning-based methods. This dataset is intended to improve the development of new approaches or the adaptation and improvement of existing ones. Furthermore, a defined division of the data into training and testing sections will ensure the comparability of approaches of different works. For the segmentation of PolSAR images, there already exist a few annotated datasets that are frequently referenced in the respective literature. These include the PolSF dataset, which contains PolSAR images from various spaceborne and airborne systems over San Francisco, the E-SAR dataset from Oberpfaffenhofen, and the Flevoland dataset, which contains an AIRSAR image depicting agricultural areas. The described datasets have several limitations that make them inadequate for evaluating learning-based image segmentation approaches. One weakness is the small amount of data, which is usually insufficient for training deep networks. Another problem is the lack of complexity of the segmentation task due to generic classes that are too easily distinguishable or spatial distributions of classes that are too simplistic, regular, and resembling each other. As a result, very high classification performances can already be achieved by simple classifiers, so that a comparison of more sophisticated classifiers, which are necessary for more challenging real-world tasks, is not possible. Another disadvantage of existing datasets is that the division into training and test areas is not fixed, which prevents the comparability of research that uses these datasets for evaluation. Our annotated, multi-frequency Pol-InSAR dataset named $\textbf{Pol-InSAR-Island}$ provides information-rich data as well as a challenging segmentation task consisting of 12 land cover classes. The Pol-InSAR data of the dataset were acquired in April 2022, on behalf of the Lower Saxony Water Management, Coastal Defence and Nature Conservation Agency (NLWKN), with the airborne F-SAR system (Reigber, 2020) of the German Aerospace Center (DLR) during a measurement campaign over the German Wadden Sea. The basics necessary for this measurement campaign in terms of data acquisition and processing were developed within the GeoWAM project (Pinheiro, 2020; Schmitz, 2022). The data acquisition was performed simultaneously in S- and L-band. Interferometric analysis is enabled by imaging the area two times with a time offset of 12 minutes and a vertical baseline of 12m. The Pol-InSAR-Island dataset does not include all flight data of the measurement campaign, but only data sections that cover the island Baltrum. Based on co-registered interferometric image pairs the coherency matrix $\mathbf{T}_6$ is calculated for each pixel, which is obtained from the scalar products of the Pauli scattering vectors $\mathrm{k}_1$ and $\mathrm{k}_2$:

Dataset for deep learning training course

1) Heart Segmentation of ventricles

2) ImageNet

3) CIFAR10

Npz, tfrecords dataset type

ForNet is a dataset of foreground objects and backgrounds extracted (and infilled) from ImageNet. It's the output of the segmentation phase of the ForAug data augmentation. ForNet recombines these foregrounds and backgrounds on the fly to create new samples for training vision transformers.

YOLO (You Only Look Once) is a popular object detection algorithm that processes images in a single pass through a neural network to simultaneously predict bounding boxes and class probabilities for objects within those boxes. YOLOv3 is one of the versions of this algorithm, known for its balance between speed and accuracy.

For training and testing YOLOv3, you can use a variety of datasets depending on your application. Some commonly used datasets for object detection tasks, including those suitable for YOLOv3, are:

COCO (Common Objects in Context): This dataset is widely used for object detection, segmentation, and captioning tasks. It contains over 200,000 labeled images with 80 object categories.

Pascal VOC (Visual Object Classes): This dataset consists of images annotated with object bounding boxes and class labels. It includes 20 object categories such as person, car, dog, etc.

Open Images Dataset: This is a large-scale dataset with millions of images annotated with object bounding boxes and class labels. It covers a wide range of object categories.

KITTI Vision Benchmark Suite: Primarily used for autonomous driving research, this dataset contains images captured from a moving vehicle with annotations for object detection, tracking, and scene understanding.

ImageNet: Although primarily known for image classification, ImageNet also contains bounding box annotations for object detection tasks. It consists of millions of images across thousands of categories.

These datasets provide a diverse range of objects in various contexts, making them suitable for training and evaluating object detection models like YOLOv3.

The convolutional neural networks (CNNs) are a powerful tool of image classification that has been widely adopted in applications of automated scene segmentation and identification. However, the mechanisms underlying CNN image classification remain to be elucidated. In this study, we developed a new approach to address this issue by investigating transfer of learning in representative CNNs (AlexNet, VGG, ResNet-101, and Inception-ResNet-v2) on classifying geometric shapes based on local/global features or invariants. While the local features are based on simple components, such as orientation of line segment or whether two lines are parallel, the global features are based on the whole object such as whether an object has a hole or whether an object is inside of another object. Six experiments were conducted to test two hypotheses on CNN shape classification. The first hypothesis is that transfer of learning based on local features is higher than transfer of learning based on global features. The second hypothesis is that the CNNs with more layers and advanced architectures have higher transfer of learning based global features. The first two experiments examined how the CNNs transferred learning of discriminating local features (square, rectangle, trapezoid, and parallelogram). The other four experiments examined how the CNNs transferred learning of discriminating global features (presence of a hole, connectivity, and inside/outside relationship). While the CNNs exhibited robust learning on classifying shapes, transfer of learning varied from task to task, and model to model. The results rejected both hypotheses. First, some CNNs exhibited lower transfer of learning based on local features than that based on global features. Second the advanced CNNs exhibited lower transfer of learning on global features than that of the earlier models. Among the tested geometric features, we found that learning of discriminating inside/outside relationship was the most difficult to be transferred, indicating an effective benchmark to develop future CNNs. In contrast to the “ImageNet” approach that employs natural images to train and analyze the CNNs, the results show proof of concept for the “ShapeNet” approach that employs well-defined geometric shapes to elucidate the strengths and limitations of the computation in CNN image classification. This “ShapeNet” approach will also provide insights into understanding visual information processing the primate visual systems.

Abstract: Pol-InSAR-Island is the first publicly available multi-frequency Polarimetric Interferometric Synthetic Aperture Radar (Pol-InSAR) benchmark dataset for land cover classification. The strong scientific interest and the accompanying rapid development of machine learning, in particular deep learning, has led to a significant improvement in automatic image interpretation in recent years. Research generally focuses on classification or segmentation of optical images, but there are already several successful approaches that apply deep learning techniques to the analysis of PolSAR or Pol-InSAR images. While the success of learning-based methods for the analysis of optical images has been strongly driven by public benchmark datasets such as ImageNet and Cityscapes, which contain a large number of annotated training and test data, comparable datasets for the PolSAR and especially the Pol-InSAR domain are almost non-existent. To fill this gap, this work presents a new multi-frequency Pol-InSAR benchmark dataset for training and testing learning-based methods. The dataset contains Pol-InSAR data acquired in S- and L-band by DLR’s airborne F-SAR system over the East Frisian island Baltrum. To allow interferometric analysis a repeat-pass configuration with a time offset of several minutes and a vertical baseline of 40 m is used. The image data are given as geocoded 6 × 6 coherency matrices on a 1 m × 1 m grid and is labeled by 12 different land cover classes. The Pol-InSAR-Island dataset is intended to improve the development of new learning-based approaches for multi-frequency Pol-InSAR classification. To ensure the comparability of various approaches, a defined division of the data into training and testing sections is given. For more information, refer to the corresponding research article: https://doi.org/10.1016/j.ophoto.2023.100047 Pol-InSAR-Island - A Benchmark Dataset for Multi-frequency Pol-InSAR Data Land Cover Classification (Version 2) is the updated version of the dataset. The PolSAR as well as the label images remain unchanged, but additional files containing the corresponding incidence angle and the vertical wavenumbers are added. TechnicalRemarks: # Pol-InSAR-Island dataset: This folder contains multi-frequency Pol-InSAR data acquired by the F-SAR system of the German Aerospace Center (DLR) over Baltrum and corresponding land cover labels. Data structure: - data - FP1 # Flight path 1 - L # Frequency band - T6 # Pol-InSAR data - incidence.bin # Incidence angle [rad] - kz_*.bin ' Vertical wavenumber for vv, hv, vh and vv polarization [rad/m] - pauli.bmp # Pauli-RGB image of the master scene - S - ... - FP2 # Flight path 2 - ... - label # Land cover label - FP1 # Flight path 1 - label_train.bin # Geocoded training label - label_test.bin # Geocoded test label - ... - FP2 # Flight path 2 - ... Data format: The data is provided as flat-binary raster files (.bin) with an accompanying ASCII header file (*.hdr) in ENVI-format. For Pol-InSAR data the real and imaginary components of the diagonal elments and upper triangle elements of the 6 x 6 coherency matrix are stored in seperated files (T11.bin, T12_real.bin, T12_imag.bin,...) Land cover labels contained in label_train.bin and label_test.bin are encoded as integers using the following mapping:

Sensory ecologists have found that this s background matching camouflage strategy works by deceiving the visual perceptual system of the observer. Naturally, addressing concealed object detection (COD) requires a significant amount of visual perception knowledge. Understanding COD has not only scientific value in itself, but it also important for applications in many fundamental fields, such as computer vision (e.g., for search-and-rescue work, or rare species discovery), medicine (e.g., polyp segmentation, lung infection segmentation), agriculture (e.g., locust detection to prevent invasion), and art (e.g., recreational art). The high intrinsic similarities between the targets and non-targets make COD far more challenging than traditional object segmentation/detection. Although it has gained increased attention recently, studies on COD still remain scarce, mainly due to the lack of a sufficiently large dataset and a standard benchmark like Pascal-VOC, ImageNet, MS-COCO, ADE20K, and DAVIS.

To build the large-scale COD dataset, we build the COD10K, which contains 10,000 images (5,066 camouflaged, 3,000 background, 1,934 noncamouflaged), divided into 10 super-classes, and 78 sub-classes (69 camouflaged, nine non-camouflaged) which are collected from multiple photography websites.

A large-scale aerial farmland image dataset for semantic segmentation of agricultural patterns. Collects 94,986 high-quality aerial images from 3,432 farmlands across the US, where each image consists of RGB and Near-infrared (NIR) channels with resolution as high as 10 cm per pixel.

Pol-InSAR-Island dataset:

This folder contains multi-frequency Pol-InSAR data acquired by the F-SAR system of the German Aerospace Center (DLR) over Baltrum and corresponding land cover labels. Data structure: - data - FP1 # Flight path 1 - L # Frequency band - T6 # Pol-InSAR data - incidence.bin # Incidence angle [rad] - kz_*.bin ' Vertical wavenumber for vv, hv, vh and vv polarization [rad/m] - pauli.bmp # Pauli-RGB image of the master scene - S - ... - FP2 # Flight path 2 - ... - label # Land cover label - FP1 # Flight path 1 - label_train.bin # Geocoded training label - label_test.bin # Geocoded test label - ... - FP2 # Flight path 2 - ... Data format: The data is provided as flat-binary raster files (.bin) with an accompanying ASCII header file (*.hdr) in ENVI-format. For Pol-InSAR data the real and imaginary components of the diagonal elments and upper triangle elements of the 6 x 6 coherency matrix are stored in seperated files (T11.bin, T12_real.bin, T12_imag.bin,...) Land cover labels contained in label_train.bin and label_test.bin are encoded as integers using the following mapping: 0 - Unassigned
1 - Tidal flat
2 - Water
3 - Coastal shrub
4 - Dense, high vegetation
5 - White dune
6 - Peat bog
7 - Grey dune
8 - Couch grass
9 - Upper saltmarsh
10 - Lower saltmarsh
11 - Sand
12 - Settlement

The goal of this challenge is to recognize objects from a number of visual object classes in realistic scenes (i.e. not pre-segmented objects). It is fundamentally a supervised learning learning problem in that a training set of labelled images is provided. The twenty object classes that have been selected are: Person: person Animal: bird, cat, cow, dog, horse, sheep Vehicle: aeroplane, bicycle, boat, bus, car, motorbike, train Indoor: bottle, chair, dining table, potted plant, sofa, tv/monitor There will be three main competitions: classification, detection, and segmentation; and three "taster" competition: person layout, action classification, and ImageNet large scale recognition: Classification/Detection Competitions Classification: For each of the twenty classes, predicting presence/absence of an example of that class in the test image.