The reviewed record of science sign in
Pith

arxiv: 2303.09792 · v3 · pith:K5V4IYZA · submitted 2023-03-17 · cs.CV

Exploring Sparse Visual Prompt for Domain Adaptive Dense Prediction

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:K5V4IYZArecord.jsonopen to challenge →

classification cs.CV
keywords domainpromptpromptsvisualimage-levelparameterssvdptarget
0
0 comments X
read the original abstract

The visual prompts have provided an efficient manner in addressing visual cross-domain problems. In previous works, Visual Domain Prompt (VDP) first introduces domain prompts to tackle the classification Test-Time Adaptation (TTA) problem by warping image-level prompts on the input and fine-tuning prompts for each target domain. However, since the image-level prompts mask out continuous spatial details in the prompt-allocated region, it will suffer from inaccurate contextual information and limited domain knowledge extraction, particularly when dealing with dense prediction TTA problems. To overcome these challenges, we propose a novel Sparse Visual Domain Prompts (SVDP) approach, which holds minimal trainable parameters (e.g., 0.1\%) in the image-level prompt and reserves more spatial information of the input. To better apply SVDP in extracting domain-specific knowledge, we introduce the Domain Prompt Placement (DPP) method to adaptively allocates trainable parameters of SVDP on the pixels with large distribution shifts. Furthermore, recognizing that each target domain sample exhibits a unique domain shift, we design Domain Prompt Updating (DPU) strategy to optimize prompt parameters differently for each sample, facilitating efficient adaptation to the target domain. Extensive experiments were conducted on widely-used TTA and continual TTA benchmarks, and our proposed method achieves state-of-the-art performance in both semantic segmentation and depth estimation tasks.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. MoASE++: Mixture of Activation Sparsity Experts with Domain-Adaptive On-policy Distillation for Continual Test Time Adaptation

    cs.CV 2026-05 unverdicted novelty 5.0

    MoASE++ combines activation sparsity experts with domain-adaptive on-policy distillation to achieve state-of-the-art continual test-time adaptation on image classification and segmentation benchmarks.