2 papers
cs.CV2025
CEM-FBGTinyDet: Context-Enhanced Foreground Balance with Gradient Tuning for tiny Objects
Tao Liu, Zhenchao Cui
Tiny object detection (TOD) reveals a fundamental flaw in feature pyramid networks: high-level features (P5-P6) frequently receive zero positive anchors under standard label assign…
cs.CV2024
SGDM: Static-Guided Dynamic Module Make Stronger Visual Models
Wenjie Xing, Zhenchao Cui, Jing Qi
The spatial attention mechanism has been widely used to improve object detection performance. However, its operation is currently limited to static convolutions lacking content-ada…