# Mask-Guided Feature Extraction and Augmentation for Ultra-Fine-Grained Visual Categorization

arXiv: https://arxiv.org/abs/2109.07755 · HTML: https://mlsanity.com/paper/2109.07755/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 40 references that are in the map.
- First posted on arXiv 16 Sep 2021.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [One weird trick for parallelizing convolutional neural networks](https://mlsanity.com/paper/1404.5997/) (2014)
- [Towards Fairer Datasets: Filtering and Balancing the Distribution of the People Subtree in the ImageNet Hierarchy](https://mlsanity.com/paper/1912.07726/) (2019)
- [Learning to Navigate for Fine-grained Classification](https://mlsanity.com/paper/1809.00287/) (2018)
- [Towards Faster Training of Global Covariance Pooling Networks by Iterative Matrix Square Root Normalization](https://mlsanity.com/paper/1712.01034/) (2017)
- [Multi-Attention Multi-Class Constraint for Fine-grained Image Recognition](https://mlsanity.com/paper/1806.05372/) (2018)
- [Object-Part Attention Model for Fine-grained Image Classification](https://mlsanity.com/paper/1704.01740/) (2017)
- [Improved Bilinear Pooling with CNNs](https://mlsanity.com/paper/1707.06772/) (2017)
- [Patchy Image Structure Classification Using Multi-Orientation Region Transform](https://mlsanity.com/paper/1912.00622/) (2019)
- [Mask Guided Attention For Fine-Grained Patchy Image Classification](https://mlsanity.com/paper/2102.02771/) (2021)
- [MobileFAN: Transferring Deep Hidden Representation for Face Alignment](https://mlsanity.com/paper/1908.03839/) (2019)
- [Self-Supervised Learning for Fine-Grained Visual Categorization](https://mlsanity.com/paper/2105.08788/) (2021)

## Abstract (arXiv)

While the fine-grained visual categorization (FGVC) problems have been greatly developed in the past years, the Ultra-fine-grained visual categorization (Ultra-FGVC) problems have been understudied. FGVC aims at classifying objects from the same species (very similar categories), while the Ultra-FGVC targets at more challenging problems of classifying images at an ultra-fine granularity where even human experts may fail to identify the visual difference. The challenges for Ultra-FGVC mainly comes from two aspects: one is that the Ultra-FGVC often arises overfitting problems due to the lack of training samples; and another lies in that the inter-class variance among images is much smaller than normal FGVC tasks, which makes it difficult to learn discriminative features for each class. To solve these challenges, a mask-guided feature extraction and feature augmentation method is proposed in this paper to extract discriminative and informative regions of images which are then used to augment the original feature map. The advantage of the proposed method is that the feature detection and extraction model only requires a small amount of target region samples with bounding boxes for training, then it can automatically locate the target area for a large number of images in the dataset at a high detection accuracy. Experimental results on two public datasets and ten state-of-the-art benchmark methods consistently demonstrate the effectiveness of the proposed method both visually and quantitatively.