-
ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual Recognition
Scale variance among different sizes of body parts and objects is a chal...
11/30/2020 ∙ by Hsin-Pai Cheng, et al. ∙
0
∙
share
read it
-
NASGEM: Neural Architecture Search via Graph Embedding Method
Neural Architecture Search (NAS) automates and prospers the design of ne...
07/08/2020 ∙ by Hsin-Pai Cheng, et al. ∙
0
∙
share
read it
-
Ordering Chaos: Memory-Aware Scheduling of Irregularly Wired Neural Networks for Edge Devices
Recent advances demonstrate that irregularly wired neural networks from ...
03/04/2020 ∙ by Byung Hoon Ahn, et al. ∙
12
∙
share
read it
-
AutoShrink: A Topology-aware NAS for Discovering Efficient Neural Architecture
Resource is an important constraint when deploying Deep Neural Networks ...
11/21/2019 ∙ by Tunhou Zhang, et al. ∙
0
∙
share
read it
-
Low-Power Computer Vision: Status, Challenges, Opportunities
Computer vision has achieved impressive progress in recent years. Meanwh...
04/15/2019 ∙ by Sergei Alyamkin, et al. ∙
16
∙
share
read it
-
Towards Leveraging the Information of Gradients in Optimization-based Adversarial Attack
In recent years, deep neural networks demonstrated state-of-the-art perf...
12/06/2018 ∙ by Jingyang Zhang, et al. ∙
0
∙
share
read it
-
LEASGD: an Efficient and Privacy-Preserving Decentralized Algorithm for Distributed Learning
Distributed learning systems have enabled training large-scale models ov...
11/27/2018 ∙ by Hsin-Pai Cheng, et al. ∙
0
∙
share
read it
-
Differentiable Fine-grained Quantization for Deep Neural Network Compression
Neural networks have shown great performance in cognitive tasks. When de...
10/20/2018 ∙ by Hsin-Pai Cheng, et al. ∙
0
∙
share
read it
-
2018 Low-Power Image Recognition Challenge
The Low-Power Image Recognition Challenge (LPIRC, https://rebootingcompu...
10/03/2018 ∙ by Sergei Alyamkin, et al. ∙
6
∙
share
read it
-
A Multi-strength Adversarial Training Method to Mitigate Adversarial Attacks
Some recent works revealed that deep neural networks (DNNs) are vulnerab...
05/27/2017 ∙ by Chang Song, et al. ∙
0
∙
share
read it
