相关论文: On the Out-of-Distribution Generalization of Self-…

We evaluate the out-of-distribution (OOD) detection performance of self-supervised learning (SSL) techniques with a new evaluation framework. Unlike the previous evaluation methods, the proposed framework adjusts the distance of OOD samples…

Recent semi-supervised learning algorithms have demonstrated greater success with higher overall performance due to better-unlabeled data representations. Nonetheless, recent research suggests that the performance of the SSL algorithm can…

This work addresses the task of self-supervised learning (SSL) on a long-tailed dataset that aims to learn balanced and well-separated representations for downstream tasks such as image classification. This task is crucial because the real…

Though Self-supervised learning (SSL) has been widely studied as a promising technique for representation learning, it doesn't generalize well on long-tailed datasets due to the majority classes dominating the feature space. Recent work…

When there are unlabeled Out-Of-Distribution (OOD) data from other classes, Semi-Supervised Learning (SSL) methods suffer from severe performance degradation and even get worse than merely training on labeled data. In this paper, we…

Semi-supervised learning (semi-SL) is a promising alternative to supervised learning for medical image analysis when obtaining good quality supervision for medical imaging is difficult. However, semi-SL assumes that the underlying…

Self-supervised learning (SSL) has achieved great success in a variety of computer vision tasks. However, the mechanism of how SSL works in these tasks remains a mystery. In this paper, we study how SSL can enhance the performance of the…

Semi-supervised learning (SSL) has been proposed to leverage unlabeled data for training powerful models when only limited labeled data is available. While existing SSL methods assume that samples in the labeled and unlabeled data share the…

In this paper, we address a complex but practical scenario in semi-supervised learning (SSL) named open-set SSL, where unlabeled data contain both in-distribution (ID) and out-of-distribution (OOD) samples. Unlike previous methods that only…

Open-set semi-supervised learning (open-set SSL) investigates a challenging but practical scenario where out-of-distribution (OOD) samples are contained in the unlabeled data. While the mainstream technique seeks to completely filter out…

Recent advances in robust semi-supervised learning (SSL) typically filter out-of-distribution (OOD) information at the sample level. We argue that an overlooked problem of robust SSL is its corrupted information on semantic level,…

Traditional machine learning paradigms are based on the assumption that both training and test data follow the same statistical pattern, which is mathematically referred to as Independent and Identically Distributed ($i.i.d.$). However, in…

In open-set semi-supervised learning (OSSL), we consider unlabeled datasets that may contain unknown classes. Existing OSSL methods often use the softmax confidence for classifying data as in-distribution (ID) or out-of-distribution (OOD).…

Self Supervised learning (SSL) has demonstrated its effectiveness in feature learning from unlabeled data. Regarding this success, there have been some arguments on the role that mutual information plays within the SSL framework. Some works…

Semi-supervised Learning (SSL) has been proven vulnerable to out-of-distribution (OOD) samples in realistic large-scale unsupervised datasets due to over-confident pseudo-labeling OODs as in-distribution (ID). A key underlying problem is…

Numerous machine learning (ML) models have been developed, including those for software engineering (SE) tasks, under the assumption that training and testing data come from the same distribution. However, training and testing distributions…

Out-of-distribution (OOD) detection is the key to deploying models safely in the open world. For OOD detection, collecting sufficient in-distribution (ID) labeled data is usually more time-consuming and costly than unlabeled data. When ID…

The discrepancy between in-distribution (ID) and out-of-distribution (OOD) samples can lead to \textit{distributional vulnerability} in deep neural networks, which can subsequently lead to high-confidence predictions for OOD samples. This…

Self-supervised learning (SSL) is now a serious competitor for supervised learning, even though it does not require data annotation. Several baselines have attempted to make SSL models exploit information about data distribution, and less…

Open-set semi-supervised learning (OSSL) leverages practical open-set unlabeled data, comprising both in-distribution (ID) samples from seen classes and out-of-distribution (OOD) samples from unseen classes, for semi-supervised learning…