Pith. sign in

REVIEW 7 cited by

Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm

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

arxiv 2110.05208 v2 pith:HJVE2A7I submitted 2021-10-11 cs.CV

Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm

classification cs.CV
keywords supervisiondataclipcontrastiveimage-textpairspre-trainingdeclip
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Recently, large-scale Contrastive Language-Image Pre-training (CLIP) has attracted unprecedented attention for its impressive zero-shot recognition ability and excellent transferability to downstream tasks. However, CLIP is quite data-hungry and requires 400M image-text pairs for pre-training, thereby restricting its adoption. This work proposes a novel training paradigm, Data efficient CLIP (DeCLIP), to alleviate this limitation. We demonstrate that by carefully utilizing the widespread supervision among the image-text pairs, our De-CLIP can learn generic visual features more efficiently. Instead of using the single image-text contrastive supervision, we fully exploit data potential through the use of (1) self-supervision within each modality; (2) multi-view supervision across modalities; (3) nearest-neighbor supervision from other similar pairs. Benefiting from intrinsic supervision, our DeCLIP-ResNet50 can achieve 60.4% zero-shot top1 accuracy on ImageNet, which is 0.8% above the CLIP-ResNet50 while using 7.1 x fewer data. Our DeCLIP-ResNet50 outperforms its counterpart in 8 out of 11 visual datasets when transferred to downstream tasks. Moreover, Scaling up the model and computing also works well in our framework.Our code, dataset and models are released at: https://github.com/Sense-GVT/DeCLIP

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 7 Pith papers

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

  1. Neutral-Reference Prompting for Vision-Language Models

    cs.CV 2026-05 unverdicted novelty 7.0

    NeRP corrects asymmetric class confusion in VLMs for unseen classes by combining neutral-prompt priors with sample likelihood to flip predictions on confusable pairs, improving new-class accuracy while preserving base...

  2. MApLe: Multi-instance Alignment of Diagnostic Reports and Large Medical Images

    cs.CV 2026-04 unverdicted novelty 6.0

    MApLe disentangles anatomy and pathology to align free-text diagnostic sentences with specific patches in large medical images via multi-instance learning.

  3. Demystifying CLIP Data

    cs.CV 2023-09 accept novelty 6.0

    MetaCLIP curates balanced 400M-pair subsets from CommonCrawl that outperform CLIP data, reaching 70.8% zero-shot ImageNet accuracy on ViT-B versus CLIP's 68.3%.

  4. Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks

    cs.LG 2026-07 conditional novelty 5.0

    A system-first taxonomy and literature synthesis of multimodal unlearning across vision, language, video, and audio, with datasets, benchmarks, metrics, applications, and open challenges.

  5. DetailCLIP: Injecting Image Details into CLIP's Feature Space

    cs.CV 2022-08 unverdicted novelty 5.0

    A patch-based fusion method extends CLIP to high-resolution images by retaining multi-scale details for improved class-prompted retrieval.

  6. ReasonCLIP-58M: Visually Grounded Commonsense Reasoning Supervision for CLIP

    cs.CV 2026-06 unverdicted novelty 4.0

    ReasonCLIP-58M applies continual pretraining with visually grounded reasoning captions on 58M examples to improve CLIP-style models on commonsense and compositional reasoning tasks.

  7. Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey

    cs.LG 2024-03 accept novelty 4.0

    A comprehensive survey of PEFT algorithms for large models, covering their performance, overhead, applications, and real-world system implementations.