Detecting Small, Densely Distributed Objects with Filter-Amplifier Networks and Loss Boosting
This addresses the problem of small object detection for applications like PCB inspection and aerial imagery, representing an incremental advancement with novel techniques.
The paper tackles the challenge of detecting small, densely distributed objects by proposing Filter-Amplifier Networks to estimate pixel-wise boundary likelihood and Loss Boosting to address loss imbalance, achieving significant improvements in accuracy, recall, and average IoU over state-of-the-art methods on PCB and VEDAI datasets.
Detecting small, densely distributed objects is a significant challenge: small objects often contain less distinctive information compared to larger ones, and finer-grained precision of bounding box boundaries are required. In this paper, we propose two techniques for addressing this problem. First, we estimate the likelihood that each pixel belongs to an object boundary rather than predicting coordinates of bounding boxes (as YOLO, Faster-RCNN and SSD do), by proposing a new architecture called Filter-Amplifier Networks (FANs). Second, we introduce a technique called Loss Boosting (LB) which attempts to soften the loss imbalance problem on each image. We test our algorithm on the problem of detecting electrical components on a new, realistic, diverse dataset of printed circuit boards (PCBs), as well as the problem of detecting vehicles in the Vehicle Detection in Aerial Imagery (VEDAI) dataset. Experiments show that our method works significantly better than current state-of-the-art algorithms with respect to accuracy, recall and average IoU.