Precise Facial Landmark Detection by Dynamic Semantic Aggregation Transformer

December 01, 2024 ยท Entered Twilight ยท ๐Ÿ› Pattern Recognition

๐Ÿ’ค TWILIGHT: Eternal Rest
Repo abandoned since publication

Repo contents: .gitignore, CTrans.py, Config.py, Improved_semhash.py, LICENSE, README.md, checkpoint, data, dataset.py, demo.py, hello.c, hello.cp36-win_amd64.pyd, hello.cp37-win_amd64.pyd, hello.cp38-win_amd64.pyd, hello.pyx, main.py, model.py, solver.py, transform.py, utils.py

Authors Jun Wan, He Liu, Yujia Wu, Zhihui Lai, Wenwen Min, Jun Liu arXiv ID 2412.00740 Category cs.CV: Computer Vision Citations 9 Venue Pattern Recognition Repository https://github.com/GERMINO-LiuHe/DSAT โญ 2 Last Checked 3 months ago
Abstract
At present, deep neural network methods have played a dominant role in face alignment field. However, they generally use predefined network structures to predict landmarks, which tends to learn general features and leads to mediocre performance, e.g., they perform well on neutral samples but struggle with faces exhibiting large poses or occlusions. Moreover, they cannot effectively deal with semantic gaps and ambiguities among features at different scales, which may hinder them from learning efficient features. To address the above issues, in this paper, we propose a Dynamic Semantic-Aggregation Transformer (DSAT) for more discriminative and representative feature (i.e., specialized feature) learning. Specifically, a Dynamic Semantic-Aware (DSA) model is first proposed to partition samples into subsets and activate the specific pathways for them by estimating the semantic correlations of feature channels, making it possible to learn specialized features from each subset. Then, a novel Dynamic Semantic Specialization (DSS) model is designed to mine the homogeneous information from features at different scales for eliminating the semantic gap and ambiguities and enhancing the representation ability. Finally, by integrating the DSA model and DSS model into our proposed DSAT in both dynamic architecture and dynamic parameter manners, more specialized features can be learned for achieving more precise face alignment. It is interesting to show that harder samples can be handled by activating more feature channels. Extensive experiments on popular face alignment datasets demonstrate that our proposed DSAT outperforms state-of-the-art models in the literature.Our code is available at https://github.com/GERMINO-LiuHe/DSAT.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Computer Vision

๐ŸŒ… ๐ŸŒ… Old Age

Fast R-CNN

Ross Girshick

cs.CV ๐Ÿ› ICCV ๐Ÿ“š 27.7K cites 11 years ago