# Joint Contrastive Learning with Infinite Possibilities

arXiv: https://arxiv.org/abs/2009.14776 · HTML: https://mlsanity.com/paper/2009.14776/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Sep 2020.

## Built on by (most cited first, 30 of 31)

- [CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP](https://mlsanity.com/paper/2110.11316/) (2021)
- [SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2204.08808/) (2022)
- [Improving Contrastive Learning by Visualizing Feature Transformation](https://mlsanity.com/paper/2108.02982/) (2021)
- [Probabilistic Contrastive Learning for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2403.06726/) (2024)
- [Mine Your Own vieW: Self-Supervised Learning Through Across-Sample Prediction](https://mlsanity.com/paper/2102.10106/) (2021)
- [A Style and Semantic Memory Mechanism for Domain Generalization](https://mlsanity.com/paper/2112.07517/) (2021)
- [A Practical Contrastive Learning Framework for Single-Image Super-Resolution](https://mlsanity.com/paper/2111.13924/) (2021)
- [CT-GLIP: 3D Grounded Language-Image Pretraining with CT Scans and Radiology Reports for Full-Body Scenarios](https://mlsanity.com/paper/2404.15272/) (2024)
- [Motion-Focused Contrastive Learning of Video Representations](https://mlsanity.com/paper/2201.04029/) (2022)
- [CoCo-BERT: Improving Video-Language Pre-training with Contrastive Cross-modal Matching and Denoising](https://mlsanity.com/paper/2112.07515/) (2021)
- [ContrastNet: A Contrastive Learning Framework for Few-Shot Text Classification](https://mlsanity.com/paper/2305.09269/) (2023)
- [Contrastive Instruction-Trajectory Learning for Vision-Language Navigation](https://mlsanity.com/paper/2112.04138/) (2021)
- [Self-supervised Mean Teacher for Semi-supervised Chest X-ray Classification](https://mlsanity.com/paper/2103.03629/) (2021)
- [Semantic Distribution-aware Contrastive Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2105.05013/) (2021)
- [Transferrable Contrastive Learning for Visual Domain Adaptation](https://mlsanity.com/paper/2112.07516/) (2021)
- [CLUDA : Contrastive Learning in Unsupervised Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2208.14227/) (2022)
- [Directional Self-supervised Learning for Heavy Image Augmentations](https://mlsanity.com/paper/2110.13555/) (2021)
- [A Low Rank Promoting Prior for Unsupervised Contrastive Learning](https://mlsanity.com/paper/2108.02696/) (2021)
- [3D Cascade RCNN: High Quality Object Detection in Point Clouds](https://mlsanity.com/paper/2211.08248/) (2022)
- [InfMasking: Unleashing Synergistic Information by Contrastive Multimodal Interactions](https://mlsanity.com/paper/2509.25270/) (2025)
- [Contrastive Learning of Global-Local Video Representations](https://mlsanity.com/paper/2104.05418/) (2021)
- [Improving Self-supervised Learning with Automated Unsupervised Outlier Arbitration](https://mlsanity.com/paper/2112.08132/) (2021)
- [CORE-Text: Improving Scene Text Detection with Contrastive Relational Reasoning](https://mlsanity.com/paper/2112.07513/) (2021)
- [Bi-Calibration Networks for Weakly-Supervised Video Representation Learning](https://mlsanity.com/paper/2206.10491/) (2022)
- [Extending Momentum Contrast with Cross Similarity Consistency Regularization](https://mlsanity.com/paper/2206.04676/) (2022)
- [MLVICX: Multi-Level Variance-Covariance Exploration for Chest X-ray Self-Supervised Representation Learning](https://mlsanity.com/paper/2403.11504/) (2024)
- [MSR: Making Self-supervised learning Robust to Aggressive Augmentations](https://mlsanity.com/paper/2206.01999/) (2022)
- [Intra-class Adaptive Augmentation with Neighbor Correction for Deep Metric Learning](https://mlsanity.com/paper/2211.16264/) (2022)
- [Semi-supervised Medical Image Segmentation via Query Distribution Consistency](https://mlsanity.com/paper/2311.12364/) (2023)
- [Affinity-Graph-Guided Contractive Learning for Pretext-Free Medical Image Segmentation with Minimal Annotation](https://mlsanity.com/paper/2410.10366/) (2024)

## Abstract (arXiv)

This paper explores useful modifications of the recent development in contrastive learning via novel probabilistic modeling. We derive a particular form of contrastive loss named Joint Contrastive Learning (JCL). JCL implicitly involves the simultaneous learning of an infinite number of query-key pairs, which poses tighter constraints when searching for invariant features. We derive an upper bound on this formulation that allows analytical solutions in an end-to-end training manner. While JCL is practically effective in numerous computer vision applications, we also theoretically unveil the certain mechanisms that govern the behavior of JCL. We demonstrate that the proposed formulation harbors an innate agency that strongly favors similarity within each instance-specific class, and therefore remains advantageous when searching for discriminative features among distinct instances. We evaluate these proposals on multiple benchmarks, demonstrating considerable improvements over existing algorithms. Code is publicly available at: https://github.com/caiqi/Joint-Contrastive-Learning.