Related papers: From Vicious to Virtuous Cycles: Synergistic Repre…

Object-centric understanding is fundamental to human vision and required for complex reasoning. Traditional methods define slot-based bottlenecks to learn object properties explicitly, while recent self-supervised vision models like DINO…

Conventional Graph Contrastive Learning (GCL) on Text-Attributed Graphs (TAGs) relies on blind stochastic augmentations, inadvertently entangling task-relevant signals with noise. We propose SDM-SCR, a robust framework anchored in…

In this paper, we investigate the problem of how to effectively master tool-use to solve complex visual reasoning tasks for Multimodal Large Language Models. To achieve that, we propose a novel Tool-supervised Reinforcement Learning…

We consider the learning from noisy labels (NL) problem which emerges in many real-world applications. In addition to the widely-studied synthetic noise in the NL literature, we also consider the pseudo labels in semi-supervised learning…

Vision Transformer (ViT) architectures represent images as collections of high-dimensional vectorized tokens, each corresponding to a rectangular non-overlapping patch. This representation trades spatial granularity for embedding…

The COVID-19 pandemic has highlighted the need for a tool to speed up triage in ultrasound scans and provide clinicians with fast access to relevant information. The proposed video-summarization technique is a step in this direction that…

Building robust and real-time classifiers with diverse datasets are one of the most significant challenges to deep learning researchers. It is because there is a considerable gap between a model built with training (seen) data and real…

In this study, the problem of computing a sparse representation of multi-dimensional visual data is considered. In general, such data e.g., hyperspectral images, color images or video data consists of signals that exhibit strong local…

Model-based reinforcement learning (RL) has proven to be a data efficient approach for learning control tasks but is difficult to utilize in domains with complex observations such as images. In this paper, we present a method for learning…

Reinforcement Learning (RL) is crucial for empowering VideoLLMs with complex spatiotemporal reasoning. However, current RL paradigms predominantly rely on random data shuffling or naive curriculum strategies based on scalar difficulty…

Fundamentally, super-resolution is ill-posed problem because a low-resolution image can be obtained from many high-resolution images. Recent studies for super-resolution cannot create diverse super-resolution images. Although SRFlow tried…

Contrastive learning has achieved great success in skeleton-based representation learning recently. However, the prevailing methods are predominantly negative-based, necessitating additional momentum encoder and memory bank to get negative…

Diffusion models have demonstrated exceptional capabilities in image restoration, yet their application to video super-resolution (VSR) faces significant challenges in balancing fidelity with temporal consistency. Our evaluation reveals a…

At the core of self-supervised learning for vision is the idea of learning invariant or equivariant representations with respect to a set of data transformations. This approach, however, introduces strong inductive biases, which can render…

A Recurrent Neural Network (RNN) for Video Super Resolution (VSR) is generally trained with randomly clipped and cropped short videos extracted from original training videos due to various challenges in learning RNNs. However, since this…

How to improve the ability of scene representation is a key issue in vision-oriented decision-making applications, and current approaches usually learn task-relevant state representations within visual reinforcement learning to address this…

Object-centric representation learning aims to decompose visual scenes into fixed-size vectors called "slots" or "object files", where each slot captures a distinct object. Current state-of-the-art object-centric models have shown…

We present a self-supervised Contrastive Video Representation Learning (CVRL) method to learn spatiotemporal visual representations from unlabeled videos. Our representations are learned using a contrastive loss, where two augmented clips…

Not having access to compact and meaningful representations is known to significantly increase the complexity of reinforcement learning (RL). For this reason, it can be useful to perform state representation learning (SRL) before tackling…

Neural networks exhibit severe brittleness to semantically irrelevant transformations. A mere 75ms electrocardiogram (ECG) phase shift degrades latent cosine similarity from 1.0 to 0.2, while sensor rotations collapse activity recognition…