logo
CanyamAI summaries for academic research
language
MobileMobile
  • Phone FeatureWeChat Mini Program
EnglishEnglish
noticeNotice
BlogBlog
delete
arrow
Return

Closed-loop correction reprogramming for fine-grained visual prompting

delete2026-04-23
delete0
PRE
AI
X
Xueyi Zhang
Y
Yuan Liao
S
Siqi Cai *
M
Mingrui Lao
H
Haizhou Li
DOI：10.1016/j.neunet.2026.108991delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
• We propose CCR, a dual-stream visual reprogramming framework with feedback control. • A proportional controller dynamically adjusts attention based on prediction error. • CCR improves accuracy by up to 10.8% with only 0.64% additional parameters. • Our method yields interpretable attention without requiring supervision.
Keywords:
CCR
visual reprogramming
feedback control
attention mechanism
fine-grained visual prompting

Journal

Neural Networks cover
Neural Networks
IF:
6.3
Papers:
8.3K
Citations:
3.0W

Organization

T
the chinese university of hong kong
Scholars:
4.5K
Papers: 2.1K
Citations: 0
N
national university of defense technology
Scholars:
5.0K
Papers: 1.5K
Citations: 0
H
Harbin Institute of Technology
Scholars:
1.6W
Papers: 5.0K
Citations: 8.5W
researcher View more organizations
Cited Papers

Cited Papers

No cited papers available