相关论文: Test-Time Training for Semantic Segmentation with …

Detecting lane markings in road scenes poses a challenge due to their intricate nature, which is susceptible to unfavorable conditions. While lane markings have strong shape priors, their visibility is easily compromised by lighting…

A key requirement for the success of supervised deep learning is a large labeled dataset - a condition that is difficult to meet in medical image analysis. Self-supervised learning (SSL) can help in this regard by providing a strategy to…

Despite its empirical success, the theoretical foundations of self-supervised contrastive learning (CL) are not yet fully established. In this work, we address this gap by showing that standard CL objectives implicitly approximate a…

Self-supervised pre-training with contrastive learning is a powerful method for learning from sparsely labeled data. However, performance can drop considerably when there is a shift in the distribution of data from training to test time. We…

Obtaining labelled ECG data for developing supervised models is challenging. Contrastive learning (CL) has emerged as a promising pretraining approach that enables effective transfer learning with limited labelled data. However, existing CL…

Deep networks trained on the source domain show degraded performance when tested on unseen target domain data. To enhance the model's generalization ability, most existing domain generalization methods learn domain invariant features by…

We propose Domain-Conditioned Meta-Contrastive Learning, a framework for improving the cross-domain generalization of vision-language models. While contrastive models such as CLIP achieve strong performance through large-scale training,…

Human beings can quickly adapt to environmental changes by leveraging learning experience. However, the poor ability of adapting to dynamic environments remains a major challenge for AI models. To better understand this issue, we study the…

Contrastive learning (CL) continuously achieves significant breakthroughs across multiple domains. However, the most common InfoNCE-based methods suffer from some dilemmas, such as \textit{uniformity-tolerance dilemma} (UTD) and…

There are a number of studies about extraction of bottleneck (BN) features from deep neural networks (DNNs)trained to discriminate speakers, pass-phrases and triphone states for improving the performance of text-dependent speaker…

Transformations in the input space of Deep Neural Networks (DNN) lead to unintended changes in the feature space. Almost perceptually identical inputs, such as adversarial examples, can have significantly distant feature representations. On…

Domain adaptation is one of the most crucial techniques to mitigate the domain shift problem, which exists when transferring knowledge from an abundant labeled sourced domain to a target domain with few or no labels. Partial domain…

In recent years, the introduction of self-supervised contrastive learning (SSCL) has demonstrated remarkable improvements in representation learning across various domains, including natural language processing and computer vision. By…

Model quantization is critical for deploying large language models (LLMs) on resource-constrained hardware, yet recent work has revealed severe security risks that benign LLMs in full precision may exhibit malicious behaviors after…

This work considers supervised contrastive learning for semantic segmentation. We apply contrastive learning to enhance the discriminative power of the multi-scale features extracted by semantic segmentation networks. Our key methodological…

The effectiveness of contrastive learning technology in natural language processing tasks is yet to be explored and analyzed. How to construct positive and negative samples correctly and reasonably is the core challenge of contrastive…

Cross-domain sentiment analysis aims to predict the sentiment of texts in the target domain using the model trained on the source domain to cope with the scarcity of labeled data. Previous studies are mostly cross-entropy-based methods for…

Contrastive representation learning (CRL) underpins many modern foundation models. Despite recent theoretical progress, existing analyses suffer from several key limitations: (i) the statistical consistency of CRL remains poorly understood;…

Recently, Miller et al. (2021) and Baek et al. (2022) empirically demonstrated strong linear correlations between in-distribution (ID) versus out-of-distribution (OOD) accuracy and agreement. These trends, coined accuracy-on-the-line (ACL)…

Deploying models on target domain data subject to distribution shift requires adaptation. Test-time training (TTT) emerges as a solution to this adaptation under a realistic scenario where access to full source domain data is not available…