Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Official PyTorch Implementation for "Rotate to Attend: Convolutional Triplet Attention Module." [WACV 2021]
| Date | Stars |
|---|---|
| 2026-07-24 | 441 |
| 2026-07-25 | 442 |
| 2026-07-28 | 442 |
| 2026-07-30 | 442 |
| 2026-08-06 | 442 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<p float="center">
<img src ="figures/page-0.jpg" width="1000"/>
</p>
<p float="center">
<a href="https://openaccess.thecvf.com/content/WACV2021/html/Misra_Rotate_to_Attend_Convolutional_Triplet_Attention_Module_WACV_2021_paper.html" alt="CVF">
<img src="https://img.shields.io/badge/CVF-Page-purple.svg" /></a>
<a href="https://arxiv.org/abs/2010.03045" alt="ArXiv">
<img src="https://img.shields.io/badge/Preprint-arXiv-blue.svg" /></a>
<a href="https://openaccess.thecvf.com/content/WACV2021/papers/Misra_Rotate_to_Attend_Convolutional_Triplet_Attention_Module_WACV_2021_paper.pdf" alt="PDF">
<img src="https://img.shields.io/badge/WACV-PDF-neon.svg" /></a>
<a href="https://openaccess.thecvf.com/content/WACV2021/supplemental/Misra_Rotate_to_Attend_WACV_2021_supplemental.pdf" alt="Supp">
<img src="https://img.shields.io/badge/WACV-Supp-pink.svg" /></a>
<a href="https://landskapeai.github.io/publication/triplet/" alt="Project">
<img src="https://img.shields.io/badge/Project-Website-green.svg" /></a>
<a href="https://landskapeai.github.io/slides/triplet/#/" alt="Slides">
<img src="https://img.shields.io/badge/WACV-Slides-yellow.svg" /></a>
<a href="https://youtu.be/ZW9_2bNF1zo" alt="Video">
<img src="https://img.shields.io/badge/WACV-Video-maroon.svg" /></a>
</p>
*Abstract - Benefiting from the capability of building inter-dependencies 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 cross-dimension 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 in-sight 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.*
<p float="left">
<img src ="figures/triplet.png" width="1000"/>
</p>
<p>
<em>Figure 1. Structural Design of Triplet Attention Module. </em>
</p>
<p float="left">
<img src ="figures/comp.png" width="1000"/>
</p>
<p>
<em>Figure 2. (a). Squeeze Excitation Block. (b). Convolution Block Attention Module (CBAM) (Note - GMP denotes - Global Max Pooling). (c). Global Context (GC) block. (d). Triplet Attention (ours). </em>
</p>
<p float="left">
<img src ="figures/grad1.jpg" width="1000"/>
</p>
<p>
<em>Figure 3. GradCAM and GradCAM++ comparisons for ResNet-50 based on sample images from ImageNet dataset. </em>
</p>
*For generating GradCAM and GradCAM++ results, please follow the code on this [repository](https://github.com/1Konny/gradcam_plus_plus-pytorch).*
<details>
<summary>Changelogs/ Updates: (Click to expand)</summary>
* [05/11/20] v2 of our paper is out on [arXiv](https://arxiv.org/abs/2010.03045).
* [02/11/20] Our paper is accepted to [WACV 2021](http://wacv2021.thecvf.com/home).
* [06/10/20] Preprint of our paper is out on [arXiv](https://arxiv.org/abs/2010.03045v1).
</details>
## Pretrained Models:
### ImageNet:
|Model|Parameters|GFLOPs|Top-1 Error|Top-5 Error|Weights|
|:---:|:---:|:---:|:---:|:---:|:---:|
|ResNet-18 + Excerpt of 13,064 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:3b0164d4b8876a7a, topic:computer-vision, readme:computer vision, readme:object detection
matched fp:3b0164d4b8876a7a, topic:deep-learning