paper-with-me

홈 › Papers

InstanT: Semi-supervised Learning with Instance-dependent Thresholds

2023-10-29 · NeurIPS 2023 11

Semi-supervised learning (SSL) has been a fundamental challenge in machine learning for decades. The primary family of SSL algorithms, known as pseudo-labeling, involves assigning pseudo-labels to confident unlabeled instances and incorporating them into the training set. Therefore, the selection criteria of confident instances are crucial to the success of SSL. Recently, there has been growing interest in the development of SSL methods that use dynamic or adaptive thresholds. Yet, these methods typically apply the same threshold to all samples, or use class-dependent thresholds for instances belonging to a certain class, while neglecting instance-level information. In this paper, we propose the study of instance-dependent thresholds, which has the highest degree of freedom compared with existing methods. Specifically, we devise a novel instance-dependent threshold function for all unlabeled instances by utilizing their instance-level ambiguity and the instance-dependent error rates of pseudo-labels, so instances that are more likely to have incorrect pseudo-labels will have higher thresholds. Furthermore, we demonstrate that our instance-dependent threshold function provides a bounded probabilistic guarantee for the correctness of the pseudo-labels it assigns.

📄 PDF Abstract BibTeX arXiv:2310.18910

Code (1)

tmllab/2023_neurips_instant pytorch

Similar Papers 제목 키워드 기반

Pixelwise Instance Segmentation with a Dynamically Instantiated Network

2017-04-07 · CVPR 2017 7 · Anurag Arnab, Philip H. S. Torr

Semantic segmentation and object detection research have recently achieved rapid progress. However, the former task has no notion of different instances of the same object, and the latter operates at a coarse, bounding-b…

Instance SegmentationObjectobject-detectionObject Detection+3

Semi-Supervised and Long-Tailed Object Detection with CascadeMatch

2023-05-24 · Yuhang Zang, Kaiyang Zhou, Chen Huang, Chen Change Loy

This paper focuses on long-tailed object detection in the semi-supervised learning setting, which poses realistic challenges, but has rarely been studied in the literature. We propose a novel pseudo-labeling-based detect…

Long-tailed Object DetectionObjectobject-detectionObject Detection+1

Dual-Decoupling Learning and Metric-Adaptive Thresholding for Semi-Supervised Multi-Label Learning

2024-07-26 · Jia-Hao Xiao, Ming-Kun Xie, Heng-Bo Fan, Gang Niu 외

Semi-supervised multi-label learning (SSMLL) is a powerful framework for leveraging unlabeled data to reduce the expensive cost of collecting precise multi-label annotations. Unlike semi-supervised learning, one cannot s…

Multi-Label LearningPseudo Label

SimMatch: Semi-supervised Learning with Similarity Matching

2022-03-14 · CVPR 2022 1 · Mingkai Zheng, Shan You, Lang Huang, Fei Wang 외

Learning with few labeled data has been a longstanding problem in the computer vision and machine learning research community. In this paper, we introduced a new semi-supervised learning framework, SimMatch, which simult…

Semantic SimilaritySemantic Textual SimilaritySemi-Supervised Image Classification

Feedback-Driven Pseudo-Label Reliability Assessment: Redefining Thresholding for Semi-Supervised Semantic Segmentation

2025-05-12 · Negin Ghamsarian, Sahar Nasirihaghighi, Klaus Schoeffmann, Raphael Sznitman

Semi-supervised learning leverages unlabeled data to enhance model performance, addressing the limitations of fully supervised approaches. Among its strategies, pseudo-supervision has proven highly effective, typically r…

Pseudo LabelPseudo Label FilteringSemantic SegmentationSemi-Supervised Semantic Segmentation