# Unsupervised Feature Learning by Cross-Level Instance-Group Discrimination

arXiv: https://arxiv.org/abs/2008.03813 · HTML: https://mlsanity.com/paper/2008.03813/

## Key facts

- Cited by 51 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Aug 2020.

## Built on by (most cited first, 30 of 51)

- [Cut and Learn for Unsupervised Object Detection and Instance Segmentation](https://mlsanity.com/paper/2301.11320/) (2023)
- [Multi-Granularity Cross-modal Alignment for Generalized Medical Visual Representation Learning](https://mlsanity.com/paper/2210.06044/) (2022)
- [Decoupled Contrastive Learning](https://mlsanity.com/paper/2110.06848/) (2021)
- [Contrastive Learning with Stronger Augmentations](https://mlsanity.com/paper/2104.07713/) (2021)
- [Debiased Learning from Naturally Imbalanced Pseudo-Labels](https://mlsanity.com/paper/2201.01490/) (2022)
- [Twin Contrastive Learning for Online Clustering](https://mlsanity.com/paper/2210.11680/) (2022)
- [Learning Representation for Clustering via Prototype Scattering and Positive Sampling](https://mlsanity.com/paper/2111.11821/) (2021)
- [Improving Contrastive Learning by Visualizing Feature Transformation](https://mlsanity.com/paper/2108.02982/) (2021)
- [HCSC: Hierarchical Contrastive Selective Coding](https://mlsanity.com/paper/2202.00455/) (2022)
- [Unsupervised Hierarchical Semantic Segmentation with Multiview Cosegmentation and Clustering Transformers](https://mlsanity.com/paper/2204.11432/) (2022)
- [VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentation](https://mlsanity.com/paper/2308.14710/) (2023)
- [Unsupervised Universal Image Segmentation](https://mlsanity.com/paper/2312.17243/) (2023)
- [Continuous Learning for Android Malware Detection](https://mlsanity.com/paper/2302.04332/) (2023)
- [Rethinking Patch Dependence for Masked Autoencoders](https://mlsanity.com/paper/2401.14391/) (2024)
- [MHCCL: Masked Hierarchical Cluster-Wise Contrastive Learning for Multivariate Time Series](https://mlsanity.com/paper/2212.01141/) (2022)
- [Unsupervised Selective Labeling for More Effective Semi-Supervised Learning](https://mlsanity.com/paper/2110.03006/) (2021)
- [Subclass-balancing Contrastive Learning for Long-tailed Recognition](https://mlsanity.com/paper/2306.15925/) (2023)
- [Self-supervised remote sensing feature learning: Learning Paradigms, Challenges, and Future Works](https://mlsanity.com/paper/2211.08129/) (2022)
- [Revisiting a kNN-based Image Classification System with High-capacity Storage](https://mlsanity.com/paper/2204.01186/) (2022)
- [Unsupervised Visual Representation Learning by Synchronous Momentum Grouping](https://mlsanity.com/paper/2207.06167/) (2022)
- [MaskCon: Masked Contrastive Learning for Coarse-Labelled Dataset](https://mlsanity.com/paper/2303.12756/) (2023)
- [Connecting Joint-Embedding Predictive Architecture with Contrastive Self-supervised Learning](https://mlsanity.com/paper/2410.19560/) (2024)
- [Multimodal contrastive learning for remote sensing tasks](https://mlsanity.com/paper/2209.02329/) (2022)
- [Boosting Novel Category Discovery Over Domains with Soft Contrastive Learning and All-in-One Classifier](https://mlsanity.com/paper/2211.11262/) (2022)
- [Learning Hierarchical Image Segmentation For Recognition and By Recognition](https://mlsanity.com/paper/2210.00314/) (2022)
- [Energy-Based Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2202.04933/) (2022)
- [Topic Modeling as Multi-Objective Contrastive Optimization](https://mlsanity.com/paper/2402.07577/) (2024)
- [Visual Lexicon: Rich Image Features in Language Space](https://mlsanity.com/paper/2412.06774/) (2024)
- [Rethinking Prototypical Contrastive Learning through Alignment, Uniformity and Correlation](https://mlsanity.com/paper/2210.10194/) (2022)
- [FLSL: Feature-level Self-supervised Learning](https://mlsanity.com/paper/2306.06203/) (2023)

## Abstract (arXiv)

Unsupervised feature learning has made great strides with contrastive learning based on instance discrimination and invariant mapping, as benchmarked on curated class-balanced datasets. However, natural data could be highly correlated and long-tail distributed. Natural between-instance similarity conflicts with the presumed instance distinction, causing unstable training and poor performance. Our idea is to discover and integrate between-instance similarity into contrastive learning, not directly by instance grouping, but by cross-level discrimination (CLD) between instances and local instance groups. While invariant mapping of each instance is imposed by attraction within its augmented views, between-instance similarity could emerge from common repulsion against instance groups. Our batch-wise and cross-view comparisons also greatly improve the positive/negative sample ratio of contrastive learning and achieve better invariant mapping. To effect both grouping and discrimination objectives, we impose them on features separately derived from a shared representation. In addition, we propose normalized projection heads and unsupervised hyper-parameter tuning for the first time. Our extensive experimentation demonstrates that CLD is a lean and powerful add-on to existing methods such as NPID, MoCo, InfoMin, and BYOL on highly correlated, long-tail, or balanced datasets. It not only achieves new state-of-the-art on self-supervision, semi-supervision, and transfer learning benchmarks, but also beats MoCo v2 and SimCLR on every reported performance attained with a much larger compute. CLD effectively brings unsupervised learning closer to natural data and real-world applications. Our code is publicly available at: https://github.com/frank-xwang/CLD-UnsupervisedLearning.