paper-with-me

홈 › Papers

Demystifying Contrastive Self-Supervised Learning: Invariances, Augmentations and Dataset Biases

2020-07-28 · NeurIPS 2020 12 · Senthil Purushwalkam, Abhinav Gupta

Self-supervised representation learning approaches have recently surpassed their supervised learning counterparts on downstream tasks like object detection and image classification. Somewhat mysteriously the recent gains in performance come from training instance classification models, treating each image and it's augmented versions as samples of a single class. In this work, we first present quantitative experiments to demystify these gains. We demonstrate that approaches like MOCO and PIRL learn occlusion-invariant representations. However, they fail to capture viewpoint and category instance invariance which are crucial components for object recognition. Second, we demonstrate that these approaches obtain further gains from access to a clean object-centric training dataset like Imagenet. Finally, we propose an approach to leverage unstructured videos to learn representations that possess higher viewpoint invariance. Our results show that the learned representations outperform MOCOv2 trained on the same data in terms of invariances encoded and the performance on downstream image classification and semantic segmentation tasks.

📄 PDF Abstract BibTeX arXiv:2007.13916

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationGeneral Classificationimage-classificationImage ClassificationObjectobject-detectionObject DetectionObject RecognitionRepresentation LearningSelf-Supervised LearningSemantic Segmentation

Methods 이 논문이 사용한 방법론

Jigsaw Jigsaw is a self-supervision approach that relies on jigsaw-like puzzles as the pretext task in order to learn image representations.
PIRL Pretext-Invariant Representation Learning (PIRL, pronounced as “pearl”) learns invariant representations based on pretext tasks. PIRL is used with a commonly used pretext task…
Batch Normalization 설명 없음
InfoNCE 설명 없음
MoCo 설명 없음

Similar Papers 제목 키워드 기반

A Theoretical Characterization of Optimal Data Augmentations in Self-Supervised Learning

2024-11-04 · Shlomo Libo Feigin, Maximilian Fleissner, Debarghya Ghoshdastidar

Data augmentations play an important role in the recent success of Self-Supervised Learning (SSL). While commonly viewed as encoding invariances into the learned representations, this interpretation overlooks the impact …

Self-Supervised Learning

Amortised Invariance Learning for Contrastive Self-Supervision

2023-02-24 · Ruchika Chavhan, Henry Gouk, Jan Stuehmer, Calum Heggan 외

Contrastive self-supervised learning methods famously produce high quality transferable representations by learning invariances to different data augmentations. Invariances established during pre-training can be interpre…

Contrastive LearningRepresentation LearningSelf-Supervised Learning

Domain Confused Contrastive Learning for Unsupervised Domain Adaptation

2022-07-10 · NAACL 2022 7 · Quanyu Long, Tianze Luo, Wenya Wang, Sinno Jialin Pan

In this work, we study Unsupervised Domain Adaptation (UDA) in a challenging self-supervised approach. One of the difficulties is how to learn task discrimination in the absence of target labels. Unlike previous literatu…

Contrastive LearningDomain AdaptationUnsupervised Domain Adaptation

Skeleton-Contrastive 3D Action Representation Learning

2021-08-08 · Fida Mohammad Thoker, Hazel Doughty, Cees G. M. Snoek

This paper strives for self-supervised learning of a feature space suitable for skeleton-based action recognition. Our proposal is built upon learning invariances to input skeleton representations and various skeleton au…

Action RecognitionContrastive LearningFew-Shot Skeleton-Based Action RecognitionRepresentation Learning+4

Automatic Data Augmentation Selection and Parametrization in Contrastive Self-Supervised Speech Representation Learning

2022-04-08 · Salah Zaiem, Titouan Parcollet, Slim Essid

Contrastive learning enables learning useful audio and speech representations without ground-truth labels by maximizing the similarity between latent representations of similar signal segments. In this framework various …

Contrastive LearningData AugmentationRepresentation LearningSpeech Representation Learning