Related papers: Modulate Your Spectrum in Self-Supervised Learning

Self-supervised learning (SSL) can be used to solve complex visual tasks without human labels. Self-supervised representations encode useful semantic information about images, and as a result, they have already been used for tasks such as…

Recent advances of deep learning have achieved remarkable performances in various challenging computer vision tasks. Especially in object localization, deep convolutional neural networks outperform traditional approaches based on extraction…

Image steganalysis is a special binary classification problem that aims to classify natural cover images and suspected stego images which are the results of embedding very weak secret message signals into covers. How to effectively suppress…

Recent years have witnessed tremendous success in Self-Supervised Learning (SSL), which has been widely utilized to facilitate various downstream tasks in Computer Vision (CV) and Natural Language Processing (NLP) domains. However,…

It is commonly recognized that color variations caused by differences in stains is a critical issue for histopathology image analysis. Existing methods adopt color matching, stain separation, stain transfer or the combination of them to…

Sentence embedding is a cornerstone in NLP. Whitening has been claimed to be an effective operation to improve embedding quality obtained from Large Language Models (LLMs). However, we find that the efficacy of whitening is model-dependent…

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…

We propose universally slimmable self-supervised learning (dubbed as US3L) to achieve better accuracy-efficiency trade-offs for deploying self-supervised models across different devices. We observe that direct adaptation of self-supervised…

Spectral Embedding (SE) has often been used to map data points from non-linear manifolds to linear subspaces for the purpose of classification and clustering. Despite significant advantages, the subspace structure of data in the original…

Self-supervised representation learning (SSL) methods provide an effective label-free initial condition for fine-tuning downstream tasks. However, in numerous realistic scenarios, the downstream task might be biased with respect to the…

Supervised learning methods have been found to exhibit inductive biases favoring simpler features. When such features are spuriously correlated with the label, this can result in suboptimal performance on minority subgroups. Despite the…

Self-Supervised Learning (SSL) surmises that inputs and pairwise positive relationships are enough to learn meaningful representations. Although SSL has recently reached a milestone: outperforming supervised methods in many modalities\dots…

We present streaming self-training (SST) that aims to democratize the process of learning visual recognition models such that a non-expert user can define a new task depending on their needs via a few labeled examples and minimal domain…

Training implicit neural representations (INRs) to capture fine-scale details typically relies on iterative backpropagation and is often hindered by spectral bias when the target exhibits highly non-uniform frequency content. We propose…

Self-supervised learning (SSL) models confront challenges of abrupt informational collapse or slow dimensional collapse. We propose TriNet, which introduces a novel triple-branch architecture for preventing collapse and stabilizing the…

We propose a novel theoretical framework to understand contrastive self-supervised learning (SSL) methods that employ dual pairs of deep ReLU networks (e.g., SimCLR). First, we prove that in each SGD update of SimCLR with various loss…

Recent advances in image-level self-supervised learning (SSL) have made significant progress, yet learning dense representations for patches remains challenging. Mainstream methods encounter an over-dispersion phenomenon that patches from…

Deep learning has been a prevalence in computational chemistry and widely implemented in molecule property predictions. Recently, self-supervised learning (SSL), especially contrastive learning (CL), gathers growing attention for the…

Self-Supervised Learning (SSL) is a paradigm that leverages unlabeled data for model training. Empirical studies show that SSL can achieve promising performance in distribution shift scenarios, where the downstream and training…

Self-supervised learning for inverse problems allows to train a reconstruction network from noise and/or incomplete data alone. These methods have the potential of enabling learning-based solutions when obtaining ground-truth references for…