Distribution-Aware Calibration for Object Detection with Noisy Bounding Boxes

TL;DR

This paper introduces DISCO, a novel method that models proposal distributions to calibrate supervision signals, significantly improving object detection accuracy on noisy datasets.

Contribution

DISCO is the first approach to incorporate spatial distribution modeling for calibrating supervision in noisy object detection datasets.

Findings

Achieves state-of-the-art results on Pascal VOC and MS-COCO with noisy annotations.

Effectively improves detection performance at high noise levels.

Introduces three distribution-aware techniques for proposal augmentation, box refinement, and confidence estimation.

Abstract

Large-scale well-annotated datasets are of great importance for training an effective object detector. However, obtaining accurate bounding box annotations is laborious and demanding. Unfortunately, the resultant noisy bounding boxes could cause corrupt supervision signals and thus diminish detection performance. Motivated by the observation that the real ground-truth is usually situated in the aggregation region of the proposals assigned to a noisy ground-truth, we propose DIStribution-aware CalibratiOn (DISCO) to model the spatial distribution of proposals for calibrating supervision signals. In DISCO, spatial distribution modeling is performed to statistically extract the potential locations of objects. Based on the modeled distribution, three distribution-aware techniques, i.e., distribution-aware proposal augmentation (DA-Aug), distribution-aware box refinement (DA-Ref), and distribution-aware confidence estimation (DA-Est), are developed to improve classification, localization, and interpretability, respectively. Extensive experiments on large-scale noisy image datasets (i.e., Pascal VOC and MS-COCO) demonstrate that DISCO can achieve state-of-the-art detection performance, especially at high noise levels. Code is available at https://github.com/Correr-Zhou/DISCO.