Pith. sign in

REVIEW 9 cited by

Prototypical Contrastive Learning of Unsupervised Representations

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2005.04966 v5 pith:XTCWFZAS submitted 2020-05-11 cs.CV cs.LG

Junnan Li , Pan Zhou , Caiming Xiong , Steven C.H. Hoi This is my paper
classification cs.CVcs.LG
keywords learningcontrastiveprototypesinstance-wiselossnetworkprototypicalrepresentations
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This paper presents Prototypical Contrastive Learning (PCL), an unsupervised representation learning method that addresses the fundamental limitations of instance-wise contrastive learning. PCL not only learns low-level features for the task of instance discrimination, but more importantly, it implicitly encodes semantic structures of the data into the learned embedding space. Specifically, we introduce prototypes as latent variables to help find the maximum-likelihood estimation of the network parameters in an Expectation-Maximization framework. We iteratively perform E-step as finding the distribution of prototypes via clustering and M-step as optimizing the network via contrastive learning. We propose ProtoNCE loss, a generalized version of the InfoNCE loss for contrastive learning, which encourages representations to be closer to their assigned prototypes. PCL outperforms state-of-the-art instance-wise contrastive learning methods on multiple benchmarks with substantial improvement in low-resource transfer learning. Code and pretrained models are available at https://github.com/salesforce/PCL.

Discussion (0). Sign in to comment.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. CMCC-ReID: Cross-Modality Clothing-Change Person Re-Identification

    cs.CV 2026-04 unverdicted novelty 8.0 of 10

    The paper introduces the CMCC-ReID task, constructs the SYSU-CMCC benchmark dataset, and proposes the PIA network with disentangling and prototype modules that outperforms prior methods on combined modality and clothi...

  2. DUDE: Diffusion-Based Unsupervised Cross-Domain Image Retrieval

    cs.CV 2025-09 conditional novelty 6.0 of 10

    A diffusion-based disentanglement method that separates object content from domain style achieves state-of-the-art unsupervised cross-domain image retrieval on three benchmarks.

  3. Learning Generalizable Robot Policy with Human Demonstration Video as a Prompt

    cs.RO 2025-05 conditional novelty 6.0 of 10

    A two-stage pipeline trains a robot policy that accepts a human demonstration video as a prompt and generalizes beyond its robot training tasks, with success rates of up to 79 percent on known task variations and unde...

  4. Context Distribution Restoration for Social Surveys: A Recoverability-Adaptive Transport Framework

    cs.SI 2026-07 conditional novelty 5.5 of 10

    Recoverability-adaptive Sinkhorn transport restores sample-level survey metadata under a known prior P(M), cutting total variation to <0.001 with modest accuracy loss on CHNS, NHANES, and BRFSS.

  5. Valid Property-Enhanced Contrastive Learning for Targeted Optimization & Resampling for Novel Drug Design

    cs.LG 2025-08 conditional novelty 5.0 of 10

    VECTOR+ combines contrastive learning and Gaussian mixture sampling to generate novel, synthetically plausible inhibitors from low-data datasets, with improved docking scores over known compounds.

  6. A Generalized Learning Framework for Self-Supervised Contrastive Learning

    cs.LG 2025-08 unverdicted novelty 5.0 of 10

    A single framework unifies BYOL, Barlow Twins, and SwAV, plus a plug-in calibration method, ADC, that improves learned representations by preserving input-space distances.

  7. Global Context-aware Representation Learning for Spatially Resolved Transcriptomics

    cs.LG 2025-05 conditional novelty 5.0 of 10

    Spotscape improves spatial-domain identification in spatial transcriptomics by learning augmentation-invariant global spot similarities and a slice-level similarity matching objective.

  8. Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification

    cs.CV 2025-05 conditional novelty 5.0 of 10

    Proto-FG3D replaces the softmax classifier with prototype matching for fine-grained 3D shape classification, reporting state-of-the-art accuracy on FG3D and ModelNet40 with built-in interpretability.

  9. Emerging Trends in Pseudo-Label Refinement for Weakly Supervised Semantic Segmentation with Image-Level Supervision

    cs.CV 2025-07 unverdicted novelty 1.0 of 10

    A survey organizing recent weak supervision methods for semantic segmentation into internal and external pseudo-label refinement strategies, with future directions.

Pith tools