Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

natural-language-processing-2

Visual Prompting

3260 papers • 126 benchmarks • 313 datasets

Visual Prompting is the task of streamlining computer vision processes by harnessing the power of prompts, inspired by the breakthroughs of text prompting in NLP. This innovative approach involves using a few visual prompts to swiftly convert an unlabeled dataset into a deployed model, significantly reducing development time for both individual projects and enterprise solutions.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in visual-prompting-5

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find visual-prompting-5 models and implementations

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

Segment Anything

Nikhila Ravi, Wan-Yen Lo, Ross B. Girshick, Laura Gustafson, Chloé Rolland, A. Berg, A. Kirillov, Eric Mintun, Hanzi Mao, Tete Xiao, Spencer Whitehead, Piotr Dollár•Tue Apr 04 2023

The Segment Anything Model (SAM) is introduced: a new task, model, and dataset for image segmentation, and its zero-shot performance is impressive – often competitive with or even superior to prior fully supervised results.

10582

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

0

Visual in-Context Prompting

Jianwei Yang, Chun-yue Li, Xueyan Zou, Hao Zhang, Feng Li, Qing Jiang, Tianhe Ren, Shilong Liu, Huaizhe Xu, Hongyang Li, Lei Zhang, Jianfeng Gao•Tue Nov 21 2023

This paper builds on top of an encoder-decoder architecture, and develops a versatile prompt encoder to support a variety of prompts like strokes, boxes, and points, and enhances it to take an arbitrary number of reference image segments as the context.

53 0

Visual Prompting for Adversarial Robustness

Yuguang Yao, Pin-Yu Chen, P. Lorenz, Aochuan Chen, Sijia Liu•Tue Oct 11 2022

This work proposes a new VP method, termed Class-wise Adversarial Visual Prompting (C-AVP), to generate class-wise visual prompts so as to not only leverage the strengths of ensemble prompts but also optimize their interrelations to improve model robustness.

44 0

Explicit Visual Prompting for Universal Foreground Segmentations

Chi-Man Pun, Weihuang Liu, Xiaodong Cun, Xi Shen•Sun May 28 2023

This paper takes inspiration from the widely-used pre-training and then prompt tuning protocols in NLP and proposes a new visual prompting model, named Explicit Visual Prompting (EVP), which freezes a pre-trained model and then learns task-specific knowledge using a few extra parameters.

23 0

Exploring Visual Prompts for Adapting Large-Scale Models

Phillip Isola, S. Sankaranarayanan, Hyojin Bahng, Ali Jahanian•Wed Mar 30 2022

The surprising effectiveness of visual prompting provides a new perspective on adapting pre-trained models in vision and is particularly effective for CLIP and robust to distribution shift, achieving performance competitive with standard linear probes.

344 0

Visual Prompting via Image Inpainting

Alexei A. Efros, Trevor Darrell, Amir Bar, Yossi Gandelsman, A. Globerson•Wed Aug 31 2022

This paper investigates visual prompting: given input-output image example(s) of a new task at test time and a new input image, the goal is to automatically produce the output image, consistent with the given examples, and shows that posing this problem as simple image inpainting turns out to be surprisingly effective.

271 0

Understanding and Improving Visual Prompting: A Label-Mapping Perspective

Yuguang Yao, Pin-Yu Chen, Aochuan Chen, Sijia Liu, Yihua Zhang•Sun Nov 20 2022

A new VP framework, termed ILM-VP (iterative label mapping-based visual prompting), which automatically re-maps the source labels to the target labels and progressively improves the target task accuracy of VP is proposed.

99 0

Unleashing the Power of Visual Prompting At the Pixel Level

A. Yuille, Cihang Xie, Chen Wei, Xianhang Li, Junyang Wu, Huiyu Wang, Yuyin Zhou•Tue Dec 20 2022

A simple and effective visual prompting method for adapting pre-trained models to downstream recognition tasks, which sets a new record of 82.8% average accuracy across 12 popular classification datasets, substantially surpassing the prior art by +5.6%.

48 0

Text-Visual Prompting for Efficient 2D Temporal Video Grounding

Jinghan Jia, Sijia Liu, Yimeng Zhang, Xin Chen, Ke Ding•Wed Mar 08 2023

This paper proposes a novel text-visual prompting (TVP) framework, which incorporates optimized perturbation patterns (that the authors call 'prompts') into both visual inputs and textual features of a TVG model and shows that TVP allows us to effectively co-train vision encoder and language encoder in a 2D TVG models and improves the performance of crossmodal feature fusion using only low-complexity sparse 2D visual features.

32 0

Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V

Jianwei Yang, Chun-yue Li, Jianfeng Gao, Xueyan Zou, Hao Zhang, Feng Li•Sat Dec 31 2022

The experiments show that GPT-4V with SoM outperforms the state-of-the-art fully-finetuned referring segmentation model on RefCOCOg in a zero-shot setting and the effectiveness of SoM on a wide range of fine-grained vision and multimodal tasks.

296 0

Adding a benchmark result helps the community track progress.

Visual Prompting | State-of-the-Art