no code implementations • 9 Apr 2024 • Pin-Hung Kuo, Jinshan Pan, Shao-Yi Chien, Ming-Hsuan Yang
By elaborate adjustment of the tensor shapes and dimensions for the dot product, we split the typical self-attention of quadratic complexity into four operations of linear complexity.
1 code implementation • 23 Dec 2021 • Chih-Ting Liu, Chien-Yi Wang, Shao-Yi Chien, Shang-Hong Lai
Current state-of-the-art deep learning based face recognition (FR) models require a large number of face identities for central training.
1 code implementation • 27 Nov 2021 • Pin-Hung Kuo, Jinshan Pan, Shao-Yi Chien, Ming-Hsuan Yang
Most existing methods usually formulate the non-blind deconvolution problem into a maximum-a-posteriori framework and address it by manually designing kinds of regularization terms and data terms of the latent clear images.
no code implementations • 29 Sep 2021 • Tsai-Shien Chen, Chih-Ting Liu, Shao-Yi Chien
Fine-grained recognition aims to discriminate the sub-categories of the images within one general category.
no code implementations • 19 Jun 2021 • Chun-Tse Lin, Wei-Chih Tu, Chih-Ting Liu, Shao-Yi Chien
In the interactive segmentation, users initially click on the target object to segment the main body and then provide corrections on mislabeled regions to iteratively refine the segmentation masks.
no code implementations • 14 Jun 2021 • Chih-Ting Liu, Man-Yu Lee, Tsai-Shien Chen, Shao-Yi Chien
Person re-identification (re-ID) has received great success with the supervised learning methods.
no code implementations • ICLR 2022 • Tsai-Shien Chen, Wei-Chih Hung, Hung-Yu Tseng, Shao-Yi Chien, Ming-Hsuan Yang
Self-supervised learning has recently shown great potential in vision tasks through contrastive learning, which aims to discriminate each image, or instance, in the dataset.
1 code implementation • 22 May 2021 • Chih-Ting Liu, Jun-Cheng Chen, Chu-Song Chen, Shao-Yi Chien
Besides, we discover the errors not only for the identity labels of tracklets but also for the evaluation protocol for the test data of MARS.
no code implementations • ICCV 2021 • Jan P. Klopp, Keng-Chi Liu, Shao-Yi Chien, Liang-Gee Chen
This hybrid solution has a small scope of only 10s or 100s of frames and allows for a low complexity both on the encoding and the decoding side.
no code implementations • CVPR 2021 • Jan P. Klopp, Keng-Chi Liu, Liang-Gee Chen, Shao-Yi Chien
Recent research suggests that generative adversarial networks have the ability to overcome this limitation and serve as a multi-modal loss, especially for textures.
no code implementations • 12 Oct 2020 • Tsai-Shien Chen, Man-Yu Lee, Chih-Ting Liu, Shao-Yi Chien
Our VCAM enables the feature learning framework channel-wisely reweighing the importance of each feature maps according to the "viewpoint" of input vehicle.
no code implementations • 5 Oct 2020 • Po-Hsiang Yu, Sih-Sian Wu, Jan P. Klopp, Liang-Gee Chen, Shao-Yi Chien
We investigate pruning and quantization for deep neural networks.
no code implementations • 2 Oct 2020 • Chih-Ting Liu, Yu-Jhe Li, Shao-Yi Chien, Yu-Chiang Frank Wang
As a result, our approach is able to augment the labeled training data in the semi-supervised setting.
no code implementations • 18 Sep 2020 • Yu-Sheng Lin, Hung Chang Lu, Yang-Bin Tsao, Yi-Min Chih, Wei-Chao Chen, Shao-Yi Chien
We propose GrateTile, an efficient, hardwarefriendly data storage scheme for sparse CNN feature maps (activations).
1 code implementation • ECCV 2020 • Tsai-Shien Chen, Chih-Ting Liu, Chih-Wei Wu, Shao-Yi Chien
Vehicle re-identification (re-ID) focuses on matching images of the same vehicle across different cameras.
no code implementations • 19 Oct 2019 • Jan P. Klopp, Liang-Gee Chen, Shao-Yi Chien
The method can be applied to any existing video codec to increase coding gains while its low computational footprint allows for an application under resource-constrained conditions.
1 code implementation • 5 Aug 2019 • Chih-Ting Liu, Chih-Wei Wu, Yu-Chiang Frank Wang, Shao-Yi Chien
Video-based person re-identification (Re-ID) aims at matching video sequences of pedestrians across non-overlapping cameras.
Ranked #11 on Person Re-Identification on MARS
no code implementations • 31 May 2019 • Jyun-Yi Wu, Cheng Yu, Szu-Wei Fu, Chih-Ting Liu, Shao-Yi Chien, Yu Tsao
In addition, a parameter quantization (PQ) technique was applied to reduce the size of a neural network by representing weights with fewer cluster centroids.
no code implementations • CVPR 2018 • Wei-Chih Tu, Ming-Yu Liu, Varun Jampani, Deqing Sun, Shao-Yi Chien, Ming-Hsuan Yang, Jan Kautz
Specifically, we propose a new loss function that takes the segmentation error into account for affinity learning.
no code implementations • ICCV 2017 • Yu-Sheng Lin, Wei-Chao Chen, Shao-Yi Chien
Recently, convolutional neural networks (CNNs) have achieved great success in fields such as computer vision, natural language processing, and artificial intelligence.
2 code implementations • 30 May 2017 • Chih-Ting Liu, Yi-Heng Wu, Yu-Sheng Lin, Shao-Yi Chien
Deep Convolutional Neural Networks (CNNs) are widely employed in modern computer vision algorithms, where the input image is convolved iteratively by many kernels to extract the knowledge behind it.
1 code implementation • 1 Feb 2017 • Yi-Ling Chen, Jan Klopp, Min Sun, Shao-Yi Chien, Kwan-Liu Ma
Photo composition is an important factor affecting the aesthetics in photography.
1 code implementation • CVPR 2016 • Wei-Chih Tu, Shengfeng He, Qingxiong Yang, Shao-Yi Chien
In this paper, we present a real-time salient object detection system based on the minimum spanning tree.
Ranked #5 on Video Salient Object Detection on MCL (using extra training data)