Related papers: MaDi: Learning to Mask Distractions for Generaliza…

Most existing text recognition methods are trained on large-scale synthetic datasets due to the scarcity of labeled real-world datasets. Synthetic images, however, cannot faithfully reproduce real-world scenarios, such as uneven…

Few-shot learning aims to correctly recognize query samples from unseen classes given a limited number of support samples, often by relying on global embeddings of images. In this paper, we propose to equip the backbone network with an…

We introduce a new distributed policy gradient algorithm and show that it outperforms existing reward-aware training procedures such as REINFORCE, minimum risk training (MRT) and proximal policy optimization (PPO) in terms of training…

Unsupervised anomaly detection in brain images is crucial for identifying injuries and pathologies without access to labels. However, the accurate localization of anomalies in medical images remains challenging due to the inherent…

Masked Autoencoders (MAE) achieve self-supervised learning of image representations by randomly removing a portion of visual tokens and reconstructing the original image as a pretext task, thereby significantly enhancing pretraining…

The objective of meta-learning is to exploit the knowledge obtained from observed tasks to improve adaptation to unseen tasks. As such, meta-learners are able to generalize better when they are trained with a larger number of observed tasks…

In fighting games, individual players of the same skill level often exhibit distinct strategies from one another through their gameplay. Despite this, the majority of AI agents for fighting games have only a single strategy for each "level"…

Multi-agent reinforcement learning involves multiple agents interacting with each other and a shared environment to complete tasks. When rewards provided by the environment are sparse, agents may not receive immediate feedback on the…

Deep neural networks have become commonplace in the domain of reinforcement learning, but are often expensive in terms of the number of parameters needed. While compressing deep neural networks has of late assumed great importance to…

Reinforcement learning (RL) algorithms have been around for decades and employed to solve various sequential decision-making problems. These algorithms however have faced great challenges when dealing with high-dimensional environments. The…

Model-based methods have significantly contributed to distinguishing task-irrelevant distractors for visual control. However, prior research has primarily focused on heterogeneous distractors like noisy background videos, leaving…

Masked Image Modeling (MIM) achieves outstanding success in self-supervised representation learning. Unfortunately, MIM models typically have huge computational burden and slow learning process, which is an inevitable obstacle for their…

Domain-adaptive trajectory imitation is a skill that some predators learn for survival, by mapping dynamic information from one domain (their speed and steering direction) to a different domain (current position of the moving prey). An…

Imitation learning allows agents to learn complex behaviors from demonstrations. However, learning a complex vision-based task may require an impractical number of demonstrations. Meta-imitation learning is a promising approach towards…

Deep reinforcement learning has been applied successfully to solve various real-world problems and the number of its applications in the multi-agent settings has been increasing. Multi-agent learning distinctly poses significant challenges…

3D mask presentation attack detection is crucial for protecting face recognition systems against the rising threat of 3D mask attacks. While most existing methods utilize multimodal features or remote photoplethysmography (rPPG) signals to…

In reinforcement learning algorithms, it is a common practice to account for only a single view of the environment to make the desired decisions; however, utilizing multiple views of the environment can help to promote the learning of…

Referring Image Segmentation (RIS) is an advanced vision-language task that involves identifying and segmenting objects within an image as described by free-form text descriptions. While previous studies focused on aligning visual and…

The performance of image-based Reinforcement Learning (RL) agents can vary depending on the position of the camera used to capture the images. Training on multiple cameras simultaneously, including a first-person egocentric camera, can…

Developing agents for complex and underspecified tasks, where no clear objective exists, remains challenging but offers many opportunities. This is especially true in video games, where simulated players (bots) need to play realistically,…