Papers › Sill-Net: Feature Augmentation with Separated Illumination Representation

Sill-Net: Feature Augmentation with Separated Illumination Representation

6 Feb 2021arXiv:2102.03539archive 2025-07-28

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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

lanfenghuanyu/Sill-Net officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Few-Shot Image ClassificationImage ClassificationObjectObject RecognitionTraffic Sign Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Image Classification CIFAR-FS 5-way (1-shot) Illumination Augmentation Accuracy 87.73 #5 of 38 Archive leaderboard report
Few-Shot Image Classification CIFAR-FS 5-way (5-shot) Illumination Augmentation Accuracy 91.09 #6 of 39 Archive leaderboard report
Few-Shot Image Classification CUB 200 5-way 1-shot Illumination Augmentation Accuracy 94.73 #6 of 36 Archive leaderboard report
Few-Shot Image Classification CUB 200 5-way 5-shot Illumination Augmentation Accuracy 96.28 #5 of 32 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) Illumination Augmentation Accuracy 82.99 #11 of 105 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) Illumination Augmentation Accuracy 89.14 #13 of 95 Archive leaderboard report
Traffic Sign Recognition BelgaLogos Sill-Net Accuracy 89.48 #1 of 1 Archive leaderboard report
Traffic Sign Recognition Belgian Traffic Sign Classification Sill-Net Accuracy 98.97 #1 of 1 Archive leaderboard report
Traffic Sign Recognition Chinese Traffic Sign Database Sill-Net Accuracy 97.19 #1 of 1 Archive leaderboard report
Traffic Sign Recognition FlickrLogos-32 Sill-Net Accuracy 95.80 #1 of 1 Archive leaderboard report
Traffic Sign Recognition GTSRB Sill-Net Accuracy 99.68% #2 of 5 Archive leaderboard report
Traffic Sign Recognition TopLogo-10 Sill-Net Accuracy 89.66 #1 of 1 Archive leaderboard report
Traffic Sign Recognition Tsinghua-Tencent 100K Sill-Net Accuracy 99.53 #6 of 6 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections