Pith. sign in

REVIEW 15 cited by

How Much Can CLIP Benefit Vision-and-Language Tasks?

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 2107.06383 v1 pith:7YUNHCRR submitted 2021-07-13 cs.CV cs.AIcs.CLcs.LG

How Much Can CLIP Benefit Vision-and-Language Tasks?

classification cs.CV cs.AIcs.CLcs.LG
keywords clipvisualtasksdatabetterclip-vilencodersmodels
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Most existing Vision-and-Language (V&L) models rely on pre-trained visual encoders, using a relatively small set of manually-annotated data (as compared to web-crawled data), to perceive the visual world. However, it has been observed that large-scale pretraining usually can result in better generalization performance, e.g., CLIP (Contrastive Language-Image Pre-training), trained on a massive amount of image-caption pairs, has shown a strong zero-shot capability on various vision tasks. To further study the advantage brought by CLIP, we propose to use CLIP as the visual encoder in various V&L models in two typical scenarios: 1) plugging CLIP into task-specific fine-tuning; 2) combining CLIP with V&L pre-training and transferring to downstream tasks. We show that CLIP significantly outperforms widely-used visual encoders trained with in-domain annotated data, such as BottomUp-TopDown. We achieve competitive or better results on diverse V&L tasks, while establishing new state-of-the-art results on Visual Question Answering, Visual Entailment, and V&L Navigation tasks. We release our code at https://github.com/clip-vil/CLIP-ViL.

discussion (0)

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

Forward citations

Cited by 15 Pith papers

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

  1. VideoChat: Chat-Centric Video Understanding

    cs.CV 2023-05 conditional novelty 7.0

    VideoChat integrates video models and LLMs via a learnable interface for chat-based spatiotemporal and causal video reasoning, trained on a new video-centric instruction dataset.

  2. LAION-5B: An open large-scale dataset for training next generation image-text models

    cs.CV 2022-10 accept novelty 7.0

    LAION-5B is an openly released dataset of 5.85 billion CLIP-filtered image-text pairs that enables replication of foundational vision-language models.

  3. Hierarchical Text-Conditional Image Generation with CLIP Latents

    cs.CV 2022-04 accept novelty 7.0

    A hierarchical prior-decoder model using CLIP latents generates more diverse text-conditional images than direct methods while preserving photorealism and caption fidelity.

  4. Memory-Efficient Transfer Learning with Fading Side Networks via Masked Dual Path Distillation

    cs.CV 2026-04 unverdicted novelty 6.0

    MDPD mutually distills knowledge between a frozen backbone and a learnable side network during fine-tuning, then discards the side network at inference to accelerate speed by at least 25% while preserving accuracy.

  5. MP-ISMoE: Mixed-Precision Interactive Side Mixture-of-Experts for Efficient Transfer Learning

    cs.LG 2026-04 unverdicted novelty 6.0

    MP-ISMoE uses Gaussian noise perturbed iterative quantization and interactive side mixture-of-experts to deliver higher accuracy than prior memory-efficient transfer learning methods while keeping similar parameter an...

  6. Stealthy and Adjustable Text-Guided Backdoor Attacks on Multimodal Pretrained Models

    cs.CR 2026-04 unverdicted novelty 6.0

    Introduces a text-guided backdoor attack using common textual words as triggers and visual perturbations for stealthy, adjustable control on multimodal pretrained models.

  7. Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts

    cs.MA 2026-01 unverdicted novelty 6.0

    MACL deploys image, text, name, and coordination agents with message passing and adaptive balancing to achieve 1-5% precision gains on VISTA-Beyond for few-shot and zero-shot OOD alignment.

  8. GPT-4V(ision) is a Generalist Web Agent, if Grounded

    cs.IR 2024-01 conditional novelty 6.0

    GPT-4V achieves 51.1% success on live web tasks as a generalist agent when plans are manually grounded, outperforming text-only models, but automatic grounding lags far behind oracle performance.

  9. InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation

    cs.CV 2023-07 unverdicted novelty 6.0

    InternVid supplies 7M videos and LLM captions to train ViCLIP, which reaches leading zero-shot action recognition and competitive retrieval performance.

  10. CoCa: Contrastive Captioners are Image-Text Foundation Models

    cs.CV 2022-05 accept novelty 6.0

    CoCa unifies contrastive and generative pretraining in one image-text model to reach 86.3% zero-shot ImageNet accuracy and new state-of-the-art results on multiple downstream benchmarks.

  11. UniMesh: Unifying 3D Mesh Understanding and Generation

    cs.CV 2026-04 unverdicted novelty 5.0

    UniMesh unifies 3D mesh generation and understanding in one model via a Mesh Head interface, Chain of Mesh iterative editing, and an Actor-Evaluator self-reflection loop.

  12. InternVideo: General Video Foundation Models via Generative and Discriminative Learning

    cs.CV 2022-12 unverdicted novelty 5.0

    InternVideo combines masked video modeling and video-language contrastive learning into a single foundation model that reaches state-of-the-art results on 39 video datasets including 91.1% top-1 on Kinetics-400.

  13. GIT: A Generative Image-to-text Transformer for Vision and Language

    cs.CV 2022-05 unverdicted novelty 5.0

    GIT achieves new state-of-the-art results on 12 vision-language benchmarks, including surpassing human performance on TextCaps, via a simplified single-encoder single-decoder transformer scaled on large pre-training data.

  14. ReVision : A Post-Hoc, Vision-Based Technique for Replacing Unacceptable Concepts in Image Generation Pipeline

    cs.CR 2026-02 conditional novelty 4.0

    ReVision uses a vision-language model's bounding box to gate attention-based image editing, suppressing unsafe concepts while better preserving benign background in multi-concept scenes.

  15. A Survey on Semantic Communication for Vision: Categories, Frameworks, Enabling Techniques, and Applications

    eess.IV 2026-01 unverdicted novelty 4.0

    A survey that classifies visual semantic communication into preservation, expansion, and refinement categories and reviews their machine-learning components and applications.