Y
Yurong Chen
Researcher at Intel
Publications - 128
Citations - 6642
Yurong Chen is an academic researcher from Intel. The author has contributed to research in topics: Convolutional neural network & Object detection. The author has an hindex of 32, co-authored 115 publications receiving 5207 citations.
Papers
More filters
Proceedings Article
Incremental Network Quantization: Towards Lossless CNNs with Low-precision Weights
TL;DR: Extensive experiments on the ImageNet classification task using almost all known deep CNN architectures including AlexNet, VGG-16, GoogleNet and ResNets well testify the efficacy of the proposed INQ, showing that at 5-bit quantization, models have improved accuracy than the 32-bit floating-point references.
Proceedings Article
Dynamic network surgery for efficient DNNs
Yiwen Guo,Anbang Yao,Yurong Chen +2 more
TL;DR: A novel network compression method called dynamic network surgery, which can remarkably reduce the network complexity by making on-the-fly connection pruning by proving that it outperforms the recent pruning method by considerable margins.
Proceedings ArticleDOI
HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection
TL;DR: HyperNet as discussed by the authors is based on an elaborately designed Hyper Feature which aggregates hierarchical feature maps first and then compresses them into a uniform space, thus enabling them to construct HyperNet by sharing them both in generating proposals and detecting objects via an end to end joint training strategy.
Posted Content
Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights
TL;DR: In Incremental Network Quantization (INQ) as discussed by the authors, the weights in each layer of a pre-trained CNN model are divided into two disjoint groups and quantized by a variable-length encoding method.
Proceedings ArticleDOI
DSOD: Learning Deeply Supervised Object Detectors from Scratch
TL;DR: Deeply Supervised Object Detector (DSOD), a framework that can learn object detectors from scratch following the single-shot detection (SSD) framework, and one of the key findings is that deep supervision, enabled by dense layer-wise connections, plays a critical role in learning a good detector.