Related papers: Exploring the Diversity and Invariance in Yourself…

We demonstrate that self-learning techniques like entropy minimization and pseudo-labeling are simple and effective at improving performance of a deployed computer vision model under systematic domain shifts. We conduct a wide range of…

A data augmentation module is utilized in contrastive learning to transform the given data example into two views, which is considered essential and irreplaceable. However, the predetermined composition of multiple data augmentations brings…

We address the problem of depth and ego-motion estimation from image sequences. Recent advances in the domain propose to train a deep learning model for both tasks using image reconstruction in a self-supervised manner. We revise the…

Deep Learning based methods have emerged as the indisputable leaders for virtually all image restoration tasks. Especially in the domain of microscopy images, various content-aware image restoration (CARE) approaches are now used to improve…

Incremental learning (IL) aims to overcome catastrophic forgetting of previous tasks while learning new ones. Existing IL methods make strong assumptions that the incoming task type will either only increases new classes or domains (i.e.…

Existing self-supervised learning methods learn representation by means of pretext tasks which are either (1) discriminating that explicitly specify which features should be separated or (2) aligning that precisely indicate which features…

Recent Vision-Language Pre-trained (VLP) models based on dual encoder have attracted extensive attention from academia and industry due to their superior performance on various cross-modal tasks and high computational efficiency. They…

Vision transformers combined with self-supervised learning have enabled the development of models which scale across large datasets for several downstream tasks like classification, segmentation and detection. The low-shot learning…

Humans can identify objects following various spatial transformations such as scale and viewpoint. This extends to novel objects, after a single presentation at a single pose, sometimes referred to as online invariance. CNNs have been…

Deep image translation methods have recently shown excellent results, outputting high-quality images covering multiple modes of the data distribution. There has also been increased interest in disentangling the internal representations…

Unsupervised pre-training has emerged as a transformative paradigm, displaying remarkable advancements in various domains. However, the susceptibility to domain shift, where pre-training data distribution differs from fine-tuning, poses a…

Recent years have witnessed the rise and success of pre-training techniques in visually-rich document understanding. However, most existing methods lack the systematic mining and utilization of layout-centered knowledge, leading to…

Representation learning constitutes a pivotal cornerstone in contemporary deep learning paradigms, offering a conduit to elucidate distinctive features within the latent space and interpret the deep models. Nevertheless, the inherent…

Physics-driven deep learning (PD-DL) models have proven to be a powerful approach for improved reconstruction of rapid MRI scans. In order to train these models in scenarios where fully-sampled reference data is unavailable, self-supervised…

Domain incremental learning (DIL) poses a significant challenge in real-world scenarios, as models need to be sequentially trained on diverse domains over time, all the while avoiding catastrophic forgetting. Mitigating representation…

Multiple Instance Learning (MIL), a powerful strategy for weakly supervised learning, is able to perform various prediction tasks on gigapixel Whole Slide Images (WSIs). However, the tens of thousands of patches in WSIs usually incur a vast…

Visual grounding aims to align visual information of specific regions of images with corresponding natural language expressions. Current visual grounding methods leverage pre-trained visual and language backbones independently to obtain…

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…

Recently unsupervised learning of depth from videos has made remarkable progress and the results are comparable to fully supervised methods in outdoor scenes like KITTI. However, there still exist great challenges when directly applying…

Self-supervised learning methods have witnessed a recent surge of interest after proving successful in multiple application fields. In this work, we leverage these techniques, and we propose 3D versions for five different self-supervised…