Spatial Group-wise Enhance: Improving Semantic Feature Learning in Convolutional Networks

23 May 2019Xiang LiXiaolin HuJian Yang

The Convolutional Neural Networks (CNNs) generate the feature representation of complex objects by collecting hierarchical and different parts of semantic sub-features. These sub-features can usually be distributed in grouped form in the feature vector of each layer, representing various semantic entities... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Image Classification ImageNet SGE-ResNet101 Top 1 Accuracy 78.7980% # 80
Top 5 Accuracy 94.3680% # 57

Methods used in the Paper