https://github.com/AFeng-x/Draw-and-Understand
공식 코드Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want
Papers with Code 아카이브
Visual Prompting
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
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.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/FoundationVision/Groma
공식 코드Groma: Localized Visual Tokenization for Grounding Multimodal Large Language Models
https://github.com/IBM/AutoVP
공식 코드AutoVP: An Automated Visual Prompting Framework and Benchmark
https://github.com/Phoveran/vp-for-adversarial-robustness
공식 코드https://github.com/Qi-Zhangyang/GPT4Scene
공식 코드GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models
https://github.com/alhojel/visual_task_vectors
공식 코드https://github.com/amirbar/visual_prompting
공식 코드https://github.com/ant-8/GUI-Grounding-via-Iterative-Narrowing
공식 코드https://github.com/baaivision/emu
공식 코드https://github.com/baaivision/tokenize-anything
공식 코드https://github.com/casia-iva-lab/fastsam
공식 코드https://github.com/changdaeoh/blackvip
공식 코드BlackVIP: Black-Box Visual Prompting for Robust Transfer Learning
https://github.com/chenshihfang/GOT
공식 코드https://github.com/diamond264/ByMyEyes
공식 코드By My Eyes: Grounding Multimodal Large Language Models with Sensor Data via Visual Prompting
https://github.com/ezzzli/prompt-pate
공식 코드Exploring the Benefits of Visual Prompting in Differential Privacy
https://github.com/facebookresearch/segment-anything
공식 코드https://github.com/google-research-datasets/uicrit
공식 코드UICrit: Enhancing Automated Design Evaluation with a UICritique Dataset
https://github.com/hjbahng/visual_prompting
공식 코드https://github.com/hsb1357173526/dynamic_visual_prompting
공식 코드Adapting Pre-trained Language Models to Vision-Language Tasks via Dynamic Visual Prompting
https://github.com/ibm/vp-llr
공식 코드https://github.com/inst-it/inst-it
공식 코드Inst-IT: Boosting Multimodal Instance Understanding via Explicit Visual Prompt Instruction Tuning
https://github.com/intel/TVP
공식 코드Text-Visual Prompting for Efficient 2D Temporal Video Grounding
https://github.com/jieshibo/memvp
공식 코드Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning
https://github.com/jincan333/lor-vp
공식 코드LoR-VP: Low-Rank Visual Prompting for Efficient Vision Model Adaptation
https://github.com/landskape-ai/reprogram_lt
공식 코드https://github.com/leixy20/scaffold
공식 코드Scaffolding Coordinates to Promote Vision-Language Coordination in Large Multi-Modal Models
https://github.com/microsoft/SoM
공식 코드Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V
https://github.com/nifangbaage/explicit-visual-prompt
공식 코드Explicit Visual Prompting for Low-Level Structure Segmentations
https://github.com/olivesgatech/pointprompt
공식 코드Benchmarking Human and Automated Prompting in the Segment Anything Model
https://github.com/optml-group/ilm-vp
공식 코드Understanding and Improving Visual Prompting: A Label-Mapping Perspective
https://github.com/rafiibnsultan/geosam
공식 코드GeoSAM: Fine-tuning SAM with Multi-Modal Prompts for Mobility Infrastructure Segmentation
https://github.com/sampson-lee/onlinemmsi
공식 코드https://github.com/sergiotasconmorales/locvqallm
공식 코드Targeted Visual Prompting for Medical Visual Question Answering
https://github.com/shahzadnit/ez-clip
공식 코드https://github.com/shikiw/dam-vp
공식 코드https://github.com/soon-yau/upgpt
공식 코드UPGPT: Universal Diffusion Model for Person Image Generation, Editing and Pose Transfer
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.