相关论文: Unsupervised Salient Patch Selection for Data-Effi…

Single Image Reflection Removal (SIRR) in real-world images is a challenging task due to diverse image degradations occurring on the glass surface during light transmission and reflection. Many existing methods rely on specific prior…

Vision-and-Language Navigation (VLN) requires an agent to find a specified spot in an unseen environment by following natural language instructions. Dominant methods based on supervised learning clone expert's behaviours and thus perform…

Multiple instance learning (MIL) has become a preferred method for gigapixel whole slide image (WSI) classification without requiring patch-level annotations. Current MIL research primarily relies on embedding-based approaches, which…

Recent research highlights the potential of multimodal foundation models in tackling complex decision-making challenges. However, their large parameters make real-world deployment resource-intensive and often impractical for constrained…

The task of dataset distillation aims to find a small set of synthetic images such that training a model on them reproduces the performance of the same model trained on a much larger dataset of real samples. Existing distillation methods…

Pre-training Reinforcement Learning agents in a task-agnostic manner has shown promising results. However, previous works still struggle in learning and discovering meaningful skills in high-dimensional state-spaces, such as pixel-spaces.…

Model-based imitation learning (MBIL) is a popular reinforcement learning method that improves sample efficiency on high-dimension input sources, such as images and videos. Following the convention of MBIL research, existing algorithms are…

We propose DiRL, a Diversity-inducing Representation Learning technique for histopathology imaging. Self-supervised learning techniques, such as contrastive and non-contrastive approaches, have been shown to learn rich and effective…

In-context reinforcement learning (ICRL) promises fast adaptation to unseen environments without parameter updates, but current methods either cannot improve beyond the training distribution or require near-optimal data, limiting practical…

Fine-tuning Diffusion Models remains an underexplored frontier in generative artificial intelligence (GenAI), especially when compared with the remarkable progress made in fine-tuning Large Language Models (LLMs). While cutting-edge…

Regression that predicts continuous quantity is a central part of applications using computational imaging and computer vision technologies. Yet, studying and understanding self-supervised learning for regression tasks - except for a…

This paper targets the efficient construction of a safety shield for decision making in scenarios that incorporate uncertainty. Markov decision processes (MDPs) are prominent models to capture such planning problems. Reinforcement learning…

Recent advances in reinforcement learning have shown that language models can develop sophisticated reasoning through training on tasks with verifiable rewards, but these approaches depend on human-curated problem-answer pairs and…

Self-Supervised learning (SSL) has become the new state-of-art in several domain classification and segmentation tasks. Of these, one popular category in SSL is distillation networks such as BYOL. This work proposes RSDnet, which applies…

Unsupervised Reinforcement Learning (RL) aims to discover diverse behaviors that can accelerate the learning of downstream tasks. Previous methods typically focus on entropy-based exploration or empowerment-driven skill learning. However,…

Images suffer from heavy spatial redundancy because pixels in neighboring regions are spatially correlated. Existing approaches strive to overcome this limitation by reducing less meaningful image regions. However, current leading methods…

Few-shot class incremental learning (FSCIL) portrays the problem of learning new concepts gradually, where only a few examples per concept are available to the learner. Due to the limited number of examples for training, the techniques…

Diffusion and flow models have emerged as powerful generative approaches capable of modeling diverse and multimodal behavior. However, applying these models to offline reinforcement learning (RL) remains challenging due to the iterative…

Despite the tremendous achievements of deep convolutional neural networks (CNNs) in many computer vision tasks, understanding how they actually work remains a significant challenge. In this paper, we propose a novel two-step understanding…

The first step in Multiple Instance Learning (MIL) algorithms for Whole Slide Image (WSI) classification consists of tiling the input image into smaller patches and computing their feature vectors produced by a pre-trained feature extractor…