Continual World is a benchmark consisting of realistic and meaningfully diverse robotic tasks built on top of Meta-World as a testbed.

Abstract: There have been emerging a number of benchmarks and techniques for the detection of deepfakes. However, very few works study the detection of incrementally appearing deepfakes in the real-world scenarios. To simulate the wild scenes, this paper suggests a continual deepfake detection benchmark (CDDB) over a new collection of deepfakes from both known and unknown generative models. The suggested CDDB designs multiple evaluations on the detection over easy, hard, and long sequence of deepfake tasks, with a set of appropriate measures. In addition, we exploit multiple approaches to adapt multiclass incremental learning methods, commonly used in the continual visual recognition, to the continual deepfake detection problem. We evaluate existing methods, including their adapted ones, on the proposed CDDB. Within the proposed benchmark, we explore some commonly known essentials of standard continual learning. Our study provides new insights on these essentials in the context of continual deepfake detection. The suggested CDDB is clearly more challenging than the existing benchmarks, which thus offers a suitable evaluation avenue to the future research.

Feature selection is an important solution for dealing with high-dimensional data in the fields of machine learning and data mining. In this paper, we present an improved mountain gazelle optimizer (IMGO) based on the newly proposed mountain gazelle optimizer (MGO) and design a binary version of IMGO (BIMGO) to solve the feature selection problem for medical data. First, the gazelle population is initialized using iterative chaotic map with infinite collapses (ICMIC) mapping, which increases the diversity of the population. Second, a nonlinear control factor is introduced to balance the exploration and exploitation components of the algorithm. Individuals in the population are perturbed using a spiral perturbation mechanism to enhance the local search capability of the algorithm. Finally, a neighborhood search strategy is used for the optimal individuals to enhance the exploitation and convergence capabilities of the algorithm. The superior ability of the IMGO algorithm to solve continuous problems is demonstrated on 23 benchmark datasets. Then, BIMGO is evaluated on 16 medical datasets of different dimensions and compared with 8 well-known metaheuristic algorithms. The experimental results indicate that BIMGO outperforms the competing algorithms in terms of the fitness value, number of selected features and sensitivity. In addition, the statistical results of the experiments demonstrate the significantly superior ability of BIMGO to select the most effective features in medical datasets.

The recent breakthroughs in computer vision have benefited from the availability of large representative datasets (e.g. ImageNet and COCO) for training. Yet, robotic vision poses unique challenges for applying visual algorithms developed from these standard computer vision datasets due to their implicit assumption over non-varying distributions for a fixed set of tasks. Fully retraining models each time a new task becomes available is infeasible due to computational, storage and sometimes privacy issues, while naive incremental strategies have been shown to suffer from catastrophic forgetting. It is crucial for the robots to operate continuously under openset and detrimental conditions with adaptive visual perceptual systems, where lifelong learning is a fundamental capability. However, very few datasets and benchmarks are available to evaluate and compare emerging techniques. To fill this gap, we provide a new lifelong robotic vision dataset (“OpenLORISObject”) collected via RGB-D cameras. The dataset embeds the challenges faced by a robot in the real-life application and provides new benchmarks for validating lifelong object recognition algorithms. This dataset could support object classification, detection and segmentation. The 1 st version of OpenLORIS-Object is a collection of 121 instances, including 40 categories daily necessities objects under 20 scenes. For each instance, a 17 to 25 seconds video (at 30 fps) has been recorded with a depth camera delivering around 500 to 750 frames (260 to 600 distinguishable object views are manually picked and provided in the dataset). 4 environmental factors, each has 3 level changes, are considered explicitly, including illumination variants during recording, occlusion percentage of the objects, object pixel size in each frame, and the clutter of the scene. Note that the variables of 3) object size and 4) camera-object distance are combined together because in the real-world scenarios, it is hard to distinguish the effects of these two factors brought to the actual data collected from the mobile robots, but we can identify their joint effects on the actual pixel sizes of the objects in the frames roughly. The variable 5) is considered as different recorded views of the objects. The defined three difficulty levels for each factor are shown in Table. II (totally we have 12 levels w.r.t. the environment factors across all instances). The levels 1, 2, and 3 are ranked with increasing difficulties.

Offline reinforcement learning (RL) is a promising direction that allows RL agents to be pre-trained from large datasets avoiding recurrence of expensive data collection. To advance the field, it is crucial to generate large-scale datasets. Compositional RL is particularly appealing for generating such large datasets, since 1) it permits creating many tasks from few components, and 2) the task structure may enable trained agents to solve new tasks by combining relevant learned components. This submission provides four offline RL datasets for simulated robotic manipulation created using the 256 tasks from CompoSuite Mendez et al., 2022. In every task in CompoSuite, a robot arm is used to manipulate an object to achieve an objective all while trying to avoid an obstacle. There are for components for each of these four axes that can be combined arbitrarily leading to a total of 256 tasks. The component choices are * Robot: IIWA, Jaco, Kinova3, Panda* Object: Hollow box, box, dumbbell, plate* Objective: Push, pick and place, put in shelf, put in trashcan* Obstacle: None, wall between robot and object, wall between goal and object, door between goal and object The four included datasets are collected using separate agents each trained to a different degree of performance, and each dataset consists of 256 million transitions. The degrees of performance are expert data, medium data, warmstart data and replay data: * Expert dataset: Transitions from an expert agent that was trained to achieve 90% success on every task.* Medium dataset: Transitions from a medium agent that was trained to achieve 30% success on every task.* Warmstart dataset: Transitions from a Soft-actor critic agent trained for a fixed duration of one million steps.* Medium-replay-subsampled dataset: Transitions that were stored during the training of a medium agent up to 30% success. These datasets are intended for the combined study of compositional generalization and offline reinforcement learning. Methods The datasets were collected by using several deep reinforcement learning agents trained to the various degrees of performance described above on the CompoSuite benchmark (https://github.com/Lifelong-ML/CompoSuite) which builds on top of robosuite (https://github.com/ARISE-Initiative/robosuite) and uses the MuJoCo simulator (https://github.com/deepmind/mujoco). During reinforcement learning training, we stored the data that was collected by each agent in a separate buffer for post-processing. Then, after training, to collect the expert and medium dataset, we run the trained agents for 2000 trajectories of length 500 online in the CompoSuite benchmark and store the trajectories. These add up to a total of 1 million state-transitions tuples per dataset, totalling a full 256 million datapoints per dataset. The warmstart and medium-replay-subsampled dataset contain trajectories from the stored training buffer of the SAC agent trained for a fixed duration and the medium agent respectively. For medium-replay-subsampled data, we uniformly sample trajectories from the training buffer until we reach more than 1 million transitions. Since some of the tasks have termination conditions, some of these trajectories are trunctated and not of length 500. This sometimes results in a number of sampled transitions larger than 1 million. Therefore, after sub-sampling, we artificially truncate the last trajectory and place a timeout at the final position. This can in some rare cases lead to one incorrect trajectory if the datasets are used for finite horizon experimentation. However, this truncation is required to ensure consistent dataset sizes, easy data readability and compatibility with other standard code implementations. The four datasets are split into four tar.gz folders each yielding a total of 12 compressed folders. Every sub-folder contains all the tasks for one of the four robot arms for that dataset. In other words, every tar.gz folder contains a total of 64 tasks using the same robot arm and four tar.gz files form a full dataset. This is done to enable people to only download a part of the dataset in case they do not need all 256 tasks. For every task, the data is separately stored in an hdf5 file allowing for the usage of arbitrary task combinations and mixing of data qualities across the four datasets. Every task is contained in a folder that is named after the CompoSuite elements it uses. In other words, every task is represented as a folder named

We aim to improve the bAbI benchmark as a means of developing intelligent dialogue agents. To this end, we propose concatenated-bAbI (catbAbI): an infinite sequence of bAbI stories. catbAbI is generated from the bAbI dataset and during training, a random sample/story from any task is drawn without replacement and concatenated to the ongoing story. The preprocessig for catbAbI addresses several issues: it removes the supporting facts, leaves the questions embedded in the story, inserts the correct answer after the question mark, and tokenises the full sample into a single sequence of words. As such, catbAbI is designed to be trained in an autoregressive way and analogous to closed-book question answering.

catbAbI models can be trained in two different ways: language modelling mode (LM-mode) or question-answering mode (QA-mode). In LM-mode, the catbAbI models are trained like autoregressive word-level language models. In QA-mode, the catbAbI models are only trained to predict the tokens that are answers to questions—making it more similar to regular bAbI. QA-mode is simply implemented by masking out losses on non-answer predictions. In both training modes, the model performance is solely measured by its accuracy and perplexity when answering the questions.

The widespread adoption of cloud computing necessitates privacy-preserving techniques that allow information to be processed without disclosure. This paper proposes a method to increase the accuracy and performance of privacy-preserving Convolutional Neural Networks with Homomorphic Encryption (CNN-HE) by Self-Learning Activation Functions (SLAF). SLAFs are polynomials with trainable coefficients updated during training, together with synaptic weights, for each polynomial independently to learn task-specific and CNN-specific features. We theoretically prove its feasibility to approximate any continuous activation function to the desired error as a function of the SLAF degree. Two CNN-HE models are proposed: CNN-HE-SLAF and CNN-HE-SLAF-R. In the first model, all activation functions are replaced by SLAFs, and CNN is trained to find weights and coefficients. In the second one, CNN is trained with the original activation, then weights are fixed, activation is substituted by SLAF, and CNN is shortly re-trained to adapt SLAF coefficients. We show that such self-learning can achieve the same accuracy 99.38% as a non-polynomial ReLU over non-homomorphic CNNs and lead to an increase in accuracy (99.21%) and higher performance (6.26 times faster) than the state-of-the-art CNN-HE CryptoNets on the MNIST optical character recognition benchmark dataset.

Public ECG dataset of continuous raw signals for representation learning containing 11 thousand patients and 2 billion labelled beats.