Related papers: Exploring the Diversity and Invariance in Yourself…

Self-supervised representation learning approaches have recently surpassed their supervised learning counterparts on downstream tasks like object detection and image classification. Somewhat mysteriously the recent gains in performance come…

There is a growing interest in designing models that can deal with images from different visual domains. If there exists a universal structure in different visual domains that can be captured via a common parameterization, then we can use a…

We propose a general framework for self-supervised learning of transferable visual representations based on Video-Induced Visual Invariances (VIVI). We consider the implicit hierarchy present in the videos and make use of (i) frame-level…

Deep image prior (DIP) and its variants have showed remarkable potential for solving inverse problems in computer vision, without any extra training data. Practical DIP models are often substantially overparameterized. During the fitting…

Self-supervised methods have recently proved to be nearly as effective as supervised ones in various imaging inverse problems, paving the way for learning-based approaches in scientific and medical imaging applications where ground truth…

Ensembling a neural network is a widely recognized approach to enhance model performance, estimate uncertainty, and improve robustness in deep supervised learning. However, deep ensembles often come with high computational costs and memory…

In this work, we study different approaches to self-supervised pretraining of object detection models. We first design a general framework to learn a spatially consistent dense representation from an image, by randomly sampling and…

Self-supervised visual representation learning traditionally focuses on image-level instance discrimination. Our study introduces an innovative, fine-grained dimension by integrating patch-level discrimination into these methodologies. This…

All-in-one image restoration tackles different types of degradations with a unified model instead of having task-specific, non-generic models for each degradation. The requirement to tackle multiple degradations using the same model can…

In recent years, deep neural networks tasks have increasingly relied on high-quality image inputs. With the development of high-resolution representation learning, the task of image dehazing has received significant attention. Previously,…

Image-to-image translation has drawn great attention during the past few years. It aims to translate an image in one domain to a given reference image in another domain. Due to its effectiveness and efficiency, many applications can be…

Self-supervised learning methods overcome the key bottleneck for building more capable AI: limited availability of labeled data. However, one of the drawbacks of self-supervised architectures is that the representations that they learn are…

Recent self-supervised contrastive methods have been able to produce impressive transferable visual representations by learning to be invariant to different data augmentations. However, these methods implicitly assume a particular set of…

Pre-training is a dominant paradigm in computer vision. For example, supervised ImageNet pre-training is commonly used to initialize the backbones of object detection and segmentation models. He et al., however, show a surprising result…

State-of-the-art methods for self-supervised learning (SSL) build representations by maximizing the similarity between different transformed "views" of a sample. Without sufficient diversity in the transformations used to create views,…

Self-supervised learning has emerged as a powerful paradigm for training deep neural networks, particularly in medical imaging where labeled data is scarce. While current approaches typically rely on synthetic augmentations of single…

The self-supervised contrastive learning strategy has attracted considerable attention due to its exceptional ability in representation learning. However, current contrastive learning tends to learn global coarse-grained representations of…

Self-supervised representation learning often uses data augmentations to induce some invariance to "style" attributes of the data. However, with downstream tasks generally unknown at training time, it is difficult to deduce a priori which…

Unified Multimodal models (UMMs) built on a single architecture have shown impressive performance in both understanding and generation. We identify a fundamental challenge that lies in inductive biases induced by distinct supervision…

Magnetic Resonance Imaging (MRI) is widely used in clinical practice, but suffered from prolonged acquisition time. Although deep learning methods have been proposed to accelerate acquisition and demonstrate promising performance, they rely…