Rotate to Attend: Convolutional Triplet Attention Module
Diganta Misra,Trikay Nalamada,Ajay Uppili Arasanipalai,Qibin Hou +3 more
- pp 3138-3147
Reads0
Chats0
TLDR
Triplet Attention as discussed by the authors proposes triplet attention, a novel method for computing attention weights by capturing cross-dimension interaction using a three-branch structure, which can be easily plugged into classic backbone networks as an add-on module.Abstract:
Benefiting from the capability of building interdependencies among channels or spatial locations, attention mechanisms have been extensively studied and broadly used in a variety of computer vision tasks recently. In this paper, we investigate light-weight but effective attention mechanisms and present triplet attention, a novel method for computing attention weights by capturing crossdimension interaction using a three-branch structure. For an input tensor, triplet attention builds inter-dimensional dependencies by the rotation operation followed by residual transformations and encodes inter-channel and spatial information with negligible computational overhead. Our method is simple as well as efficient and can be easily plugged into classic backbone networks as an add-on module. We demonstrate the effectiveness of our method on various challenging tasks including image classification on ImageNet-1k and object detection on MSCOCO and PASCAL VOC datasets. Furthermore, we provide extensive insight into the performance of triplet attention by visually inspecting the GradCAM and GradCAM++ results. The empirical evaluation of our method supports our intuition on the importance of capturing dependencies across dimensions when computing attention weights. Code for this paper can be publicly accessed at https://github.com/LandskapeAI/triplet-attention.read more
Citations
More filters
Proceedings ArticleDOI
Coordinate Attention for Efficient Mobile Network Design
TL;DR: CoordAttention as mentioned in this paper embeds positional information into channel attention to capture long-range dependencies along one spatial direction and meanwhile precise positional information can be preserved along the other spatial direction.
Journal ArticleDOI
Attention mechanisms in computer vision: A survey
TL;DR: Guo et al. as mentioned in this paper provide a comprehensive review of various attention mechanisms in computer vision and categorize them according to approach, such as channel attention, spatial attention, temporal attention, and branch attention.
Posted Content
Attention Mechanisms in Computer Vision: A Survey.
Meng-Hao Guo,Tian-Xing Xu,Jiangjiang Liu,Zheng-Ning Liu,Peng-Tao Jiang,Tai-Jiang Mu,Song-Hai Zhang,Ralph R. Martin,Ming-Ming Cheng,Shi-Min Hu +9 more
TL;DR: A comprehensive review of attention mechanisms in computer vision can be found in this article, which categorizes them according to approach, such as channel attention, spatial attention, temporal attention and branch attention.
Proceedings ArticleDOI
NTIRE 2021 Challenge on Image Deblurring
Seungjun Nah,Sanghyun Son,Suyoung Lee,Radu Timofte,Kyoung Mu Lee,Liangyu Chen,Jie Zhang,Xin Lu,Xiaojie Chu,Chengpeng Chen,Zhiwei Xiong,Ruikang Xu,Zeyu Xiao,Jie Huang,Yueyi Zhang,Si Xi,Jia Wei,Haoran Bai,Songsheng Cheng,Hao Wei,Long Sun,Jinhui Tang,Jinshan Pan,Donghyeon Lee,Chulhee Lee,Taesung Kim,Xiaobing Wang,Dafeng Zhang,Zhihong Pan,Tianwei Lin,Wenhao Wu,Dongliang He,Baopu Li,Boyun Li,Teng Xi,Gang Zhang,Jingtuo Liu,Junyu Han,Errui Ding,Guangpin Tao,Wenqing Chu,Yun Cao,Donghao Luo,Ying Tai,Tong Lu,Chengjie Wang,Jilin Li,Feiyue Huang,Hanting Chen,Shuaijun Chen,Tianyu Guo,Yunhe Wang,Syed Waqas Zamir,Aditya Arora,Salman Khan,Munawar Hayat,Fahad Shahbaz Khan,Ling Shao,Yushen Zuo,Yimin Ou,Yuanjun Chai,Lei Shi,Shuai Liu,Lei Lei,Chaoyu Feng,Kai Zeng,Yuying Yao,Xinran Liu,Zhizhou Zhang,Huacheng Huang,Yunchen Zhang,Mingchao Jiang,Wenbin Zou,Si Miao,Yangwoo Kim,Yuejin Sun,Senyou Deng,Wenqi Ren,Xiaochun Cao,Tao Wang,Maitreya Suin,A.N. Rajagopalan,Vinh Van Duong,Thuc Huu Nguyen,Jonghoon Yim,Byeungwoo Jeon,Ru Li,Junwei Xie,Jong-Wook Han,Jun-Ho Choi,Jun-Hyuk Kim,Jong-Seok Lee,Jiaxin Zhang,Fan Peng,David Svitov,Dmitry Pakulich,Jaeyeob Kim,Jechang Jeong +97 more
TL;DR: The NTIRE 2021 Challenge on Image Deblurring as mentioned in this paper focused on image deblurring, where both the tracks aim to recover a high-quality clean image from a blurry image, different artifacts are jointly involved.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Proceedings ArticleDOI
ImageNet: A large-scale hierarchical image database
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
Proceedings ArticleDOI
Going deeper with convolutions
Christian Szegedy,Wei Liu,Yangqing Jia,Pierre Sermanet,Scott Reed,Dragomir Anguelov,Dumitru Erhan,Vincent Vanhoucke,Andrew Rabinovich +8 more
TL;DR: Inception as mentioned in this paper is a deep convolutional neural network architecture that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14).
Book ChapterDOI
Microsoft COCO: Common Objects in Context
Tsung-Yi Lin,Michael Maire,Serge Belongie,James Hays,Pietro Perona,Deva Ramanan,Piotr Dollár,C. Lawrence Zitnick +7 more
TL;DR: A new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of scene understanding by gathering images of complex everyday scenes containing common objects in their natural context.