Layer-wise Customized Weak Segmentation Block and AIoU Loss for Accurate Object Detection

TL;DR

This paper introduces a scale-customized weak segmentation block and an adaptive IoU loss to improve object detection accuracy across different object sizes, addressing scale variation and sample imbalance issues.

Contribution

It proposes a novel scale-customized weak segmentation block and an adaptive IoU loss integrated into a single-shot detector for more accurate, scale-aware object detection.

Findings

Outperforms existing methods on PASCAL VOC and MS COCO datasets.

Effectively handles scale variation and class imbalance in object detection.

Achieves higher detection accuracy with improved bounding box precision.

Abstract

The anchor-based detectors handle the problem of scale variation by building the feature pyramid and directly setting different scales of anchors on each cell in different layers. However, it is difficult for box-wise anchors to guide the adaptive learning of scale-specific features in each layer because there is no one-to-one correspondence between box-wise anchors and pixel-level features. In order to alleviate the problem, in this paper, we propose a scale-customized weak segmentation (SCWS) block at the pixel level for scale customized object feature learning in each layer. By integrating the SCWS blocks into the single-shot detector, a scale-aware object detector (SCOD) is constructed to detect objects of different sizes naturally and accurately. Furthermore, the standard location loss neglects the fact that the hard and easy samples may be seriously imbalanced. A forthcoming problem is that it is unable to get more accurate bounding boxes due to the imbalance. To address this problem, an adaptive IoU (AIoU) loss via a simple yet effective squeeze operation is specified in our SCOD. Extensive experiments on PASCAL VOC and MS COCO demonstrate the superiority of our SCOD.