Pith. sign in

REVIEW 9 cited by

CLIP-Adapter: Better Vision-Language Models with Feature Adapters

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 2110.04544 v2 pith:YJDZQQQJ submitted 2021-10-09 cs.CV cs.CL

Peng Gao , Shijie Geng , Renrui Zhang , Teli Ma , Rongyao Fang , Yongfeng Zhang , Hongsheng Li , Yu Qiao This is my paper
classification cs.CVcs.CL
keywords clip-adapterpromptvisualfeaturelearnvision-languageadaptersbetter
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large-scale contrastive vision-language pre-training has shown significant progress in visual representation learning. Unlike traditional visual systems trained by a fixed set of discrete labels, a new paradigm was introduced in \cite{radford2021learning} to directly learn to align images with raw texts in an open-vocabulary setting. On downstream tasks, a carefully chosen text prompt is employed to make zero-shot predictions.~To avoid non-trivial prompt engineering, context optimization \cite{zhou2021coop} has been proposed to learn continuous vectors as task-specific prompts with few-shot training examples.~In this paper, we show that there is an alternative path to achieve better vision-language models other than prompt tuning.~While prompt tuning is for the textual inputs, we propose CLIP-Adapter to conduct fine-tuning with feature adapters on either visual or language branch. Specifically, CLIP-Adapter adopts an additional bottleneck layer to learn new features and performs residual-style feature blending with the original pre-trained features.~As a consequence, CLIP-Adapter is able to outperform context optimization while maintains a simple design. Experiments and extensive ablation studies on various visual classification tasks demonstrate the effectiveness of our approach. Code is released at t https://github.com/gaopengcuhk/CLIP-Adapter.

Discussion (0). Sign in to comment.

Forward citations

Cited by 9 Pith papers

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

  1. Attn-Adapter: Attention Is All You Need for Online Few-shot Learner of Vision-Language Model

    cs.CV 2025-09 conditional novelty 6.0 of 10

    A dual attention adapter using support-image memory and local-global feature mixing improves CLIP few-shot and domain-shift classification.

  2. TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking

    cs.CV 2025-07 conditional novelty 6.0 of 10

    TrackAny3D adapts a pretrained 3D point cloud transformer into a single category-unified LiDAR tracker that beats prior category-agnostic methods on KITTI, NuScenes, and Waymo.

  3. MVL-Loc: Leveraging Vision-Language Model for Generalizable Multi-Scene Camera Relocalization

    cs.CV 2025-07 conditional novelty 6.0 of 10

    MVL-Loc fuses CLIP image and text features with per-scene pose heads and reports state-of-the-art multi-scene relocalization accuracy on 7Scenes and Cambridge Landmarks.

  4. Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting

    cs.LG 2025-05 conditional novelty 6.0 of 10

    Proxy-FDA aligns the local neighborhood structure of pre-trained and fine-tuned feature spaces, generating synthetic proxies to reduce concept forgetting during fine-tuning.

  5. Regularizing Subspace Redundancy of Low-Rank Adaptation

    cs.CV 2025-07 conditional novelty 5.0 of 10

    ReSoRA adds a penalty that reduces redundancy among rank-1 subspaces of LoRA-style adapters, producing modest accuracy improvements on vision-language retrieval and visual classification.

  6. GLAD: Generalizable Tuning for Vision-Language Models

    cs.CV 2025-07 conditional novelty 5.0 of 10

    GLAD improves few-shot CLIP generalization by fusing original and sharpness-aware gradients during LoRA tuning and adding image-conditional text alignment.

  7. Distill CLIP (DCLIP): Enhancing Image-Text Retrieval via Cross-Modal Transformer Distillation

    cs.CV 2025-05 conditional novelty 5.0 of 10

    DCLIP fine-tunes a CLIP student's image encoder to match a YOLO-region, bidirectional cross-attention teacher, improving retrieval while retaining most zero-shot accuracy.

  8. Multimodal-Guided Dynamic Dataset Pruning for Robust and Efficient Data-Centric Learning

    cs.LG 2025-07 conditional novelty 4.0 of 10

    A dynamic pruning method scores each sample by combining task loss with CLIP image-text similarity and selects samples near the median score each epoch.

  9. Beam-Guided Knowledge Replay for Knowledge-Rich Image Captioning using Vision-Language Model

    cs.CV 2025-05 conditional novelty 3.0 of 10

    Applying beam search, patch self-attention, and cosine scheduling to the K-Replay captioning framework improves knowledge-keyword recognition on KnowCap, though the full combined model is not reported.

Pith tools