Towards Noise-resistant Object Detection with Noisy Annotations
This addresses the costly need for accurate annotations in object detection by enabling training with noisy data, though it is an incremental improvement over existing noise-handling methods.
The paper tackles the problem of training object detectors with noisy annotations containing both label and bounding box errors, proposing a framework that jointly optimizes noise correction and model training to achieve state-of-the-art performance on PASCAL VOC and MS-COCO datasets.
Training deep object detectors requires significant amount of human-annotated images with accurate object labels and bounding box coordinates, which are extremely expensive to acquire. Noisy annotations are much more easily accessible, but they could be detrimental for learning. We address the challenging problem of training object detectors with noisy annotations, where the noise contains a mixture of label noise and bounding box noise. We propose a learning framework which jointly optimizes object labels, bounding box coordinates, and model parameters by performing alternating noise correction and model training. To disentangle label noise and bounding box noise, we propose a two-step noise correction method. The first step performs class-agnostic bounding box correction by minimizing classifier discrepancy and maximizing region objectness. The second step distils knowledge from dual detection heads for soft label correction and class-specific bounding box refinement. We conduct experiments on PASCAL VOC and MS-COCO dataset with both synthetic noise and machine-generated noise. Our method achieves state-of-the-art performance by effectively cleaning both label noise and bounding box noise. Code to reproduce all results will be released.