paper-with-me

Papers

CLIP Models are Few-shot Learners: Empirical Studies on VQA and Visual Entailment

2022-03-14 · ACL 2022 5 · Haoyu Song, Li Dong, Wei-Nan Zhang, Ting Liu, Furu Wei

CLIP has shown a remarkable zero-shot capability on a wide range of vision tasks. Previously, CLIP is only regarded as a powerful visual encoder. However, after being pre-trained by language supervision from a large amount of image-caption pairs, CLIP itself should also have acquired some few-shot abilities for vision-language tasks. In this work, we empirically show that CLIP can be a strong vision-language few-shot learner by leveraging the power of language. We first evaluate CLIP's zero-shot performance on a typical visual question answering task and demonstrate a zero-shot cross-modality transfer capability of CLIP on the visual entailment task. Then we propose a parameter-efficient fine-tuning strategy to boost the few-shot performance on the vqa task. We achieve competitive zero/few-shot results on the visual question answering and visual entailment tasks without introducing any additional pre-training procedure.

📄 PDF Abstract BibTeX arXiv:2203.07190

Code (0)

등록된 구현이 없습니다.

Tasks

parameter-efficient fine-tuningQuestion AnsweringVisual EntailmentVisual Question AnsweringVisual Question Answering (VQA)

Methods 이 논문이 사용한 방법론

CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

Learning Generalized Zero-Shot Learners for Open-Domain Image Geolocalization

2023-02-01 · Lukas Haas, Silas Alberti, Michal Skreta

Image geolocalization is the challenging task of predicting the geographic coordinates of origin for a given photo. It is an unsolved problem relying on the ability to combine visual clues with general knowledge about th…

Generalized Zero-Shot LearningMeta-LearningPhoto geolocation estimationZero-Shot Learning

Diagnosing Ensemble Few-Shot Classifiers

2022-06-09 · Weikai Yang, Xi Ye, Xingxing Zhang, Lanxi Xiao 외

The base learners and labeled samples (shots) in an ensemble few-shot classifier greatly affect the model performance. When the performance is not satisfactory, it is usually difficult to understand the underlying causes…

Bootstrap Fine-Grained Vision-Language Alignment for Unified Zero-Shot Anomaly Localization

2023-08-30 · Hanqiu Deng, Zhaoxiang Zhang, Jinan Bao, Xingyu Li

Contrastive Language-Image Pre-training (CLIP) models have shown promising performance on zero-shot visual recognition tasks by learning visual representations under natural language supervision. Recent studies attempt t…

Anomaly DetectionAnomaly LocalizationTest-time Adaptationzero-shot anomaly detection

Prompt, Generate, then Cache: Cascade of Foundation Models makes Strong Few-shot Learners

2023-03-03 · CVPR 2023 1 · Renrui Zhang, Xiangfei Hu, Bohao Li, Siyuan Huang 외

Visual recognition in low-data regimes requires deep neural networks to learn generalized representations from limited training samples. Recently, CLIP-based methods have shown promising few-shot performance benefited fr…

Few-Shot LearningRepresentation Learning

Making Pretrained Language Models Good Long-tailed Learners

2022-05-11 · Chen Zhang, Lei Ren, Jingang Wang, Wei Wu 외

Prompt-tuning has shown appealing performance in few-shot classification by virtue of its capability in effectively exploiting pre-trained knowledge. This motivates us to check the hypothesis that prompt-tuning is also a…

Classification