Pith. sign in

REVIEW 16 cited by

Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling

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 2111.03930 v2 pith:NWKFONAM submitted 2021-11-06 cs.CV cs.CL

Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling

classification cs.CV cs.CL
keywords tip-adapteradapterfew-shottextbftrainingclipclip-adapterperformance
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Contrastive Vision-Language Pre-training, known as CLIP, has provided a new paradigm for learning visual representations by using large-scale contrastive image-text pairs. It shows impressive performance on zero-shot knowledge transfer to downstream tasks. To further enhance CLIP's few-shot capability, CLIP-Adapter proposed to fine-tune a lightweight residual feature adapter and significantly improves the performance for few-shot classification. However, such a process still needs extra training and computational resources. In this paper, we propose \textbf{T}raining-Free CL\textbf{IP}-\textbf{Adapter} (\textbf{Tip-Adapter}), which not only inherits CLIP's training-free advantage but also performs comparably or even better than CLIP-Adapter. Tip-Adapter does not require any back propagation for training the adapter, but creates the weights by a key-value cache model constructed from the few-shot training set. In this non-parametric manner, Tip-Adapter acquires well-performed adapter weights without any training, which is both efficient and effective. Moreover, the performance of Tip-Adapter can be further boosted by fine-tuning such properly initialized adapter for only a few epochs with super-fast convergence speed. We conduct extensive experiments of few-shot classification on ImageNet and other 10 datasets to demonstrate the superiority of proposed Tip-Adapter. The code will be released at \url{https://github.com/gaopengcuhk/Tip-Adapter}.

discussion (0)

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

Forward citations

Cited by 16 Pith papers

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

  1. Timage: A Generative Text-in-Image Paradigm for Fine-Tuning Vision-Language Models

    cs.CV 2026-06 unverdicted novelty 7.0

    Timage generates text query overlays on images via Constrained Schrödinger Bridge to boost fine-grained spatial reasoning in vision-language models, outperforming larger systems on VMCBench with a 7B backbone.

  2. Reviving In-domain Fine-tuning Methods for Source-Free Cross-domain Few-shot Learning

    cs.CV 2026-05 unverdicted novelty 7.0

    LoRA adapters fix collapsed visual CLS token attention in CLIP for superior cross-domain few-shot learning, and the new Semantic Probe framework revives prompt methods to reach state-of-the-art on four benchmarks.

  3. LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention

    cs.CV 2023-03 conditional novelty 7.0

    LLaMA-Adapter turns frozen LLaMA 7B into a capable instruction follower using only 1.2M new parameters and zero-init attention, matching Alpaca while extending to image-conditioned reasoning on ScienceQA and COCO.

  4. Adding Conditional Control to Text-to-Image Diffusion Models

    cs.CV 2023-02 conditional novelty 7.0

    ControlNet adds spatial conditioning controls to pretrained text-to-image diffusion models via zero convolutions for stable fine-tuning on small or large datasets.

  5. Geometry-Aware Distillation for Prompt Tuning Biomedical Vision-Language Models

    cs.CV 2026-06 unverdicted novelty 6.0

    OGKD injects inter-class geometry into teacher targets for two distillation losses (GAD on global tokens, LGD on patches) and reports 1.7-2.8% average accuracy gains over prior VLM adaptation methods on 11 medical datasets.

  6. Plug-and-play Class-aware Knowledge Injection for Prompt Learning with Visual-Language Model

    cs.CV 2026-05 unverdicted novelty 6.0

    CAKI generates class-specific prompts from few-shot samples of the same class, stores them in a knowledge bank, and uses query-key matching to inject relevant class knowledge into test instance predictions for improve...

  7. SpecPL: Disentangling Spectral Granularity for Prompt Learning

    cs.CV 2026-05 unverdicted novelty 6.0

    SpecPL introduces spectral decomposition via frozen VAE and counterfactual high-frequency permutation to bridge modality asymmetry in VLM prompt learning, reaching 81.51% harmonic-mean accuracy on 11 benchmarks.

  8. GA2-CLIP: Generic Attribute Anchor for Efficient Prompt Tuningin Video-Language Models

    cs.CV 2025-11 unverdicted novelty 6.0

    GA2-CLIP uses generic attribute anchors and coupled hard-soft prompts to preserve generalization in prompt-tuned video-language models on base-to-new class tasks.

  9. On the Provable Importance of Gradients for Language-Assisted Image Clustering

    cs.CV 2025-10 unverdicted novelty 6.0

    GradNorm selects positive nouns via gradient magnitudes from cross-entropy loss, with an error bound proving it subsumes prior CLIP methods and delivers SOTA clustering results.

  10. SeMoBridge: Semantic Modality Bridge for Efficient Few-Shot Adaptation of CLIP

    cs.CV 2025-09 unverdicted novelty 6.0

    SeMoBridge projects images into the text modality via a semantic bridge to reduce CLIP's intra-modal misalignment and improve few-shot performance.

  11. Semantics Disentanglement and Composition for Universal Image Coding with Efficiently LLM Reasoning and Generative Diffusion

    cs.CV 2024-12 unverdicted novelty 6.0

    UniCodec uses LLM-driven semantic disentanglement at the encoder and diffusion-based compositional generation at the decoder to enable one codec for both human perception and machine vision tasks without task-specific...

  12. Token-Based Dual-view Fusion and Adaptation of Large Vision Models for Breast Cancer Classification

    cs.CV 2026-07 conditional novelty 5.0

    A token-based dual-view fusion framework inserts dedicated cross-attention fusion tokens at multiple depths of a frozen vision transformer to improve mammogram classification.

  13. Parameter-Efficient Adapter Tuning for Tabular-Image Multimodal Learning

    cs.CV 2026-06 unverdicted novelty 5.0

    TI-Adapter applies embedding-level and bottleneck adapters to achieve competitive or better performance than full fine-tuning on 20 tabular-image datasets while training far fewer parameters.

  14. Text-Guided Multi-Scale Frequency Representation Adaptation

    cs.CV 2026-05 unverdicted novelty 5.0

    FreqAdapter adapts multimodal models by text-guided multi-scale fine-tuning in the frequency domain, claiming better performance and efficiency than signal-space PEFT methods.

  15. CLIP-SVD: Efficient and Interpretable Vision-Language Adaptation via Singular Values

    cs.CV 2025-09 unverdicted novelty 5.0

    CLIP-SVD performs parameter-efficient adaptation of CLIP by fine-tuning singular values from SVD of weight matrices, reporting SOTA few-shot accuracy on 21 datasets plus a language-based interpretability analysis.

  16. 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.