Attention Branch Network: Learning of Attention Mechanism for Visual Explanation
By Hiroshi Fukui, Tsubasa Hirakawa, Takayoshi Yamashita, Hironobu Fujiyoshi. Computer Vision and Pattern Recognition, 2018
462 citations recorded by the source corpus.
Visual explanation enables humans to understand the decision making of deep convolutional neural network (CNN), but it is insufficient to contribute to improving CNN performance. In this paper, we focus on the attention map for visual explanation, which represents a high response value as the attention location in image recognition. This attention region significantly improves the performance of CNN by introducing an attention mechanism that focuses on a specific region in an image. In this work, we propose Attention Branch Network (ABN), which extends a response-based visual explanation model by introducing a branch structure with an attention mechanism. ABN can be applicable to several image recognition tasks by introducing a branch for the attention mechanism and is trainable for visual explanation and image recognition in an end-to-end manner. We evaluate ABN on several image recognition tasks such as image classification, fine-grained recognition, and multiple facial attribute recognition. Experimental results indicate that ABN outperforms the baseline models on these image recognition tasks while generating an attention map for visual explanation. Our code is available.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/e8874d7d585ae1c355e186efdcc9f704b3d43b49
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
- Lawrence Carin
- Ricardo Henao
- Yaozong Gao
- Masahiro Mitsuhara
- Tsubasa Hirakawa
- Fanjie Kong
- Fei Wu
- Dinggang Shen
In Computer Vision and Pattern Recognition
- Lawrence Carin
- Ricardo Henao
- Yaozong Gao
- Dinggang Shen
- Qian Wang
- Masahiro Mitsuhara
- Tsubasa Hirakawa
- Fanjie Kong
Citations in the corpus
- Global Attention Mechanism: Retain Information to Enhance Channel-Spatial Interactions (2021, methodology): “We compare GAM against SE, BAM, CBAM, TAM, and Attention Branch Network (ABN) (Fukui et al. [2019]).”
- Rotate to Attend: Convolutional Triplet Attention Module (2020, unknown): “35 ABN [9] 43.”
- FcaNet: Frequency Channel Attention Networks (2020, methodology): “Besides these works, many methods try to extend the attention mechanism to specific tasks, like multi-label clas-sification [14], saliency detection [44], visual explanation [10], and super-resolution [43].”
- Proactive Pseudo-Intervention: Causally Informed Contrastive Learning For Interpretable Vision Models (2020, background): “In [19] an additional attention branch is learned to generate attention map, and then applies the attention map to the original image or feature map; they achieve compelling attention maps on nat-ural images.”
- Dual-Sampling Attention Network for Diagnosis of COVID-19 From Community Acquired Pneumonia (2020, background): “The key idea of CAM [28], [29], [56] is to back-propagate weights of the fullyconnected layer onto the convolutional feature maps for generating the attention maps.”
- Embedding Human Knowledge into Deep Neural Network via Attention Map (2019, methodology): “To address this issue, ABN has been proposed (Fukui et al., 2019), which extends an attention map for the visual explanation to an attention mechanism.”