PSP-FSOD improves cross-domain few-shot object detection by prompting a VLM to jointly vary foreground and background in generated training images, plus Gaussian feature perturbation with distribution correction.
Lei Qi, Hongpeng Yang, Yinghuan Shi, and Xin Geng
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Prompt-Driven Simulation with Feature Perturbation for Cross-Domain Few-Shot Object Detection
PSP-FSOD improves cross-domain few-shot object detection by prompting a VLM to jointly vary foreground and background in generated training images, plus Gaussian feature perturbation with distribution correction.