no code implementations • 29 Apr 2021 • Tse-Wei Chen, Deyu Wang, Wei Tao, Dongchao Wen, Lingxiao Yin, Tadayuki Ito, Kinya Osa, Masami Kato
In this paper, we propose a network module, Cascaded and Separable Structure of Dilated (CASSOD) Convolution, and a special hardware system to handle the CASSOD networks efficiently.
Ranked #1 on Face Detection on ADE20K
no code implementations • 29 Apr 2021 • Tse-Wei Chen, Wei Tao, Deyu Wang, Dongchao Wen, Kinya Osa, Masami Kato
In order to handle modern convolutional neural networks (CNNs) efficiently, a hardware architecture of CNN inference accelerator is proposed to handle depthwise convolutions and regular convolutions, which are both essential building blocks for embedded-computer-vision algorithms.
Ranked #1 on Face Detection on WIDER FACE
no code implementations • 29 Apr 2021 • Tse-Wei Chen, Motoki Yoshinaga, Hongxing Gao, Wei Tao, Dongchao Wen, Junjie Liu, Kinya Osa, Masami Kato
"Lightweight convolutional neural networks" is an important research topic in the field of embedded vision.
Ranked #1 on Face Detection on FDDB (Accuracy metric)
no code implementations • 29 Sep 2020 • Junjie Liu, Dongchao Wen, Deyu Wang, Wei Tao, Tse-Wei Chen, Kinya Osa, Masami Kato
In this paper, we provide an explicit convex optimization example where training the BNNs with the traditionally adaptive optimization methods still faces the risk of non-convergence, and identify that constraining the range of gradients is critical for optimizing the deep binary model to avoid highly suboptimal solutions.
no code implementations • 10 Sep 2020 • Junjie Liu, Dongchao Wen, Deyu Wang, Wei Tao, Tse-Wei Chen, Kinya Osa, Masami Kato
Despite the achievements of recent binarization methods on reducing the performance degradation of Binary Neural Networks (BNNs), gradient mismatching caused by the Straight-Through-Estimator (STE) still dominates quantized networks.
Ranked #949 on Image Classification on ImageNet
no code implementations • 19 Nov 2019 • Hongxing Gao, Wei Tao, Dongchao Wen, Tse-Wei Chen, Kinya Osa, Masami Kato
Furthermore, based on YOLOv2, we design IFQ-Tinier-YOLO face detector which is a fixed-point network with 256x reduction in model size (246k Bytes) than Tiny-YOLO.
Ranked #10 on Face Detection on FDDB
no code implementations • 13 Nov 2019 • Hongxing Gao, Wei Tao, Dongchao Wen, Junjie Liu, Tse-Wei Chen, Kinya Osa, Masami Kato
Firstly, we employ weights with duplicated channels for the weight-intensive layers to reduce the model size.
Ranked #1 on Face Detection on WIDER Face (GFLOPs metric)
no code implementations • 13 Nov 2019 • Junjie Liu, Dongchao Wen, Hongxing Gao, Wei Tao, Tse-Wei Chen, Kinya Osa, Masami Kato
Despite the recent works on knowledge distillation (KD) have achieved a further improvement through elaborately modeling the decision boundary as the posterior knowledge, their performance is still dependent on the hypothesis that the target network has a powerful capacity (representation ability).
Ranked #191 on Image Classification on CIFAR-10 (using extra training data)