Papers › Boosting Contrastive Self-Supervised Learning with False Negative Cancellation
Boosting Contrastive Self-Supervised Learning with False Negative Cancellation
Tri Huynh, Simon Kornblith, Matthew R. Walter, Michael Maire, Maryam Khademi
Self-supervised representation learning has made significant leaps fueled by progress in contrastive learning, which seeks to learn transformations that embed positive input pairs nearby, while pushing negative pairs far apart. While positive pairs can be generated reliably (e.g., as different views of the same image), it is difficult to accurately establish negative pairs, defined as samples from different images regardless of their semantic content or visual features. A fundamental problem in contrastive learning is mitigating the effects of false negatives. Contrasting false negatives induces two critical issues in representation learning: discarding semantic information and slow convergence. In this paper, we propose novel approaches to identify false negatives, as well as two strategies to mitigate their effect, i.e. false negative elimination and attraction, while systematically performing rigorous evaluations to study this problem in detail. Our method exhibits consistent improvements over existing contrastive learning-based methods. Without labels, we identify false negatives with 40% accuracy among 1000 semantic classes on ImageNet, and achieve 5.8% absolute improvement in top-1 accuracy over the previous state-of-the-art when finetuning with 1% labels. Our code is available at https://github.com/google-research/fnc.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Self-Supervised Image Classification | ImageNet | FNC (ResNet-50) | Number of Params | 24M | #84 of 144 | Archive leaderboard | report |
| Self-Supervised Image Classification | ImageNet | FNC (ResNet-50) | Top 1 Accuracy | 74.4% | #84 of 144 | Archive leaderboard | report |
| Self-Supervised Image Classification | ImageNet | FNC (ResNet-50) | Top 5 Accuracy | 91.8% | #84 of 144 | Archive leaderboard | report |
| Semi-Supervised Image Classification | ImageNet - 1% labeled data | FNC (ResNet-50) | Top 1 Accuracy | 63.7% | #32 of 65 | Archive leaderboard | report |
| Semi-Supervised Image Classification | ImageNet - 1% labeled data | FNC (ResNet-50) | Top 5 Accuracy | 85.3% | #32 of 65 | 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
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