Papers with Code 아카이브
Visual Prompt Tuning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 4
- 보존된 평가 기록
- 40
Visual Prompt Tuning(VPT) only introduces a small amount of task-specific learnable parameters into the input space while freezing the entire pre-trained Transformer backbone during downstream training. In practice, these additional parameters are simply prepended into the input sequence of each Transformer layer and learned together with a linear head during fine-tuning. VPT is especially effective in the low-data regime, and maintains its advantage across data scales. Finally, VPT is competitive for a range of Transformer scales and designs (ViTBase/Large/Huge, Swin). Put together, the results suggest that VPT is one of the most effective ways of adapting ever-growing vision backbones.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Attention to Burstiness: Low-Rank Bilinear Prompt Tuning
DA-VPT: Semantic-Guided Visual Prompt Tuning for Vision Transformers
Q-Adapt: Adapting LMM for Visual Quality Assessment with Progressive Instruction Tuning
Visual Variational Autoencoder Prompt Tuning
Iterative Prompt Relocation for Distribution-Adaptive Visual Prompt Tuning
Exploring Interpretability for Visual Prompt Tuning with Hierarchical Concepts
Adaptive Prompt: Unlocking the Power of Visual Prompt Tuning
Prompt-CAM: A Simpler Interpretable Transformer for Fine-Grained Analysis
Harnessing Large Language and Vision-Language Models for Robust Out-of-Distribution Detection
MedFocusCLIP : Improving few shot classification in medical datasets using pixel wise attention
Defending Multimodal Backdoored Models by Repulsive Visual Prompt Tuning
Semantic Hierarchical Prompt Tuning for Parameter-Efficient Fine-Tuning
Adaptive Prompt Tuning: Vision Guided Prompt Tuning with Cross-Attention for Fine-Grained Few-Shot Learning
Med-PerSAM: One-Shot Visual Prompt Tuning for Personalized Segment Anything Model in Medical Domain
Visual Fourier Prompt Tuning
Improving Visual Prompt Tuning by Gaussian Neighborhood Minimization for Long-Tailed Visual Recognition
TuneVLSeg: Prompt Tuning Benchmark for Vision-Language Segmentation Models
End-to-end Multi-source Visual Prompt Tuning for Survival Analysis in Whole Slide Images
CVPT: Cross-Attention help Visual Prompt Tuning adapt visual task
SAN: Hypothesizing Long-Term Synaptic Development and Neural Engram Mechanism in Scalable Model's Parameter-Efficient Fine-Tuning
Probing the Efficacy of Federated Parameter-Efficient Fine-Tuning of Vision Transformers for Medical Image Classification
Visual Prompt Tuning in Null Space for Continual Learning
TAI++: Text as Image for Multi-Label Image Classification by Co-Learning Transferable Prompt
iVPT: Improving Task-relevant Information Sharing in Visual Prompt Tuning by Cross-layer Dynamic Connection
ECLIPSE: Efficient Continual Learning in Panoptic Segmentation with Visual Prompt Tuning
CoDA: Instructive Chain-of-Domain Adaptation with Severity-Aware Visual Prompt Tuning
LSPT: Long-term Spatial Prompt Tuning for Visual Representation Learning
CoLLaVO: Crayon Large Language and Vision mOdel
Revisiting the Power of Prompt for Visual Tuning
Facing the Elephant in the Room: Visual Prompt Tuning or Full Finetuning?
Plug-and-Play Transformer Modules for Test-Time Adaptation
Open Vocabulary Semantic Scene Sketch Understanding
SA$^2$VP: Spatially Aligned-and-Adapted Visual Prompt
Progressive Learning with Visual Prompt Tuning for Variable-Rate Image Compression
Towards Few-shot Out-of-Distribution Detection
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.