Reducing Label Noise in Anchor-Free Object Detection
This work addresses label noise in object detection for computer vision applications, representing an incremental improvement over existing anchor-free methods.
The paper tackles label noise in anchor-free object detectors by proposing a new labeling strategy that sum-pools predictions to reduce contributions from non-discriminatory features, resulting in PPDet achieving top performance among anchor-free top-down detectors on COCO and outperforming major methods in small object detection with an AP_S of 31.4.
Current anchor-free object detectors label all the features that spatially fall inside a predefined central region of a ground-truth box as positive. This approach causes label noise during training, since some of these positively labeled features may be on the background or an occluder object, or they are simply not discriminative features. In this paper, we propose a new labeling strategy aimed to reduce the label noise in anchor-free detectors. We sum-pool predictions stemming from individual features into a single prediction. This allows the model to reduce the contributions of non-discriminatory features during training. We develop a new one-stage, anchor-free object detector, PPDet, to employ this labeling strategy during training and a similar prediction pooling method during inference. On the COCO dataset, PPDet achieves the best performance among anchor-free top-down detectors and performs on-par with the other state-of-the-art methods. It also outperforms all major one-stage and two-stage methods in small object detection (${AP}_{S}$ $31.4$). Code is available at https://github.com/nerminsamet/ppdet