# CliqueCNN: Deep Unsupervised Exemplar Learning

arXiv: https://arxiv.org/abs/1608.08792 · HTML: https://mlsanity.com/paper/1608.08792/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Aug 2016.

## Built on by (most cited first, 30 of 41)

- [VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning](https://mlsanity.com/paper/2105.04906/) (2021)
- [With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2104.14548/) (2021)
- [Localizing Objects with Self-Supervised Transformers and no Labels](https://mlsanity.com/paper/2109.14279/) (2021)
- [Rethinking Semantic Segmentation: A Prototype View](https://mlsanity.com/paper/2203.15102/) (2022)
- [Neighborhood Contrastive Learning for Novel Class Discovery](https://mlsanity.com/paper/2106.10731/) (2021)
- [Scalable Pre-training of Large Autoregressive Image Models](https://mlsanity.com/paper/2401.08541/) (2024)
- [Broaden Your Views for Self-Supervised Video Learning](https://mlsanity.com/paper/2103.16559/) (2021)
- [Efficient Training of Visual Transformers with Small Datasets](https://mlsanity.com/paper/2106.03746/) (2021)
- [XSkill: Cross Embodiment Skill Discovery](https://mlsanity.com/paper/2307.09955/) (2023)
- [Mean Shift for Self-Supervised Learning](https://mlsanity.com/paper/2105.07269/) (2021)
- [Self-supervised Video Transformer](https://mlsanity.com/paper/2112.01514/) (2021)
- [Visual Recognition with Deep Nearest Centroids](https://mlsanity.com/paper/2209.07383/) (2022)
- [Mugs: A Multi-Granular Self-Supervised Learning Framework](https://mlsanity.com/paper/2203.14415/) (2022)
- [Unsupervised Action Segmentation by Joint Representation Learning and Online Clustering](https://mlsanity.com/paper/2105.13353/) (2021)
- [Class-Balanced Pixel-Level Self-Labeling for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2203.09744/) (2022)
- [Exemplar Guided Deep Neural Network for Spatial Transcriptomics Analysis of Gene Expression Prediction](https://mlsanity.com/paper/2210.16721/) (2022)
- [Self-supervised Learning from 100 Million Medical Images](https://mlsanity.com/paper/2201.01283/) (2022)
- [Self-supervised object detection from audio-visual correspondence](https://mlsanity.com/paper/2104.06401/) (2021)
- [Self-supervised remote sensing feature learning: Learning Paradigms, Challenges, and Future Works](https://mlsanity.com/paper/2211.08129/) (2022)
- [Towards Understanding Why Mask-Reconstruction Pretraining Helps in Downstream Tasks](https://mlsanity.com/paper/2206.03826/) (2022)
- [Class-Incremental Few-Shot Object Detection](https://mlsanity.com/paper/2105.07637/) (2021)
- [APANet: Adaptive Prototypes Alignment Network for Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2111.12263/) (2021)
- [Measuring the Interpretability of Unsupervised Representations via Quantized Reverse Probing](https://mlsanity.com/paper/2209.03268/) (2022)
- [Guarding Barlow Twins Against Overfitting with Mixed Samples](https://mlsanity.com/paper/2312.02151/) (2023)
- [Unsupervised Visual Representation Learning via Mutual Information Regularized Assignment](https://mlsanity.com/paper/2211.02284/) (2022)
- [ARAIDA: Analogical Reasoning-Augmented Interactive Data Annotation](https://mlsanity.com/paper/2405.11912/) (2024)
- [Improving Deep Metric Learning by Divide and Conquer](https://mlsanity.com/paper/2109.04003/) (2021)
- [Spatial Entropy as an Inductive Bias for Vision Transformers](https://mlsanity.com/paper/2206.04636/) (2022)
- [FUSSL: Fuzzy Uncertain Self Supervised Learning](https://mlsanity.com/paper/2210.15818/) (2022)
- [Tied-Augment: Controlling Representation Similarity Improves Data Augmentation](https://mlsanity.com/paper/2305.13520/) (2023)

## Abstract (arXiv)

Exemplar learning is a powerful paradigm for discovering visual similarities in an unsupervised manner. In this context, however, the recent breakthrough in deep learning could not yet unfold its full potential. With only a single positive sample, a great imbalance between one positive and many negatives, and unreliable relationships between most samples, training of Convolutional Neural networks is impaired. Given weak estimates of local distance we propose a single optimization problem to extract batches of samples with mutually consistent relations. Conflicting relations are distributed over different batches and similar samples are grouped into compact cliques. Learning exemplar similarities is framed as a sequence of clique categorization tasks. The CNN then consolidates transitivity relations within and between cliques and learns a single representation for all samples without the need for labels. The proposed unsupervised approach has shown competitive performance on detailed posture analysis and object classification.