A systematic study of the foreground-background imbalance problem in deep learning for object detection

by   Hanxue Gu, et al.

The class imbalance problem in deep learning has been explored in several studies, but there has yet to be a systematic analysis of this phenomenon in object detection. Here, we present comprehensive analyses and experiments of the foreground-background (F-B) imbalance problem in object detection, which is very common and caused by small, infrequent objects of interest. We experimentally study the effects of different aspects of F-B imbalance (object size, number of objects, dataset size, object type) on detection performance. In addition, we also compare 9 leading methods for addressing this problem, including Faster-RCNN, SSD, OHEM, Libra-RCNN, Focal-Loss, GHM, PISA, YOLO-v3, and GFL with a range of datasets from different imaging domains. We conclude that (1) the F-B imbalance can indeed cause a significant drop in detection performance, (2) The detection performance is more affected by F-B imbalance when fewer training data are available, (3) in most cases, decreasing object size leads to larger performance drop than decreasing number of objects, given the same change in the ratio of object pixels to non-object pixels, (6) among all selected methods, Libra-RCNN and PISA demonstrate the best performance in addressing the issue of F-B imbalance. (7) When the training dataset size is large, the choice of method is not impactful (8) Soft-sampling methods, including focal-loss, GHM, and GFL, perform fairly well on average but are relatively unstable.


ARUBA: An Architecture-Agnostic Balanced Loss for Aerial Object Detection

Deep neural networks tend to reciprocate the bias of their training data...

Foreground-Background Imbalance Problem in Deep Object Detectors: A Review

Recent years have witnessed the remarkable developments made by deep lea...

Imbalance Problems in Object Detection: A Review

In this paper, we present a comprehensive review of the imbalance proble...

Alleviating Class-wise Gradient Imbalance for Pulmonary Airway Segmentation

Automated airway segmentation is a prerequisite for pre-operative diagno...

Compensating class imbalance for acoustic chimpanzee detection with convolutional recurrent neural networks

Automatic detection systems are important in passive acoustic monitoring...

Floaters No More: Radiance Field Gradient Scaling for Improved Near-Camera Training

NeRF acquisition typically requires careful choice of near planes for th...

Detecting Object States vs Detecting Objects: A New Dataset and a Quantitative Experimental Study

The detection of object states in images (State Detection - SD) is a pro...

Please sign up or login with your details

Forgot password? Click here to reset