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/coradlut/bi-jros
https://github.com/ddupont808/gpt-4v-act
Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V
https://github.com/digantamisra98/digantamisra98.github.io
https://github.com/geekyutao/inpaint-anything
https://github.com/harrytea/detect-anyshadow
https://github.com/huggingface/transformers
https://github.com/idea-research/t-rex
https://github.com/kornia/kornia
https://github.com/ksugar/samapi
https://github.com/lancasterli/refsam
https://github.com/li-qingyun/sam-mmrotate
https://github.com/martinsbruveris/tensorflow-image-models
https://github.com/microsoft/VLM-Video-Action-Localization
Open-Vocabulary Action Localization with Iterative Visual Prompting
https://github.com/nifangbaage/explict-visual-prompt
Explicit Visual Prompting for Universal Foreground Segmentations
https://github.com/philippendres/CellPilot
https://github.com/pwc-1/Paper-10/tree/main/sam
https://github.com/pwc-1/Paper-9/tree/main/5/vipllava
ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts
https://github.com/rayat137/VisualPromptGFSS
Visual Prompting for Generalized Few-shot Segmentation: A Multi-scale Approach
https://github.com/sqhuang0103/samreg
https://github.com/syscv/sam-hq
https://github.com/umass-foundation-model/3d-llm
https://github.com/ux-decoder/segment-everything-everywhere-all-at-once
https://github.com/ux-decoder/semantic-sam
https://github.com/vineet2104/hifics
https://github.com/vitae-transformer/samrs
https://github.com/xinghaochen/tinysam
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.