Noise-Robust Tiny Object Localization with Flows

📝 Original Info

• Title: Noise-Robust Tiny Object Localization with Flows
• ArXiv ID: 2601.00617
• Date: 2026-01-02
• Authors: Huixin Sun, Linlin Yang, Ronyu Chen, Kerui Gu, Baochang Zhang, Angela Yao, Xianbin Cao

📝 Abstract

Despite significant advances in generic object detection, a persistent performance gap remains for tiny objects compared to normal-scale objects. We demonstrate that tiny objects are highly sensitive to annotation noise, where optimizing strict localization objectives risks noise overfitting. To address this, we propose Tiny Object Localization with Flows (TOLF), a noise-robust localization framework leveraging normalizing flows for flexible error modeling and uncertainty-guided optimization. Our method captures complex, non-Gaussian prediction distributions through flow-based error modeling, enabling robust learning under noisy supervision. An uncertainty-aware gradient modulation mechanism further suppresses learning from high-uncertainty, noise-prone samples, mitigating overfitting while stabilizing training. Extensive experiments across three datasets validate our approach's effectiveness. Especially, TOLF boosts the DINO baseline by 1.2% AP on the AI-TOD dataset.

📄 Full Content

...(본문 내용이 길어 생략되었습니다. 사이트에서 전문을 확인해 주세요.)