RegNet: Self-Regulated Network for Image Classification

3 Jan 2021  ·  Jing Xu, Yu Pan, Xinglin Pan, Steven Hoi, Zhang Yi, Zenglin Xu ·

The ResNet and its variants have achieved remarkable successes in various computer vision tasks. Despite its success in making gradient flow through building blocks, the simple shortcut connection mechanism limits the ability of re-exploring new potentially complementary features due to the additive function. To address this issue, in this paper, we propose to introduce a regulator module as a memory mechanism to extract complementary features, which are further fed to the ResNet. In particular, the regulator module is composed of convolutional RNNs (e.g., Convolutional LSTMs or Convolutional GRUs), which are shown to be good at extracting Spatio-temporal information. We named the new regulated networks as RegNet. The regulator module can be easily implemented and appended to any ResNet architecture. We also apply the regulator module for improving the Squeeze-and-Excitation ResNet to show the generalization ability of our method. Experimental results on three image classification datasets have demonstrated the promising performance of the proposed architecture compared with the standard ResNet, SE-ResNet, and other state-of-the-art architectures.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Image Classification GasHisSDB RegNetY-3.2GF Accuracy 97.48 # 7
Precision 99.97 # 1
F1-Score 98.70 # 7
Medical Image Classification NCT-CRC-HE-100K RegNetY-3.2GF Accuracy (%) 95.42 # 3
F1-Score 97.39 # 3
Precision 99.97 # 2
Specificity 99.43 # 2