Related papers: Virtual embeddings and self-consistency for self-s…
Self-supervised learning (SSL) has made enormous progress and largely narrowed the gap with the supervised ones, where the representation learning is mainly guided by a projection into an embedding space. During the projection, current…
Although supervised learning has been highly successful in improving the state-of-the-art in the domain of image-based computer vision in the past, the margin of improvement has diminished significantly in recent years, indicating that a…
Self-supervised learning (SSL) is a technique for learning useful representations from unlabeled data. It has been applied effectively to domain adaptation (DA) on images and videos. It is still unknown if and how it can be leveraged for…
The recently advanced unsupervised learning approaches use the siamese-like framework to compare two "views" from the same image for learning representations. Making the two views distinctive is a core to guarantee that unsupervised methods…
A major limitation in applying deep learning to artificial intelligence (AI) systems is the scarcity of high-quality curated datasets. We investigate strong augmentation based self-supervised learning (SSL) techniques to address this…
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…
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…
Image-level weak-to-strong consistency serves as the predominant paradigm in semi-supervised learning~(SSL) due to its simplicity and impressive performance. Nonetheless, this approach confines all perturbations to the image level and…
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…
Existing data augmentation in self-supervised learning, while diverse, fails to preserve the inherent structure of natural images. This results in distorted augmented samples with compromised semantic information, ultimately impacting…
Data augmentation improves the generalization power of deep learning models by synthesizing more training samples. Sample-mixing is a popular data augmentation approach that creates additional data by combining existing samples. Recent…
Semi-supervised learning (SSL) provides an effective means of leveraging unlabeled data to improve a model's performance. In this paper, we demonstrate the power of a simple combination of two common SSL methods: consistency regularization…
Effective suppression of surface-related multiples is essential to prevent imaging artifacts and erroneous structural interpretations. While conventional approaches rely on accurate priors or subsurface model knowledge, and supervised…
A key factor in effective Self-Supervised learning (SSL) is preventing dimensional collapse, where higher-dimensional representation spaces ($R$) span a lower-dimensional subspace. Therefore, SSL optimization strategies involve guiding a…
Recent studies on semi-supervised learning (SSL) have achieved great success. Despite their promising performance, current state-of-the-art methods tend toward increasingly complex designs at the cost of introducing more network components…
CutMix is a vital augmentation strategy that determines the performance and generalization ability of vision transformers (ViTs). However, the inconsistency between the mixed images and the corresponding labels harms its efficacy. Existing…
As a newly emerging unsupervised learning paradigm, self-supervised learning (SSL) recently gained widespread attention, which usually introduces a pretext task without manual annotation of data. With its help, SSL effectively learns the…
Self-supervised learning (SSL) has recently shown remarkable results in closing the gap between supervised and unsupervised learning. The idea is to learn robust features that are invariant to distortions of the input data. Despite its…
Graph representation learning has emerged as a cornerstone for tasks like node classification and link prediction, yet prevailing self-supervised learning (SSL) methods face challenges such as computational inefficiency, reliance on…
Deep learning highly relies on the amount of annotated data. However, annotating medical images is extremely laborious and expensive. To this end, self-supervised learning (SSL), as a potential solution for deficient annotated data,…