Strong-Background Restrained Cross Entropy Loss for Scene Text Detection
In this paper, we investigate the issue of class imbalance in scene text detection. Class Balanced Cross Entropy (CBCE) loss is often adopted for addressing this imbalance problem. We find that CBCE excessively restrains the backward gradients of background. Negative samples own extremely small weig...
Saved in:
Published in | 2019 International Joint Conference on Neural Networks (IJCNN) pp. 1 - 7 |
---|---|
Main Authors | , |
Format | Conference Proceeding |
Language | English |
Published |
IEEE
01.07.2019
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | In this paper, we investigate the issue of class imbalance in scene text detection. Class Balanced Cross Entropy (CBCE) loss is often adopted for addressing this imbalance problem. We find that CBCE excessively restrains the backward gradients of background. Negative samples own extremely small weights which are offered by CBCE during training of text detectors. These tiny weight values lead to insufficient learning of background. As a result, the CBCE-based text detection methods only can achieve sub-optimal performance. We propose a novel loss function, Strong-Background Restrained Cross Entropy (SBRCE), to deal with the disadvantage in CBCE. Specifically, SBRCE effectively down-weights the loss assigned to the strong background which means well-classified negative samples. Our SBRCE can make training focused on all positive samples and weak background(i.e., hard-classified negative samples). Moreover, it can prevent the enormous amount of strong background from overwhelming text detectors during training. Experimental results show that the proposed SBRCE can improve the performance of the efficient and accurate scene text detector (EAST) by F-score of 3.3% on ICDAR2015 dataset and 1.12% on MSRA-TD500 dataset, without sacrificing the training and testing speed of EAST. |
---|---|
ISSN: | 2161-4407 |
DOI: | 10.1109/IJCNN.2019.8852198 |