Search Results for author:
Found 11 papers, 3 papers with code
ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual Recognition
We use ScaleNAS to create high-resolution models for two different tasks, ScaleNet-P for human pose estimation and ScaleNet-S for semantic segmentation.
Ranked #5 on
Multi-Person Pose Estimation
on COCO test-dev
NASGEM: Neural Architecture Search via Graph Embedding Method
To preserve graph correlation information in encoding, we propose NASGEM which stands for Neural Architecture Search via Graph Embedding Method.
Ordering Chaos: Memory-Aware Scheduling of Irregularly Wired Neural Networks for Edge Devices
To address this standing issue, we present a memory-aware compiler, dubbed SERENITY, that utilizes dynamic programming to find a sequence that finds a schedule with optimal memory footprint.
AutoShrink: A Topology-aware NAS for Discovering Efficient Neural Architecture
Specifically, both ShrinkCNN and ShrinkRNN are crafted within 1. 5 GPU hours, which is 7. 2x and 6. 7x faster than the crafting time of SOTA CNN and RNN models, respectively.
SwiftNet: Using Graph Propagation as Meta-knowledge to Search Highly Representative Neural Architectures
Designing neural architectures for edge devices is subject to constraints of accuracy, inference latency, and computational cost.
Low-Power Computer Vision: Status, Challenges, Opportunities
In addition to mobile phones, many autonomous systems rely on visual data for making decisions and some of these systems have limited energy (such as unmanned aerial vehicles also called drones and mobile robots).
Towards Leveraging the Information of Gradients in Optimization-based Adversarial Attack
We intuitively and empirically prove the rationality of our method in reducing the search space.
LEASGD: an Efficient and Privacy-Preserving Decentralized Algorithm for Distributed Learning
Distributed learning systems have enabled training large-scale models over large amount of data in significantly shorter time.
Differentiable Fine-grained Quantization for Deep Neural Network Compression
Thus judiciously selecting different precision for different layers/structures can potentially produce more efficient models compared to traditional quantization methods by striking a better balance between accuracy and compression rate.
2018 Low-Power Image Recognition Challenge
The Low-Power Image Recognition Challenge (LPIRC, https://rebootingcomputing. ieee. org/lpirc) is an annual competition started in 2015.
MAT: A Multi-strength Adversarial Training Method to Mitigate Adversarial Attacks
Our experiments show that different adversarial strengths, i. e., perturbation levels of adversarial examples, have different working zones to resist the attack.
