35 citations · 118 across the 20 of their papers we have counts for
20 papers
FedFR: Joint Optimization Federated Framework for Generic and Personalized Face Recognition
Chih-Ting Liu, Chien-Yi Wang, Shao-Yi Chien +1
Current state-of-the-art deep learning based face recognition (FR) models require a large number of face identities for central training. However, due to the growing privacy awaren…
A Dense Tensor Accelerator with Data Exchange Mesh for DNN and Vision Workloads
Yu-Sheng Lin, Wei-Chao Chen. Chia-Lin Yang, Shao-Yi Chien
We propose a dense tensor accelerator called VectorMesh, a scalable, memory-efficient architecture that can support a wide variety of DNN and computer vision workloads. Its buildin…
Learning Discriminative Shrinkage Deep Networks for Image Deconvolution
Pin-Hung Kuo, Jinshan Pan, Shao-Yi Chien +1
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…
Interactive Object Segmentation with Dynamic Click Transform
Chun-Tse Lin, Wei-Chih Tu, Chih-Ting Liu +1
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 se…
Hard Samples Rectification for Unsupervised Cross-domain Person Re-identification
Chih-Ting Liu, Man-Yu Lee, Tsai-Shien Chen +1
Person re-identification (re-ID) has received great success with the supervised learning methods. However, the task of unsupervised cross-domain re-ID is still challenging. In this…
Incremental False Negative Detection for Contrastive Learning
Tsai-Shien Chen, Wei-Chih Hung, Hung-Yu Tseng +2
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. Howeve…
Video-based Person Re-identification without Bells and Whistles
Chih-Ting Liu, Jun-Cheng Chen, Chu-Song Chen +1
Video-based person re-identification (Re-ID) aims at matching the video tracklets with cropped video frames for identifying the pedestrians under different cameras. However, there…
How to Exploit the Transferability of Learned Image Compression to Conventional Codecs
Jan P. Klopp, Keng-Chi Liu, Liang-Gee Chen +1
Lossy image compression is often limited by the simplicity of the chosen loss measure. Recent research suggests that generative adversarial networks have the ability to overcome th…
Viewpoint-Aware Channel-Wise Attentive Network for Vehicle Re-Identification
Tsai-Shien Chen, Man-Yu Lee, Chih-Ting Liu +1
Vehicle re-identification (re-ID) matches images of the same vehicle across different cameras. It is fundamentally challenging because the dramatically different appearance caused…
Joint Pruning & Quantization for Extremely Sparse Neural Networks
Po-Hsiang Yu, Sih-Sian Wu, Jan P. Klopp +2
We investigate pruning and quantization for deep neural networks. Our goal is to achieve extremely high sparsity for quantized networks to enable implementation on low cost and low…
Semantics-Guided Clustering with Deep Progressive Learning for Semi-Supervised Person Re-identification
Chih-Ting Liu, Yu-Jhe Li, Shao-Yi Chien +1
Person re-identification (re-ID) requires one to match images of the same person across camera views. As a more challenging task, semi-supervised re-ID tackles the problem that onl…
GrateTile: Efficient Sparse Tensor Tiling for CNN Processing
Yu-Sheng Lin, Hung Chang Lu, Yang-Bin Tsao +3
We propose GrateTile, an efficient, hardwarefriendly data storage scheme for sparse CNN feature maps (activations). It divides data into uneven-sized subtensors and, with small ind…
Orientation-aware Vehicle Re-identification with Semantics-guided Part Attention Network
Tsai-Shien Chen, Chih-Ting Liu, Chih-Wei Wu +1
Vehicle re-identification (re-ID) focuses on matching images of the same vehicle across different cameras. It is fundamentally challenging because differences between vehicles are…
MERIT: Tensor Transform for Memory-Efficient Vision Processing on Parallel Architectures
Yu-Sheng Lin, Wei-Chao Chen, Shao-Yi Chien
Computationally intensive deep neural networks (DNNs) are well-suited to run on GPUs, but newly developed algorithms usually require the heavily optimized DNN routines to work effi…
Utilising Low Complexity CNNs to Lift Non-Local Redundancies in Video Coding
Jan P. Klopp, Liang-Gee Chen, Shao-Yi Chien
Digital media is ubiquitous and produced in ever-growing quantities. This necessitates a constant evolution of compression techniques, especially for video, in order to maintain ef…
Spatially and Temporally Efficient Non-local Attention Network for Video-based Person Re-Identification
Chih-Ting Liu, Chih-Wei Wu, Yu-Chiang Frank Wang +1
Video-based person re-identification (Re-ID) aims at matching video sequences of pedestrians across non-overlapping cameras. It is a practical yet challenging task of how to embed…
Increasing Compactness Of Deep Learning Based Speech Enhancement Models With Parameter Pruning And Quantization Techniques
Jyun-Yi Wu, Cheng Yu, Szu-Wei Fu +3
Most recent studies on deep learning based speech enhancement (SE) focused on improving denoising performance. However, successful SE applications require striking a desirable bala…
Speech Dereverberation Based on Integrated Deep and Ensemble Learning Algorithm
Wei-Jen Lee, Syu-Siang Wang, Fei Chen +3
Reverberation, which is generally caused by sound reflections from walls, ceilings, and floors, can result in severe performance degradation of acoustic applications. Due to a comp…
Computation-Performance Optimization of Convolutional Neural Networks with Redundant Kernel Removal
Chih-Ting Liu, Yi-Heng Wu, Yu-Sheng Lin +1
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 kn…
Learning to Compose with Professional Photographs on the Web
Yi-Ling Chen, Jan Klopp, Min Sun +2
Photo composition is an important factor affecting the aesthetics in photography. However, it is a highly challenging task to model the aesthetic properties of good compositions du…