paper-with-me

홈 › Papers

GPT4Vis: What Can GPT-4 Do for Zero-shot Visual Recognition?

2023-11-27 · Wenhao Wu, Huanjin Yao, Mengxi Zhang, Yuxin Song, Wanli Ouyang, Jingdong Wang

This paper does not present a novel method. Instead, it delves into an essential, yet must-know baseline in light of the latest advancements in Generative Artificial Intelligence (GenAI): the utilization of GPT-4 for visual understanding. Our study centers on the evaluation of GPT-4's linguistic and visual capabilities in zero-shot visual recognition tasks: Firstly, we explore the potential of its generated rich textual descriptions across various categories to enhance recognition performance without any training. Secondly, we evaluate GPT-4's visual proficiency in directly recognizing diverse visual content. We conducted extensive experiments to systematically evaluate GPT-4's performance across images, videos, and point clouds, using 16 benchmark datasets to measure top-1 and top-5 accuracy. Our findings show that GPT-4, enhanced with rich linguistic descriptions, significantly improves zero-shot recognition, offering an average top-1 accuracy increase of 7% across all datasets. GPT-4 excels in visual recognition, outshining OpenAI-CLIP's ViT-L and rivaling EVA-CLIP's ViT-E, particularly in video datasets HMDB-51 and UCF-101, where it leads by 22% and 9%, respectively. We hope this research contributes valuable data points and experience for future studies. We release our code at https://github.com/whwu95/GPT4Vis.

📄 PDF Abstract BibTeX arXiv:2311.15732

Code (2)

whwu95/GPT4Vis 공식 구현
lastmile-ai/aiconfig

Tasks

Zero-Shot Learning

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Similar Papers 제목 키워드 기반

Zero-Shot Anticipation for Instructional Activities

2018-12-06 · ICCV 2019 10 · Fadime Sener, Angela Yao

How can we teach a robot to predict what will happen next for an activity it has never seen before? We address this problem of zero-shot anticipation by presenting a hierarchical model that generalizes instructional know…

Zero-Shot Learning

All About Knowledge Graphs for Actions

2020-08-28 · Pallabi Ghosh, Nirat Saini, Larry S. Davis, Abhinav Shrivastava

Current action recognition systems require large amounts of training data for recognizing an action. Recent works have explored the paradigm of zero-shot and few-shot learning to learn classifiers for unseen categories o…

Action RecognitionAllFew-Shot action recognitionFew Shot Action Recognition+5

A Fistful of Words: Learning Transferable Visual Models from Bag-of-Words Supervision

2021-12-27 · Ajinkya Tejankar, Maziar Sanjabi, Bichen Wu, Saining Xie 외

Using natural language as a supervision for training visual recognition models holds great promise. Recent works have shown that if such supervision is used in the form of alignment between images and captions in large t…

ClassificationImage Captioningimage-classificationImage Classification+3

Zero-Shot Recognition using Dual Visual-Semantic Mapping Paths

2017-03-15 · CVPR 2017 7 · Yanan Li, Donghui Wang, Huanhang Hu, Yuetan Lin 외

Zero-shot recognition aims to accurately recognize objects of unseen classes by using a shared visual-semantic mapping between the image feature space and the semantic embedding space. This mapping is learned on training…

Zero-Shot Learning

PEVA-Net: Prompt-Enhanced View Aggregation Network for Zero/Few-Shot Multi-View 3D Shape Recognition

2024-04-30 · Dongyun Lin, Yi Cheng, Shangbo Mao, Aiyuan Guo 외

Large vision-language models have impressively promote the performance of 2D visual recognition under zero/few-shot scenarios. In this paper, we focus on exploiting the large vision-language model, i.e., CLIP, to address…

3D Shape RecognitionFew-Shot LearningLanguage ModellingZero-Shot Learning