Z
Zhiqiang Shen
Researcher at Carnegie Mellon University
Publications - 86
Citations - 5234
Zhiqiang Shen is an academic researcher from Carnegie Mellon University. The author has contributed to research in topics: Computer science & Object detection. The author has an hindex of 21, co-authored 71 publications receiving 3216 citations. Previous affiliations of Zhiqiang Shen include University of Illinois at Urbana–Champaign & Hong Kong University of Science and Technology.
Papers
More filters
Proceedings ArticleDOI
Learning Efficient Convolutional Networks through Network Slimming
TL;DR: In this article, the authors proposed a network slimming method for CNNs to simultaneously reduce the model size, decrease the run-time memory footprint, and lower the number of computing operations without compromising accuracy.
Posted Content
Learning Efficient Convolutional Networks through Network Slimming
TL;DR: The approach is called network slimming, which takes wide and large networks as input models, but during training insignificant channels are automatically identified and pruned afterwards, yielding thin and compact models with comparable accuracy.
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.
Book ChapterDOI
ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functions
TL;DR: Li et al. as discussed by the authors proposed ReActNet, a baseline network by modifying and binarizing a compact real-valued network with parameter-free shortcuts, bypassing all the intermediate convolutional layers including the downsampling layers.
Proceedings ArticleDOI
Multiple Granularity Descriptors for Fine-Grained Categorization
TL;DR: This work leverages the fact that a subordinate-level object already has other labels in its ontology tree to train a series of CNN-based classifiers, each specialized at one grain level, which outperforms state-of-the-art algorithms, including those requiring strong labels.