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

05/23/2019
by   Xiang Li, et al.
0

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. However, the activation of these sub-features is often spatially affected by similar patterns and noisy backgrounds, resulting in erroneous localization and identification. We propose a Spatial Group-wise Enhance (SGE) module that can adjust the importance of each sub-feature by generating an attention factor for each spatial location in each semantic group, so that every individual group can autonomously enhance its learnt expression and suppress possible noise. The attention factors are only guided by the similarities between the global and local feature descriptors inside each group, thus the design of SGE module is extremely lightweight with almost no extra parameters and calculations. Despite being trained with only category supervisions, the SGE component is extremely effective in highlighting multiple active areas with various high-order semantics (such as the dog's eyes, nose, etc.). When integrated with popular CNN backbones, SGE can significantly boost the performance of image recognition tasks. Specifically, based on ResNet50 backbones, SGE achieves 1.2% Top-1 accuracy improvement on the ImageNet benchmark and 1.0∼2.0% AP gain on the COCO benchmark across a wide range of detectors (Faster/Mask/Cascade RCNN and RetinaNet). Codes and pretrained models are available at https://github.com/implus/PytorchInsight.

READ FULL TEXT

page 2

page 4

page 5

research
03/28/2021

BA^2M: A Batch Aware Attention Module for Image Classification

The attention mechanisms have been employed in Convolutional Neural Netw...
research
09/02/2020

IAUnet: Global Context-Aware Feature Learning for Person Re-Identification

Person re-identification (reID) by CNNs based networks has achieved favo...
research
04/05/2019

Relation-Aware Global Attention

Attention mechanism aims to increase the representation power by focusin...
research
05/23/2023

Efficient Multi-Scale Attention Module with Cross-Spatial Learning

Remarkable effectiveness of the channel or spatial attention mechanisms ...
research
04/13/2023

Boosting Convolutional Neural Networks with Middle Spectrum Grouped Convolution

This paper proposes a novel module called middle spectrum grouped convol...
research
07/23/2020

Funnel Activation for Visual Recognition

We present a conceptually simple but effective funnel activation for ima...
research
07/18/2020

Volumetric Transformer Networks

Existing techniques to encode spatial invariance within deep convolution...

Please sign up or login with your details

Forgot password? Click here to reset