SAN: Learning Relationship between Convolutional Features for Multi-Scale Object Detection

by   Yonghyun Kim, et al.

Most of the recent successful methods in accurate object detection build on the convolutional neural networks (CNN). However, due to the lack of scale normalization in CNN-based detection methods, the activated channels in the feature space can be completely different according to a scale and this difference makes it hard for the classifier to learn samples. We propose a Scale Aware Network (SAN) that maps the convolutional features from the different scales onto a scale-invariant subspace to make CNN-based detection methods more robust to the scale variation, and also construct a unique learning method which considers purely the relationship between channels without the spatial information for the efficient learning of SAN. To show the validity of our method, we visualize how convolutional features change according to the scale through a channel activation matrix and experimentally show that SAN reduces the feature differences in the scale space. We evaluate our method on VOC PASCAL and MS COCO dataset. We demonstrate SAN by conducting several experiments on structures and parameters. The proposed SAN can be generally applied to many CNN-based detection methods to enhance the detection accuracy with a slight increase in the computing time.


page 5

page 14


Object Detection for Comics using Manga109 Annotations

With the growth of digitized comics, image understanding techniques are ...

BAN: Focusing on Boundary Context for Object Detection

Visual context is one of the important clue for object detection and the...

GraphFPN: Graph Feature Pyramid Network for Object Detection

Feature pyramids have been proven powerful in image understanding tasks ...

A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets

This survey paper specially analyzed computer vision-based object detect...

STN-Homography: estimate homography parameters directly

In this paper, we introduce the STN-Homography model to directly estimat...

Learning Localized Geometric Features Using 3D-CNN: An Application to Manufacturability Analysis of Drilled Holes

3D convolutional neural networks (3D-CNN) have been used for object reco...

Learning and Visualizing Localized Geometric Features Using 3D-CNN: An Application to Manufacturability Analysis of Drilled Holes

3D Convolutional Neural Networks (3D-CNN) have been used for object reco...

Please sign up or login with your details

Forgot password? Click here to reset