StairNet: Top-Down Semantic Aggregation for Accurate One Shot Detection
This addresses a known bottleneck in object detection for computer vision applications, but it is incremental as it builds on the SSD framework.
The paper tackles the problem of small object detection in one-stage detectors like SSD by introducing a top-down feature combining module to spread strong semantics to lower layers, resulting in StairNet which significantly improves SSD's performance on PASCAL VOC datasets.
One-stage object detectors such as SSD or YOLO already have shown promising accuracy with small memory footprint and fast speed. However, it is widely recognized that one-stage detectors have difficulty in detecting small objects while they are competitive with two-stage methods on large objects. In this paper, we investigate how to alleviate this problem starting from the SSD framework. Due to their pyramidal design, the lower layer that is responsible for small objects lacks strong semantics(e.g contextual information). We address this problem by introducing a feature combining module that spreads out the strong semantics in a top-down manner. Our final model StairNet detector unifies the multi-scale representations and semantic distribution effectively. Experiments on PASCAL VOC 2007 and PASCAL VOC 2012 datasets demonstrate that StairNet significantly improves the weakness of SSD and outperforms the other state-of-the-art one-stage detectors.