Rotate to Attend: Convolutional Triplet Attention Module

By Diganta Misra, Trikay Nalamada, Ajay Uppili Arasanipalai, Qibin Hou. IEEE Workshop/Winter Conference on Applications of Computer Vision, 2020

989 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/33e738b6ca2a6e0c5020a3ea87c1ebd2a3c7497a

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Coordinate Attention for Efficient Mobile Network Design (2021, methodology): “Later works, like GENet [17], GALA [22], AA [1], and TA [28], extend this idea by adopting different spatial attention mechanisms or designing advanced attention blocks.”
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]).”
Distract Your Attention: Multi-Head Cross Attention Network for Facial Expression Recognition (2021, background): “[24] propose a new triplet attention that captures cross-dimensional interaction to efficiently build inter-dimensional dependencies.”
Omni-Dimensional Dynamic Convolution (2022, background): “Misra et al. (2021) presents an attention module having three branches conditioned on the features rotated along three different dimensions.”
Efficient Multi-Scale Attention Module with Cross-Spatial Learning (2023, background): “Different from the large depth attentions described as a linear sequence, Triplet attention (TA) [13] proposed a triplet parallel branches structure for capturing cross-dimension interaction against the different parallel branches.”
Review of Image Classification Algorithms Based on Convolutional Neural Networks (2021, background): “Not only the above BAM [138], CBAM [139], GENet [140], SKNet [141], ECA-Net [149] and CA [150], but also GALA [151], AA-Net [152] and TA [153] developed its ideas by adopting different spatial attention mechanisms or designing advanced attention blocks.”
SCSA: Exploring the Synergistic Effects Between Spatial and Channel Attention (2024, neutral): “Existing plug-and-play attention methods can be primarily categorized into three types: channel attention [23, 27, 62, 55, 31, 41], spatial attention [22, 56, 42, 9], and hybrid channel-spatial attention [57, 40, 38, 14, 20, 65, 39, 61].”
Attention mechanisms in computer vision: A survey (2021, background): “Attention mechanisms have become an indispensable technique in the field of computer vision in the era of deep learning.”