REVIEW 8 cited by
Prototypical Contrastive Learning of Unsupervised Representations
Not yet reviewed by Pith; the record is open.
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
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.
Forward citations
Cited by 8 Pith papers
-
CMCC-ReID: Cross-Modality Clothing-Change Person Re-Identification
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...
-
DUDE: Diffusion-Based Unsupervised Cross-Domain Image Retrieval
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.
-
Learning Generalizable Robot Policy with Human Demonstration Video as a Prompt
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...
-
Context Distribution Restoration for Social Surveys: A Recoverability-Adaptive Transport Framework
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.
-
Valid Property-Enhanced Contrastive Learning for Targeted Optimization & Resampling for Novel Drug Design
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.
-
A Generalized Learning Framework for Self-Supervised Contrastive Learning
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.
-
Global Context-aware Representation Learning for Spatially Resolved Transcriptomics
Spotscape improves spatial-domain identification in spatial transcriptomics by learning augmentation-invariant global spot similarities and a slice-level similarity matching objective.
-
Emerging Trends in Pseudo-Label Refinement for Weakly Supervised Semantic Segmentation with Image-Level Supervision
A survey organizing recent weak supervision methods for semantic segmentation into internal and external pseudo-label refinement strategies, with future directions.
Discussion (0). Sign in to comment.