Learning Multi-attention Convolutional Neural Network for Fine-Grained Image Recognition

Zheng, Haizhong; Fu, Jianlong; Mei, Tao; Luo, Jiebo

doi:10.1109/iccv.2017.557

Cited by 801 publications

(551 citation statements)

References 22 publications

Supporting

Mentioning

548

Contrasting

Unclassified

Order By: Relevance

“…where L data is the classification loss, γ and λ are hyperparameters that balance the contribution of different costs. Our model can be trained end-to-end using stochastic gradient descent (SGD) and does not require other optimization tricks such as multiple crops [37], data augmentation [3], model ensemble [42], and separate initialization [32] Table 1. The statistics of fine-grained datasets in this paper Caltech-UCSD Birds (CUB-Birds) [30], Stanford Cars [16], Stanford Dogs [14] and FGVC-Aircraft [25].…”

Section: Optimizationmentioning

confidence: 99%

See 1 more Smart Citation

Cross-X Learning for Fine-Grained Visual Categorization

Luo

Yang

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

164

View full text Add to dashboard Cite

Recognizing objects from subcategories with very subtle differences remains a challenging task due to the large intra-class and small inter-class variation. Recent work tackles this problem in a weakly-supervised manner: object parts are first detected and the corresponding part-specific features are extracted for fine-grained classification. However, these methods typically treat the part-specific features of each image in isolation while neglecting their relationships between different images. In this paper, we propose Cross-X learning, a simple yet effective approach that exploits the relationships between different images and between different network layers for robust multi-scale feature learning. Our approach involves two novel components: (i) a cross-category cross-semantic regularizer that guides the extracted features to represent semantic parts and, (ii) a cross-layer regularizer that improves the robustness of multi-scale features by matching the prediction distribution across multiple layers. Our approach can be easily trained end-to-end and is scalable to large datasets like NABirds. We empirically analyze the contributions of different components of our approach and demonstrate its robustness, effectiveness and state-of-the-art performance on five benchmark datasets. Code is available at https: //github.com/cswluo/CrossX.

show abstract

Section: Optimizationmentioning

confidence: 99%

“…• MA-CNN [42]: multi-attention convolutional neural network that generates multiple parts from spatiallycorrelated channels via multi-task learning.…”

Section: Optimizationmentioning

confidence: 99%

Cross-X Learning for Fine-Grained Visual Categorization

Luo

Yang

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

164

View full text Add to dashboard Cite

show abstract

“…In this paper, we follow the same motivation as above [38], [49], [50] to address the unique challenges of fine-grained classification. We importantly differ in that we do not attempt to introduce any explicit network components for discriminate part discovery.…”

Section: Introductionmentioning

confidence: 99%

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

Chang

Ding

Xie

et al. 2020

IEEE Trans. on Image Process.

262

View full text Add to dashboard Cite

Key for 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 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 on spatial-wise. The end result is therefore a set of feature channels that each 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 MC-Loss when compared with other recently proposed general-purpose losses for visual classification, on two different base networks. Code available at https://github.com/ dongliangchang/Mutual-Channel-Loss

show abstract

“…This task is very challenging as some fine-grained categories (e.g., eared grebe, and horned grebe) can only be recognized by domain experts. Different from general image tagging, fine-grained image tagging should be capable of localizing and representing the very marginal visual differences within subordinate categories [83,84]. Besides, tagging an image with "girl" or "woman" is not very existing, compared with tagging them with more personalized tags (e.g., "daughter") based on the contextual information from a user album and user-provided meta-data.…”

Section: D) Photo App On Ios 10mentioning

confidence: 99%