Distribution-Aware Calibration for Object Detection with Noisy Bounding Boxes
This addresses the challenge of labor-intensive and error-prone annotation in object detection for computer vision applications, offering an incremental improvement over existing methods.
The paper tackles the problem of noisy bounding box annotations in object detection by proposing DISCO, a distribution-aware calibration method that models proposal spatial distributions to improve supervision signals, achieving state-of-the-art performance on Pascal VOC and MS-COCO datasets, especially at high noise levels.
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.