Related papers: VICReg: Variance-Invariance-Covariance Regularizat…
Video super-resolution (VSR) is a task that aims to reconstruct high-resolution (HR) frames from the low-resolution (LR) reference frame and multiple neighboring frames. The vital operation is to utilize the relative misaligned frames for…
Studies on generalization performance of machine learning algorithms under the scope of information theory suggest that compressed representations can guarantee good generalization, inspiring many compression-based regularization methods.…
In this work, we propose the use of large set of unlabeled images as a source of regularization data for learning robust visual representation. Given a visual model trained by a labeled dataset in a supervised fashion, we augment our…
Learning visual representations with self-supervised learning has become popular in computer vision. The idea is to design auxiliary tasks where labels are free to obtain. Most of these tasks end up providing data to learn specific kinds of…
Diffusion models represent the state-of-the-art for solving inverse problems such as image restoration tasks. Diffusion-based inverse solvers incorporate a likelihood term to guide prior sampling, generating data consistent with the…
We present a new vectorial total variation method that addresses the problem of color consistent image filtering. Our approach is inspired from the double-opponent cell representation in the human visual cortex. Existing methods of…
Despite the great progress in video understanding made by deep convolutional neural networks, feature representation learned by existing methods may be biased to static visual cues. To address this issue, we propose a novel method to…
Self-supervised visual representation methods are closing the gap with supervised learning performance. These methods rely on maximizing the similarity between embeddings of related synthetic inputs created through data augmentations. This…
Several studies have recently pointed that existing Visual Question Answering (VQA) models heavily suffer from the language prior problem, which refers to capturing superficial statistical correlations between the question type and the…
Variance reduction (VR) techniques have contributed significantly to accelerating learning with massive datasets in the smooth and strongly convex setting (Schmidt et al., 2017; Johnson & Zhang, 2013; Roux et al., 2012). However, such…
Scarcity of labeled data has motivated the development of semi-supervised learning methods, which learn from large portions of unlabeled data alongside a few labeled samples. Consistency Regularization between model's predictions under…
Visual Commonsense Reasoning (VCR) remains a significant yet challenging research problem in the realm of visual reasoning. A VCR model generally aims at answering a textual question regarding an image, followed by the rationale prediction…
We propose ViC-MAE, a model that combines both Masked AutoEncoders (MAE) and contrastive learning. ViC-MAE is trained using a global featured obtained by pooling the local representations learned under an MAE reconstruction loss and…
Video contrastive learning (V-CL) has emerged as a popular framework for unsupervised video representation learning, demonstrating strong results in tasks such as action classification and detection. Yet, to harness these benefits, it is…
Visual attention in Visual Question Answering (VQA) targets at locating the right image regions regarding the answer prediction, offering a powerful technique to promote multi-modal understanding. However, recent studies have pointed out…
Objective: This paper investigates how generative models, trained on ground-truth images, can be used \changes{as} priors for inverse problems, penalizing reconstructions far from images the generator can produce. The aim is that learned…
Weakly supervised learning has emerged as an appealing alternative to alleviate the need for large labeled datasets in semantic segmentation. Most current approaches exploit class activation maps (CAMs), which can be generated from…
Invariance (defined in a general sense) has been one of the most effective priors for representation learning. Direct factorization of parametric models is feasible only for a small range of invariances, while regularization approaches,…
Visual anagrams are images that change appearance upon transformation, like flipping or rotation. With the advent of diffusion models, generating such optical illusions can be achieved by averaging noise across multiple views during the…
Variational regularization has remained one of the most successful approaches for reconstruction in imaging inverse problems for several decades. With the emergence and astonishing success of deep learning in recent years, a considerable…