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

By Y. Kim, Bong-Nam Kang, Daijin Kim. 2018

63 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection (2019, background): “Many recent works [7, 16, 17, 34, 38, 39, 40, 43, 41] propose various cross-scale connections or operations to combine features to generate pyramidal feature representations.”
Detecting tiny objects in aerial images: A normalized Wasserstein distance and a new benchmark (2022, unknown): “Besides, Kim et al. (Kim et al., 2018) introduce Scale-Aware Network (SAN) and map the features extracted from different spaces onto a scale-invariant subspace, making detectors more robust to scale variation.”
A Normalized Gaussian Wasserstein Distance for Tiny Object Detection (2021, unknown): “[10] introduce Scale-Aware Network (SAN) and map the features extracted from different spaces onto a scale-invariant subspace, making detectors more robust to scale variation.”
No More Strided Convolutions or Pooling: A New CNN Building Block for Low-Resolution Images and Small Objects (2022, background): “Moreover, SAN [15] was introduced to map multi-scale features onto a scale-invariant subspace to make a detector more robust to scale variation.”
Multi-Scale Positive Sample Refinement for Few-Shot Object Detection (2020, background): “The scale invariance has been widely explored in generic supervised detectors [11,33,34,18], while it remains largely intact in FSOD.”
Deep Learning for Generic Object Detection: A Survey (2018, background): “代表的な手法として,SharpMask [214], Deconvolutional Single Shot Detector (DSSD) [77], Feature Pyramid Network (FPN) [167], Top Down Modulation (TDM) [247], Reverse connection with Objectness prior Network (RON) [136], ZIP [156], Scale Transfer Detection Network (STDN) [321], RefineDet [308], StairNet [283], ”