paper-with-me

홈 › Papers

Contrastive Learning of Image Representations with Cross-Video Cycle-Consistency

2021-05-13 · ICCV 2021 10 · Haiping Wu, Xiaolong Wang

Recent works have advanced the performance of self-supervised representation learning by a large margin. The core among these methods is intra-image invariance learning. Two different transformations of one image instance are considered as a positive sample pair, where various tasks are designed to learn invariant representations by comparing the pair. Analogically, for video data, representations of frames from the same video are trained to be closer than frames from other videos, i.e. intra-video invariance. However, cross-video relation has barely been explored for visual representation learning. Unlike intra-video invariance, ground-truth labels of cross-video relation is usually unavailable without human labors. In this paper, we propose a novel contrastive learning method which explores the cross-video relation by using cycle-consistency for general image representation learning. This allows to collect positive sample pairs across different video instances, which we hypothesize will lead to higher-level semantics. We validate our method by transferring our image representation to multiple downstream tasks including visual object tracking, image classification, and action recognition. We show significant improvement over state-of-the-art contrastive learning methods. Project page is available at https://happywu.github.io/cycle_contrast_video.

📄 PDF Abstract BibTeX arXiv:2105.06463

Code (0)

등록된 구현이 없습니다.

Tasks

Action RecognitionContrastive Learningimage-classificationImage ClassificationObject TrackingRelationRepresentation LearningVisual Object Tracking

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Cycle-Contrast for Self-Supervised Video Representation Learning

2020-10-28 · NeurIPS 2020 12 · Quan Kong, Wenpeng Wei, Ziwei Deng, Tomoaki Yoshinaga 외

We present Cycle-Contrastive Learning (CCL), a novel self-supervised method for learning video representation. Following a nature that there is a belong and inclusion relation of video and its frames, CCL is designed to …

Action RecognitionContrastive LearningRepresentation LearningRetrieval+1

DGGAN: Degradation Guided Generative Adversarial Network for Real-time Endoscopic Video Enhancement

2025-12-08 · Handing Xu, Zhenguo Nie, Tairan Peng, Huimin Pan 외 arxiv

Endoscopic surgery relies on intraoperative video, making image quality a decisive factor for surgical safety and efficacy. Yet, endoscopic videos are often degraded by uneven illumination, tissue scattering, occlusions,…

Contrastive LearningImage EnhancementVideo Enhancement

CycleCL: Self-supervised Learning for Periodic Videos

2023-11-05 · Matteo Destro, Michael Gygli

Analyzing periodic video sequences is a key topic in applications such as automatic production systems, remote sensing, medical applications, or physical training. An example is counting repetitions of a physical exercis…

Contrastive LearningSelf-Supervised LearningTriplet

Unsupervised Contrastive Learning of Image Representations from Ultrasound Videos with Hard Negative Mining

2022-07-26 · Soumen Basu, Somanshu Singla, Mayank Gupta, Pratyaksha Rana 외

Rich temporal information and variations in viewpoints make video data an attractive choice for learning image representations using unsupervised contrastive learning (UCL) techniques. State-of-the-art (SOTA) contrastive…

Contrastive Learning

Towards Contrastive Learning in Music Video Domain

2023-09-01 · Karel Veldkamp, Mariya Hendriksen, Zoltán Szlávik, Alexander Keijser

Contrastive learning is a powerful way of learning multimodal representations across various domains such as image-caption retrieval and audio-visual representation learning. In this work, we investigate if these finding…

Contrastive LearningGenre classificationMusic TaggingRepresentation Learning+1