paper-with-me

Papers

Contrasting quadratic assignments for set-based representation learning

2022-05-31 · Artem Moskalev, Ivan Sosnovik, Volker Fischer, Arnold Smeulders

The standard approach to contrastive learning is to maximize the agreement between different views of the data. The views are ordered in pairs, such that they are either positive, encoding different views of the same object, or negative, corresponding to views of different objects. The supervisory signal comes from maximizing the total similarity over positive pairs, while the negative pairs are needed to avoid collapse. In this work, we note that the approach of considering individual pairs cannot account for both intra-set and inter-set similarities when the sets are formed from the views of the data. It thus limits the information content of the supervisory signal available to train representations. We propose to go beyond contrasting individual pairs of objects by focusing on contrasting objects as sets. For this, we use combinatorial quadratic assignment theory designed to evaluate set and graph similarities and derive set-contrastive objective as a regularizer for contrastive learning methods. We conduct experiments and demonstrate that our method improves learned representations for the tasks of metric learning and self-supervised classification.

📄 PDF Abstract BibTeX arXiv:2205.15814

Code (1)

amoskalev/contrasting_quadratic 공식 구현 pytorch

Tasks

Contrastive LearningMetric LearningRepresentation Learning

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Graph Representation Learning via Contrasting Cluster Assignments

2021-12-15 · ChunYang Zhang, Hongyu Yao, C. L. Philip Chen, Yuena Lin

With the rise of contrastive learning, unsupervised graph representation learning has been booming recently, even surpassing the supervised counterparts in some machine learning tasks. Most of existing contrastive models…

ClusteringContrastive LearningGraph Representation LearningRepresentation Learning

Deep Multiview Clustering by Contrasting Cluster Assignments

2023-04-21 · ICCV 2023 1 · Jie Chen, Hua Mao, Wai Lok Woo, Xi Peng

Multiview clustering (MVC) aims to reveal the underlying structure of multiview data by categorizing data samples into clusters. Deep learning-based methods exhibit strong feature learning capabilities on large-scale dat…

ClusteringContrastive LearningMultiview Clustering

Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting

2021-06-18 · Martine Toering, Ioannis Gatopoulos, Maarten Stol, Vincent Tao Hu

Instance-level contrastive learning techniques, which rely on data augmentation and a contrastive loss function, have found great success in the domain of visual representation learning. They are not suitable for exploit…

Action RecognitionAction Recognition In VideosContrastive LearningData Augmentation+9

Soft Contrastive Learning for Time Series

2023-12-27 · Seunghan Lee, Taeyoung Park, Kibok Lee

Contrastive learning has shown to be effective to learn representations from time series in a self-supervised way. However, contrasting similar time series instances or values from adjacent timestamps within a time serie…

Anomaly DetectionContrastive LearningTime SeriesTransfer Learning

Unsupervised Learning of Visual Features by Contrasting Cluster Assignments

2020-06-17 · NeurIPS 2020 12 · Mathilde Caron, Ishan Misra, Julien Mairal, Priya Goyal 외

Unsupervised image representations have significantly reduced the gap with supervised pretraining, notably with the recent achievements of contrastive learning methods. These contrastive methods typically work online and…

Contrastive LearningData AugmentationImage ClassificationSelf-Supervised Image Classification+1