paper-with-me

홈 › Papers

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

2021-10-09 · Peng Gao, Shijie Geng, Renrui Zhang, Teli Ma, Rongyao Fang, Yongfeng Zhang, Hongsheng Li, Yu Qiao

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.

📄 PDF Abstract BibTeX arXiv:2110.04544

Code (3)

gaopengcuhk/clip-adapter 공식 구현 pytorch
ArsenalCheng/Meta-Adapter pytorch
kenomo/industrial-clip pytorch

Tasks

Prompt EngineeringRepresentation Learning

Similar Papers 제목 키워드 기반

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

2021-11-06 · Renrui Zhang, Rongyao Fang, Wei zhang, Peng Gao 외

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 kno…

Language ModelingLanguage ModellingTransfer Learning

CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-training

2022-10-03 · ICCV 2023 1 · Tianyu Huang, Bowen Dong, Yunhan Yang, Xiaoshui Huang 외

Pre-training across 3D vision and language remains under development because of limited training data. Recent works attempt to transfer vision-language pre-training models to 3D vision. PointCLIP converts point cloud dat…

3D Point Cloud ClassificationContrastive LearningFew-Shot LearningPoint Cloud Classification+4

UniCrossAdapter: Multimodal Adaptation of CLIP for Radiology Report Generation

2025-03-20 · Yaxiong Chen, Chuang Du, Chunlei Li, Jingliang Hu 외

Automated radiology report generation aims to expedite the tedious and error-prone reporting process for radiologists. While recent works have made progress, learning to align medical images and textual findings remains …

Image CaptioningTransfer Learning

SIA-OVD: Shape-Invariant Adapter for Bridging the Image-Region Gap in Open-Vocabulary Detection

2024-10-08 · Zishuo Wang, Wenhao Zhou, Jinglin Xu, Yuxin Peng

Open-vocabulary detection (OVD) aims to detect novel objects without instance-level annotations to achieve open-world object detection at a lower cost. Existing OVD methods mainly rely on the powerful open-vocabulary ima…

object-detectionObject DetectionOpen Vocabulary Object DetectionOpen World Object Detection

Class Incremental Learning with Pre-trained Vision-Language Models

2023-10-31 · Xialei Liu, Xusheng Cao, Haori Lu, Jia-Wen Xiao 외

With the advent of large-scale pre-trained models, interest in adapting and exploiting them for continual learning scenarios has grown. In this paper, we propose an approach to exploiting pre-trained vision-language mode…

class-incremental learningClass Incremental LearningContinual LearningIncremental Learning+1