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.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Learning Visual Prompts for Guiding the Attention of Vision Transformers
Analogist: Out-of-the-box Visual In-Context Learning with Image Diffusion Model
MoVL:Exploring Fusion Strategies for the Domain-Adaptive Application of Pretrained Models in Medical Imaging Tasks
Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning
Open-Set Video-based Facial Expression Recognition with Human Expression-sensitive Prompting
Groma: Localized Visual Tokenization for Grounding Multimodal Large Language Models
BLINK: Multimodal Large Language Models Can See but Not Perceive
Exploring the Transferability of Visual Prompting for Multimodal Large Language Models
Visual Prompting for Generalized Few-shot Segmentation: A Multi-scale Approach
Finding Visual Task Vectors
Medical Visual Prompting (MVP): A Unified Framework for Versatile and High-Quality Medical Image Segmentation
Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want
Explore until Confident: Efficient Exploration for Embodied Question Answering
On the low-shot transferability of [V]-Mamba
MOKA: Open-World Robotic Manipulation through Mark-Based Visual Prompting
Tumor segmentation on whole slide images: training or prompting?
Scaffolding Coordinates to Promote Vision-Language Coordination in Large Multi-Modal Models
PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs
Generative Multimodal Models are In-Context Learners
LaViP:Language-Grounded Visual Prompts
3DAxiesPrompts: Unleashing the 3D Spatial Task Capabilities of GPT-4V
Tokenize Anything via Prompting
EZ-CLIP: Efficient Zeroshot Video Action Recognition
ViscoNet: Bridging and Harmonizing Visual and Textual Conditioning for ControlNet
Visual Prompting Upgrades Neural Network Sparsification: A Data-Model Perspective
ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts
T-Rex: Counting by Visual Prompting
Visual In-Context Prompting
GeoSAM: Fine-tuning SAM with Multi-Modal Prompts for Mobility Infrastructure Segmentation
Towards Robust and Accurate Visual Prompting
Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V
Unifying Image Processing as Visual Prompting Question Answering
AutoVP: An Automated Visual Prompting Framework and Benchmark
VPA: Fully Test-Time Visual Prompt Adaptation
Uncovering the Hidden Cost of Model Compression
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.