Sill-Net: Feature Augmentation with Separated Illumination Representation

6 Feb 2021  ·  Haipeng Zhang, Zhong Cao, Ziang Yan, ChangShui Zhang ·

For visual object recognition tasks, the illumination variations can cause distinct changes in object appearance and thus confuse the deep neural network based recognition models. Especially for some rare illumination conditions, collecting sufficient training samples could be time-consuming and expensive. To solve this problem, in this paper we propose a novel neural network architecture called Separating-Illumination Network (Sill-Net). Sill-Net learns to separate illumination features from images, and then during training we augment training samples with these separated illumination features in the feature space. Experimental results demonstrate that our approach outperforms current state-of-the-art methods in several object classification benchmarks.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data 		Result Benchmark
Traffic Sign Recognition BelgaLogos Sill-Net Accuracy 89.48 # 1
Compare
Traffic Sign Recognition Belgian Traffic Sign Classification Sill-Net Accuracy 98.97 # 1
Compare
Traffic Sign Recognition Chinese Traffic Sign Database Sill-Net Accuracy 97.19 # 1
Compare
Few-Shot Image Classification CIFAR-FS 5-way (1-shot) Illumination Augmentation Accuracy 87.73 # 5
Compare
Few-Shot Image Classification CIFAR-FS 5-way (5-shot) Illumination Augmentation Accuracy 91.09 # 6
Compare
Few-Shot Image Classification CUB 200 5-way 1-shot Illumination Augmentation Accuracy 94.73 # 6
Compare
Few-Shot Image Classification CUB 200 5-way 5-shot Illumination Augmentation Accuracy 96.28 # 5
Compare
Traffic Sign Recognition FlickrLogos-32 Sill-Net Accuracy 95.80 # 1
Compare
Traffic Sign Recognition GTSRB Sill-Net Accuracy 99.68% # 2
Compare
Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) Illumination Augmentation Accuracy 82.99 # 11
Compare
Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) Illumination Augmentation Accuracy 89.14 # 13
Compare
Traffic Sign Recognition TopLogo-10 Sill-Net Accuracy 89.66 # 1
Compare
Traffic Sign Recognition Tsinghua-Tencent 100K Sill-Net Accuracy 99.53 # 1
Compare

Methods
Add Remove

No methods listed for this paper. Add relevant methods here
Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy