Detecting Small, Densely Distributed Objects with Filter-Amplifier Networks and Loss Boosting

by   Zhenhua Chen, et al.

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.



There are no comments yet.


page 4

page 5

page 6


Ensembling object detectors for image and video data analysis

In this paper, we propose a method for ensembling the outputs of multipl...

Oriented Bounding Boxes for Small and Freely Rotated Objects

A novel object detection method is presented that handles freely rotated...

EAGLE: Large-scale Dataset for Vehicle Detection in Aerial Imagery

Multi-class vehicle detection from airborne imagery with orientation est...

Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss

Boundary discontinuity and its inconsistency to the final detection metr...

SCRDet++: Detecting Small, Cluttered and Rotated Objects via Instance-Level Feature Denoising and Rotation Loss Smoothing

Small and cluttered objects are common in real-world which are challengi...

Localization with Limited Annotation

Localization of an object within an image is a common task in medical im...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.