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

arXiv: https://arxiv.org/abs/1901.09891 · HTML: https://mlsanity.com/paper/1901.09891/

## Key facts

- Cited by 56 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jan 2019.

## Built on by (most cited first, 30 of 56)

- [Multi-attentional Deepfake Detection](https://mlsanity.com/paper/2103.02406/) (2021)
- [Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification](https://mlsanity.com/paper/2108.08728/) (2021)
- [End-to-End Diffusion Latent Optimization Improves Classifier Guidance](https://mlsanity.com/paper/2303.13703/) (2023)
- [Large Scale Visual Food Recognition](https://mlsanity.com/paper/2103.16107/) (2021)
- [CLIP-Art: Contrastive Pre-training for Fine-Grained Art Classification](https://mlsanity.com/paper/2204.14244/) (2022)
- [SportsCap: Monocular 3D Human Motion Capture and Fine-grained Understanding in Challenging Sports Videos](https://mlsanity.com/paper/2104.11452/) (2021)
- [Metrics for saliency map evaluation of deep learning explanation methods](https://mlsanity.com/paper/2201.13291/) (2022)
- [FoodLMM: A Versatile Food Assistant using Large Multi-modal Model](https://mlsanity.com/paper/2312.14991/) (2023)
- [Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classification](https://mlsanity.com/paper/2101.06635/) (2021)
- [Boosting Few-shot Fine-grained Recognition with Background Suppression and Foreground Alignment](https://mlsanity.com/paper/2210.01439/) (2022)
- [Fine-Grained Object Classification via Self-Supervised Pose Alignment](https://mlsanity.com/paper/2203.15987/) (2022)
- [Fine-grained Visual Classification with High-temperature Refinement and Background Suppression](https://mlsanity.com/paper/2303.06442/) (2023)
- [SR-GNN: Spatial Relation-aware Graph Neural Network for Fine-Grained Image Categorization](https://mlsanity.com/paper/2209.02109/) (2022)
- [Transformer with Peak Suppression and Knowledge Guidance for Fine-grained Image Recognition](https://mlsanity.com/paper/2107.06538/) (2021)
- [Improving Fine-Grained Visual Recognition in Low Data Regimes via Self-Boosting Attention Mechanism](https://mlsanity.com/paper/2208.00617/) (2022)
- [A Novel Plug-in Module for Fine-Grained Visual Classification](https://mlsanity.com/paper/2202.03822/) (2022)
- [Morph Detection Enhanced by Structured Group Sparsity](https://mlsanity.com/paper/2111.14943/) (2021)
- [Learning with Noisy labels via Self-supervised Adversarial Noisy Masking](https://mlsanity.com/paper/2302.06805/) (2023)
- [Detection of Deepfake Videos Using Long Distance Attention](https://mlsanity.com/paper/2106.12832/) (2021)
- [Fine-Grained Visual Classification using Self Assessment Classifier](https://mlsanity.com/paper/2205.10529/) (2022)
- [Exploring Vision Transformers for Fine-grained Classification](https://mlsanity.com/paper/2106.10587/) (2021)
- [Fine-Grained Few Shot Learning with Foreground Object Transformation](https://mlsanity.com/paper/2109.05719/) (2021)
- [Trusted Media Challenge Dataset and User Study](https://mlsanity.com/paper/2201.04788/) (2022)
- [DFGC 2022: The Second DeepFake Game Competition](https://mlsanity.com/paper/2206.15138/) (2022)
- [One Class One Click: Quasi Scene-level Weakly Supervised Point Cloud Semantic Segmentation with Active Learning](https://mlsanity.com/paper/2211.12657/) (2022)
- [Fair Comparison: Quantifying Variance in Resultsfor Fine-grained Visual Categorization](https://mlsanity.com/paper/2109.03156/) (2021)
- [Fine-Grained Adversarial Semi-supervised Learning](https://mlsanity.com/paper/2110.05848/) (2021)
- [TDAM: Top-Down Attention Module for Contextually Guided Feature Selection in CNNs](https://mlsanity.com/paper/2111.13470/) (2021)
- [Learn More for Food Recognition via Progressive Self-Distillation](https://mlsanity.com/paper/2303.05073/) (2023)
- [Global-Local Similarity for Efficient Fine-Grained Image Recognition with Vision Transformers](https://mlsanity.com/paper/2407.12891/) (2024)

## Abstract (arXiv)

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.