# Boosting Contrastive Self-Supervised Learning with False Negative Cancellation

arXiv: https://arxiv.org/abs/2011.11765 · HTML: https://mlsanity.com/paper/2011.11765/

## Key facts

- Cited by 119 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Nov 2020.

## Built on by (most cited first, 30 of 119)

- [On Feature Decorrelation in Self-Supervised Learning](https://mlsanity.com/paper/2105.00470/) (2021)
- [Pixel Contrastive-Consistent Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2108.09025/) (2021)
- [SimKGC: Simple Contrastive Knowledge Graph Completion with Pre-trained Language Models](https://mlsanity.com/paper/2203.02167/) (2022)
- [PromptCAL: Contrastive Affinity Learning via Auxiliary Prompts for Generalized Novel Category Discovery](https://mlsanity.com/paper/2212.05590/) (2022)
- [Weakly Supervised Contrastive Learning](https://mlsanity.com/paper/2110.04770/) (2021)
- [Best of Both Worlds: Multimodal Contrastive Learning with Tabular and Imaging Data](https://mlsanity.com/paper/2303.14080/) (2023)
- [Rebooting ACGAN: Auxiliary Classifier GANs with Stable Training](https://mlsanity.com/paper/2111.01118/) (2021)
- [Investigating the Role of Negatives in Contrastive Representation Learning](https://mlsanity.com/paper/2106.09943/) (2021)
- [Incremental False Negative Detection for Contrastive Learning](https://mlsanity.com/paper/2106.03719/) (2021)
- [Learning Audio-Visual Source Localization via False Negative Aware Contrastive Learning](https://mlsanity.com/paper/2303.11302/) (2023)
- [Solving Inefficiency of Self-supervised Representation Learning](https://mlsanity.com/paper/2104.08760/) (2021)
- [Ranking Info Noise Contrastive Estimation: Boosting Contrastive Learning via Ranked Positives](https://mlsanity.com/paper/2201.11736/) (2022)
- [Improving Molecular Contrastive Learning via Faulty Negative Mitigation and Decomposed Fragment Contrast](https://mlsanity.com/paper/2202.09346/) (2022)
- [Contrastive Domain Adaptation](https://mlsanity.com/paper/2103.15566/) (2021)
- [SelEx: Self-Expertise in Fine-Grained Generalized Category Discovery](https://mlsanity.com/paper/2408.14371/) (2024)
- [Max-Margin Contrastive Learning](https://mlsanity.com/paper/2112.11450/) (2021)
- [Bootstrapping Semi-supervised Medical Image Segmentation with Anatomical-aware Contrastive Distillation](https://mlsanity.com/paper/2206.02307/) (2022)
- [Beyond Just Vision: A Review on Self-Supervised Representation Learning on Multimodal and Temporal Data](https://mlsanity.com/paper/2206.02353/) (2022)
- [Decoupled Contrastive Multi-View Clustering with High-Order Random Walks](https://mlsanity.com/paper/2308.11164/) (2023)
- [Semi-supervised learning made simple with self-supervised clustering](https://mlsanity.com/paper/2306.07483/) (2023)
- [RelCon: Relative Contrastive Learning for a Motion Foundation Model for Wearable Data](https://mlsanity.com/paper/2411.18822/) (2024)
- [Local Spatiotemporal Representation Learning for Longitudinally-consistent Neuroimage Analysis](https://mlsanity.com/paper/2206.04281/) (2022)
- [Finding Order in Chaos: A Novel Data Augmentation Method for Time Series in Contrastive Learning](https://mlsanity.com/paper/2309.13439/) (2023)
- [Does Negative Sampling Matter? A Review with Insights into its Theory and Applications](https://mlsanity.com/paper/2402.17238/) (2024)
- [On the Efficacy of Small Self-Supervised Contrastive Models without Distillation Signals](https://mlsanity.com/paper/2107.14762/) (2021)
- [Unsupervised Representation Learning for Time Series: A Review](https://mlsanity.com/paper/2308.01578/) (2023)
- [Rethinking Negative Pairs in Code Search](https://mlsanity.com/paper/2310.08069/) (2023)
- [Contrastive Attraction and Contrastive Repulsion for Representation Learning](https://mlsanity.com/paper/2105.03746/) (2021)
- [Hard Negative Sampling Strategies for Contrastive Representation Learning](https://mlsanity.com/paper/2206.01197/) (2022)
- [Adaptive Soft Contrastive Learning](https://mlsanity.com/paper/2207.11163/) (2022)

## Abstract (arXiv)

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.