The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification

By Dongliang Chang, Jiyang Xie, Ayan Kumar Bhunia, Xiaoxu Li, Zhanyu Ma, Ming Wu, Jun Guo, Yi-Zhe Song. IEEE Transactions on Image Processing, 2020

371 citations recorded by the source corpus.

The key to solving fine-grained image categorization is finding discriminate and local regions that correspond to subtle visual traits. Great strides have been made, with complex networks designed specifically to learn part-level discriminate feature representations. In this paper, we show that it is possible to cultivate subtle details without the need for overly complicated network designs or training mechanisms – a single loss is all it takes. The main trick lies with how we delve into individual feature channels early on, as opposed to the convention of starting from a consolidated feature map. The proposed loss function, termed as mutual-channel loss (MC-Loss), consists of two channel-specific components: a discriminality component and a diversity component. The discriminality component forces all feature channels belonging to the same class to be discriminative, through a novel channel-wise attention mechanism. The diversity component additionally constraints channels so that they become mutually exclusive across the spatial dimension. The end result is therefore a set of feature channels, each of which reflects different locally discriminative regions for a specific class. The MC-Loss can be trained end-to-end, without the need for any bounding-box/part annotations, and yields highly discriminative regions during inference. Experimental results show our MC-Loss when implemented on top of common base networks can achieve state-of-the-art performance on all four fine-grained categorization datasets (CUB-Birds, FGVC-Aircraft, Flowers-102, and Stanford Cars). Ablative studies further demonstrate the superiority of the MC-Loss when compared with other recently proposed general-purpose losses for visual classification, on two different base networks. Codes are available at: https://github.com/dongliangchang/Mutual-Channel-Loss.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/3f07093e303a8a9ddc157c2fceb47802bb9b5613

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Cheng Deng
2. Kun-Juan Wei
3. Xiu-Shen Wei
4. Jian Yang
5. Jianxin Wu
6. Jinhui Tang
7. Yi-Zhe Song
8. Xu Yang

In Computer Vision and Pattern Recognition

1. Dacheng Tao
2. Luc Van Gool
3. Yuxin Peng
4. Yi Yang
5. Jian Yang
6. Jinhui Tang
7. Ming-Hsuan Yang
8. Chunhua Shen

Citations in the corpus

• Lifelong Zero-Shot Learning (2020, background): “In recent years, Zero-Shot Learning (ZSL) [Socher et al. , 2013; Xian et al. , 2018a; Zhao et al. , 2019; Wei et al. , 2019; Xu et al. , 2019] has gained increasing attention in computer vision [Chang et al. , 2020] and machine learning communities [Yang et al. , 2019].”
• Fine-Grained Image Analysis With Deep Learning: A Survey (2021, background): “MC-Loss [112] encourages the feature channels to be”
• Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches (2020, neutral): “4 MC-Loss (TIP20) [3] ResNet50 87.”