Pith. sign in

REVIEW 4 cited by

Data-Efficient Image Recognition with Contrastive Predictive Coding

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 1905.09272 v3 pith:HIIJLFWS submitted 2019-05-22 cs.CV cs.LG

Olivier J. Hénaff , Aravind Srinivas , Jeffrey De Fauw , Ali Razavi , Carl Doersch , S. M. Ali Eslami , Aaron van den Oord This is my paper · ORCID
classification cs.CVcs.LG
keywords classificationclassifierscodingcontrastivedata-efficientdatasetimageimagenet
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Human observers can learn to recognize new categories of images from a handful of examples, yet doing so with artificial ones remains an open challenge. We hypothesize that data-efficient recognition is enabled by representations which make the variability in natural signals more predictable. We therefore revisit and improve Contrastive Predictive Coding, an unsupervised objective for learning such representations. This new implementation produces features which support state-of-the-art linear classification accuracy on the ImageNet dataset. When used as input for non-linear classification with deep neural networks, this representation allows us to use 2-5x less labels than classifiers trained directly on image pixels. Finally, this unsupervised representation substantially improves transfer learning to object detection on the PASCAL VOC dataset, surpassing fully supervised pre-trained ImageNet classifiers.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

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

  1. Detecting semantic anomalies

    cs.CV 2019-08 conditional novelty 6.0 of 10

    The paper reframes OOD detection as semantic anomaly detection, proposes hold-out-class benchmarks including fine-grained ImageNet subsets, and reports that rotation-prediction and CPC auxiliary tasks improve both ano...

  2. Adaptive Prompt Tuning: Vision Guided Prompt Tuning with Cross-Attention for Fine-Grained Few-Shot Learning

    cs.CV 2024-12 conditional novelty 4.0 of 10

    APT uses cross-attention between image patches and text embeddings to dynamically refine CLIP prompts for fine-grained few-shot classification.

  3. Learning Text Styles: A Study on Transfer, Attribution, and Verification

    cs.CL 2025-07 conditional novelty 3.0 of 10

    A thesis compiles published work claiming that lightweight adapters, contrastive disentanglement, and instruction tuning improve text style transfer, authorship attribution, and authorship verification.

  4. Leveraging large language models for efficient representation learning for entity resolution

    cs.CL 2024-11 reject novelty 3.0 of 10

    Fine-tuning a Sentence-BERT model with triplet loss on entity records yields embeddings that improve entity matching F1 by 3-19% over non-fine-tuned SBERT and TF-IDF on the tested datasets.

Pith tools