# Mask-CNN: Localizing Parts and Selecting Descriptors for Fine-Grained Image Recognition

arXiv: https://arxiv.org/abs/1605.06878 · HTML: https://mlsanity.com/paper/1605.06878/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 May 2016.

## Built on by (most cited first, 10 of 10)

- [TransFG: A Transformer Architecture for Fine-grained Recognition](https://mlsanity.com/paper/2103.07976/) (2021)
- [RAMS-Trans: Recurrent Attention Multi-scale Transformer forFine-grained Image Recognition](https://mlsanity.com/paper/2107.08192/) (2021)
- [A free lunch from ViT:Adaptive Attention Multi-scale Fusion Transformer for Fine-grained Visual Recognition](https://mlsanity.com/paper/2110.01240/) (2021)
- [Learning Part Knowledge to Facilitate Category Understanding for Fine-Grained Generalized Category Discovery](https://mlsanity.com/paper/2503.16782/) (2025)
- [Cross-layer Attention Network for Fine-grained Visual Categorization](https://mlsanity.com/paper/2210.08784/) (2022)
- [TaxonRL: Reinforcement Learning with Intermediate Rewards for Interpretable Fine-Grained Visual Reasoning](https://mlsanity.com/paper/2603.04380/) (2026)
- [Exploiting Spline Models for the Training of Fully Connected Layers in Neural Network](https://mlsanity.com/paper/2102.06554/) (2021)
- [Progressive Multi-stage Interactive Training in Mobile Network for Fine-grained Recognition](https://mlsanity.com/paper/2112.04223/) (2021)
- [Discriminative Feature Learning through Feature Distance Loss](https://mlsanity.com/paper/2205.11606/) (2022)
- [Semantic Feature Integration network for Fine-grained Visual Classification](https://mlsanity.com/paper/2302.10275/) (2023)

## Abstract (arXiv)

Fine-grained image recognition is a challenging computer vision problem, due to the small inter-class variations caused by highly similar subordinate categories, and the large intra-class variations in poses, scales and rotations. In this paper, we propose a novel end-to-end Mask-CNN model without the fully connected layers for fine-grained recognition. Based on the part annotations of fine-grained images, the proposed model consists of a fully convolutional network to both locate the discriminative parts (e.g., head and torso), and more importantly generate object/part masks for selecting useful and meaningful convolutional descriptors. After that, a four-stream Mask-CNN model is built for aggregating the selected object- and part-level descriptors simultaneously. The proposed Mask-CNN model has the smallest number of parameters, lowest feature dimensionality and highest recognition accuracy when compared with state-of-the-arts fine-grained approaches.