Papers › See Better Before Looking Closer: Weakly Supervised Data Augmentation Network for...

See Better Before Looking Closer: Weakly Supervised Data Augmentation Network for Fine-Grained Visual Classification

26 Jan 2019arXiv:1901.09891archive 2025-07-28

Tao Hu, Honggang Qi, Qingming Huang, Yan Lu

Data augmentation is usually adopted to increase the amount of training data, prevent overfitting and improve the performance of deep models. However, in practice, random data augmentation, such as random image cropping, is low-efficiency and might introduce many uncontrolled background noises. In this paper, we propose Weakly Supervised Data Augmentation Network (WS-DAN) to explore the potential of data augmentation. Specifically, for each training image, we first generate attention maps to represent the object's discriminative parts by weakly supervised learning. Next, we augment the image guided by these attention maps, including attention cropping and attention dropping. The proposed WS-DAN improves the classification accuracy in two folds. In the first stage, images can be seen better since more discriminative parts' features will be extracted. In the second stage, attention regions provide accurate location of object, which ensures our model to look at the object closer and further improve the performance. Comprehensive experiments in common fine-grained visual classification datasets show that our WS-DAN surpasses the state-of-the-art methods, which demonstrates its effectiveness.

PaperPDFCode

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

Code

Victory8858/WS-DAN-Paddle mentioned on GitHubpaddle report
mv-lab/ViT-FGVC8 mentioned on GitHub report
tau-yihouxiang/WS_DAN mentioned on GitHubtf report
wvinzh/WS_DAN_PyTorch mentioned on GitHubpytorch 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

Data AugmentationFine-Grained Image ClassificationGeneral ClassificationImage CroppingWeakly-supervised Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Fine-Grained Image Classification CUB-200-2011 WS-DAN Accuracy 89.4 #16 of 30 Archive leaderboard report
Fine-Grained Image Classification FGVC Aircraft WS-DAN Accuracy 93.0% #31 of 57 Archive leaderboard report
Fine-Grained Image Classification Stanford Cars WS-DAN Accuracy 94.5% #42 of 83 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