相关论文: Did Models Sufficient Learn? Attribution-Guided Tr…

Recent advances in unsupervised domain adaptation mainly focus on learning shared representations by global distribution alignment without considering class information across domains. The neglect of class information, however, may lead to…

The field of generating recommendations within the framework of causal inference has seen a recent surge, with recommendations being likened to treatments. This approach enhances insights into the influence of recommendations on user…

Semi-supervised temporal action segmentation (SS-TA) aims to perform frame-wise classification in long untrimmed videos, where only a fraction of videos in the training set have labels. Recent studies have shown the potential of contrastive…

Deep learning (DL) techniques are highly effective for defect detection from images. Training DL classification models, however, requires vast amounts of labeled data which is often expensive to collect. In many cases, not only the…

By leveraging data from a fully labeled source domain, unsupervised domain adaptation (UDA) improves classification performance on an unlabeled target domain through explicit discrepancy minimization of data distribution or adversarial…

In this work, we present Con$^{2}$DA, a simple framework that extends recent advances in semi-supervised learning to the semi-supervised domain adaptation (SSDA) problem. Our framework generates pairs of associated samples by performing…

Training-data attribution for vision generative models aims to identify which training data influenced a given output. While most methods score individual examples, practitioners often need group-level answers (e.g., artistic styles or…

Many fine-grained classification tasks, like rare animal identification, have limited training data and consequently classifiers trained on these datasets often fail to generalize to variations in the domain like changes in weather or…

In the context of supervised statistical learning, it is typically assumed that the training set comes from the same distribution that draws the test samples. When this is not the case, the behavior of the learned model is unpredictable and…

Diffusion models (DMs) have achieved remarkable success in image and video generation. However, they still struggle with (1) physical alignment and (2) out-of-distribution (OOD) instruction following. We argue that these issues stem from…

Contrastive learning has led to substantial improvements in the quality of learned embedding representations for tasks such as image classification. However, a key drawback of existing contrastive augmentation methods is that they may lead…

In biomedical engineering, artificial intelligence has become a pivotal tool for enhancing medical diagnostics, particularly in medical image classification tasks such as detecting pneumonia from chest X-rays and breast cancer screening.…

This paper proposes Mutual Information Regularized Assignment (MIRA), a pseudo-labeling algorithm for unsupervised representation learning inspired by information maximization. We formulate online pseudo-labeling as an optimization problem…

In semi-supervised learning, unlabeled samples can be utilized through augmentation and consistency regularization. However, we observed certain samples, even undergoing strong augmentation, are still correctly classified with high…

Conformal prediction is a powerful distribution-free tool for uncertainty quantification, establishing valid prediction intervals with finite-sample guarantees. To produce valid intervals which are also adaptive to the difficulty of each…

Deep learning models have demonstrated exceptional performance across a wide range of computer vision tasks. However, their performance often degrades significantly when faced with distribution shifts, such as domain or dataset changes.…

Learning deep neural networks that are generalizable across different domains remains a challenge due to the problem of domain shift. Unsupervised domain adaptation is a promising avenue which transfers knowledge from a source domain to a…

This paper introduces a novel dual-region augmentation approach designed to reduce reliance on large-scale labeled datasets while improving model robustness and adaptability across diverse computer vision tasks, including source-free domain…

Image classification models tend to make decisions based on peripheral attributes of data items that have strong correlation with a target variable (i.e., dataset bias). These biased models suffer from the poor generalization capability…

Deep learning models can perform well in complex medical imaging classification tasks, even when basing their conclusions on spurious correlations (i.e. confounders), should they be prevalent in the training dataset, rather than on the…