Noise-Robust Tiny Object Localization with Flows

TL;DR

This paper introduces TOLF, a novel noise-robust framework for tiny object localization that uses normalizing flows and uncertainty-guided optimization to improve detection accuracy under noisy annotations.

Contribution

TOLF employs flow-based error modeling and uncertainty-aware training to enhance tiny object detection robustness against annotation noise, a novel approach in this domain.

Findings

TOLF improves AP by 1.2% on AI-TOD dataset.

Flow-based error modeling captures complex prediction distributions.

Uncertainty-guided optimization reduces overfitting to noisy labels.

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.