Papers › Similarity Contrastive Estimation for Image and Video Soft Contrastive Self-Supervised Learning

Similarity Contrastive Estimation for Image and Video Soft Contrastive Self-Supervised Learning

21 Dec 2022arXiv:2212.11187archive 2025-07-28

Julien Denize, Jaonary Rabarisoa, Astrid Orcesi, Romain Hérault

Contrastive representation learning has proven to be an effective self-supervised learning method for images and videos. Most successful approaches are based on Noise Contrastive Estimation (NCE) and use different views of an instance as positives that should be contrasted with other instances, called negatives, that are considered as noise. However, several instances in a dataset are drawn from the same distribution and share underlying semantic information. A good data representation should contain relations between the instances, or semantic similarity and dissimilarity, that contrastive learning harms by considering all negatives as noise. To circumvent this issue, we propose a novel formulation of contrastive learning using semantic similarity between instances called Similarity Contrastive Estimation (SCE). Our training objective is a soft contrastive one that brings the positives closer and estimates a continuous distribution to push or pull negative instances based on their learned similarities. We validate empirically our approach on both image and video representation learning. We show that SCE performs competitively with the state of the art on the ImageNet linear evaluation protocol for fewer pretraining epochs and that it generalizes to several downstream image tasks. We also show that SCE reaches state-of-the-art results for pretraining video representation and that the learned representation can generalize to video downstream tasks.

PaperPDFCode

Code

juliendenize/eztorch officialpytorchNOASSERTION report
cea-list/sce mentioned on GitHubpytorchNOASSERTION report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Contrastive LearningLinear evaluationRepresentation LearningSelf-Supervised Action RecognitionSelf-Supervised LearningSelf-supervised Video RetrievalSemantic SimilaritySemantic Textual Similarity

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Self-Supervised Action Recognition HMDB51 SCE (R3D-50) Frozen false #4 of 48 Archive leaderboard report
Self-Supervised Action Recognition HMDB51 SCE (R3D-50) Pre-Training Dataset Kinetics400 #4 of 48 Archive leaderboard report
Self-Supervised Action Recognition HMDB51 SCE (R3D-50) Top-1 Accuracy 74.7 #4 of 48 Archive leaderboard report
Self-Supervised Action Recognition UCF101 SCE (R3D-50) 3-fold Accuracy 95.3 #7 of 53 Archive leaderboard report
Self-Supervised Action Recognition UCF101 SCE (R3D-50) Frozen false #7 of 53 Archive leaderboard report
Self-Supervised Action Recognition UCF101 SCE (R3D-50) Pre-Training Dataset Kinetics400 #7 of 53 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Contrastive Learning

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections