My field of interests lie in the intersection of system and ML, which I’m particularly interested in building systems for machine learning and computer vision. Currently focus on Efficient DNN Model Design, advised by Prof. Min Sun and two Google AI researchers, Dr. Da-Cheng Juan and Dr. Wei-Wei.
|
QoS-aware Neural Architecture Search
A.-C. Cheng, C.-H. Lin, D.-C. Juan, W. Wei, M. Sun
NeurIPS'19 Workshop (ML for Systems)
[abs] [pdf] [website] [code]
|
|
InstaNAS: Instance-aware Neural Architecture Search
A.-C. Cheng*, C.-H. Lin*, D.-C. Juan, W. Wei, M. Sun
AAAI'20
ICML'19 Workshop (AutoML)
[abs] [pdf] [website] [code]
Conventional Neural Architecture Search (NAS) aims at
finding a single architecture that achieves the best performance, which usually optimizes task related learning objectives such as accuracy. However, a single architecture may
not be representative enough for the whole dataset with high
diversity and variety. Intuitively, electing domain-expert architectures that are proficient in domain-specific features
can further benefit architecture related objectives such as
latency. In this paper, we propose InstaNAS—an instanceaware NAS framework—that employs a controller trained to
search for a “distribution of architectures” instead of a single architecture; This allows the model to use sophisticated
architectures for the difficult samples, which usually comes
with large architecture related cost, and shallow architectures for those easy samples. During the inference phase,
the controller assigns each of the unseen input samples with
a domain expert architecture that can achieve high accuracy with customized inference costs. Experiments within a
search space inspired by MobileNetV2 show InstaNAS can
achieve up to 48.8% latency reduction without compromising accuracy on a series of datasets against MobileNetV2.
|
|
Searching Toward Pareto-Optimal Device-Aware Neural Architectures
A.-C. Cheng, J.-D. Dong, C.-H. Hsu, S.-H. Chang, M. Sun, S.-C. Chang, J.-Y. Pan, Y.-T. Chen, W. Wei, D.-C. Juan
ICCAD'18
[abs] [pdf]
Recent breakthroughs in Neural Architectural Search (NAS) have achieved state-of-the-art performance in many tasks such as image classification and language understanding. However, most existing works only optimize for model accuracy and largely ignore other important factors imposed by the underlying hardware and devices, such as latency and energy, when making inference. In this paper, we first introduce the problem of NAS and provide a survey on recent works. Then we deep dive into two recent advancements on extending NAS into multiple-objective frameworks: MONAS and DPP-Net. Both MONAS and DPP-Net are capable of optimizing accuracy and other objectives imposed by devices, searching for neural architectures that can be best deployed on a wide spectrum of devices: from embedded systems and mobile devices to workstations. Experimental results are poised to show that architectures found by MONAS and DPP-Net achieves Pareto optimality w.r.t the given objectives for various devices.
|
|
Visual Relationship Prediction via Label Clustering and Incorporation of Depth Information
H.-K. Yang, A.-C. Cheng*, K.-W. Ho*, T.-J Fu, C.-Y Lee
ECCV'18 Workshop
[abs] [pdf]
In this paper, we investigate the use of an unsupervised label clustering technique and demonstrate that it enables substantial improvements in visual relationship prediction accuracy on the Person in Context (PIC) dataset. We propose to group object labels with similar patterns of relationship distribution in the dataset into fewer categories. Label clustering not only mitigates both the large classification space and class imbalance issues, but also potentially increases data samples for each clustered category. We further propose to incorporate depth information as an additional feature into the instance segmentation model. The additional depth prediction path supplements the relationship prediction model in a way that bounding boxes or segmentation masks are unable to deliver. We have rigorously evaluated the proposed techniques and performed various ablation analysis to validate the benefits of them.
|
|
DPP-Net: Device-aware Progressive Search for Pareto-optimal Neural Architectures
J.-D. Dong, A.-C. Cheng, D.-C. Juan, W. Wei, M. Sun
ECCV'18
[abs] [pdf]
Recent breakthroughs in Neural Architectural Search (NAS) have achieved state-of-the-art performances in applications such as image classification and language modeling. However, these techniques typically ignore device-related objectives such as inference time, memory usage, and power consumption. Optimizing neural architecture for device-related objectives is immensely crucial for deploying deep networks on portable devices with limited computing resources. We propose DPP-Net: Device-aware Progressive Search for Pareto-optimal Neural Architectures, optimizing for both device-related (e.g., inference time and memory usage) and device-agnostic (e.g., accuracy and model size) objectives. DPP-Net employs a compact search space inspired by current state-of-the-art mobile CNNs, and further improves search efficiency by adopting progressive search (Liu et al. 2017). Experimental results on CIFAR-10 are poised to demonstrate the effectiveness of Pareto-optimal networks found by DPP-Net, for three different devices: (1) a workstation with Titan X GPU, (2) NVIDIA Jetson TX1 embedded system, and (3) mobile phone with ARM Cortex-A53. Compared to CondenseNet and NASNet (Mobile), DPP-Net achieves better performances: higher accuracy and shorter inference time on various devices. Additional experimental results show that models found by DPP-Net also achieve considerably-good performance on ImageNet as well.
|
|
PPP-Net: Platform-aware Progressive Search for Pareto-optimal Neural Architectures
J.-D. Dong, A.-C. Cheng, D.-C. Juan, W. Wei, M. Sun
ICLR'18 Workshop
[abs] [pdf]
Recent breakthroughs in Neural Architectural Search (NAS) have achieved state-of-the-art performances in many applications such as image recognition. However, these techniques typically ignore platform-related constrictions (e.g., inference time and power consumptions) that can be critical for portable devices with limited computing resources. We propose PPP-Net: a multi-objective architectural search framework to automatically generate networks that achieve Pareto Optimality. PPP-Net employs a compact search space inspired by operations used in state-of-the-art mobile CNNs. PPP-Net has also adopted the progressive search strategy used in a recent literature (Liu et al. (2017a)). Experimental results demonstrate that PPP-Net achieves better performances in both (a) higher accuracy and (b) shorter inference time, comparing to the state-of-the-art CondenseNet.
|
|
Supporting Internet-of-Things Analytics in a Fog Computing Platform
H. Hong, P. Tsai, A.-C. Cheng, Y. Uddin, N. Venkatasubramanian, and C. Hsu
CloudCom'17
[abs] [pdf] [website]
Modern IoT analytics are computational and data
intensive. Existing analytics are mostly hosted in cloud data centers, and may suffer from high latency, network congestion, and
privacy issues. In this paper, we design, implement, and evaluate
a fog computing platform that runs analytics in a distributed
way on multiple devices, including IoT devices, edge servers,
and data-center servers. We focus on the core optimization
problem: making deployment decisions to maximize the number
of satisfied IoT analytics. We carefully formulate the deployment
problem and design an efficient algorithm, named SSE, to solve
it. Moreover, we conduct a detailed measurement study to derive
system models of the IoT analytics based on diverse QoS levels
and heterogeneous devices to facilitate the optimal deployment
decisions. We implement a testbed to conduct experiments, which
show that the system models achieve reasonably good accuracy.
More importantly, 100% of the deployed IoT analytics satisfy the
QoS targets. We also conduct extensive simulations for largerscale scenarios. The simulation results reveal that our SSE algorithm outperforms a state-of-the-art algorithm by up to 89.4%
and 168.3% in terms of the number of satisfied IoT analytics
and active devices. In addition, our SSE algorithm reduces CPU,
RAM, and network resource consumptions by 18.4%, 12.7%, and
898.3%, respectively, and terminates in polynomial time.</div>
</td>
</tr>
|
Distributed Analytics in Fog Computing Platforms Using Tensorflow and Kubernetesm
P. Tsai, H. Hong, A.-C. Cheng, and C. Hsu
APNOMS'17
[abs] [pdf] [website]
Modern Internet-of-Things (IoT) applications produce large amount of data and require powerful analytics approaches, such as Deep Learning to extract useful information. Existing IoT applications transmit the data to resource-rich data centers for analytics. However, it may congest networks, overload data centers, and increase security vulnerability. In this paper, we implement a platform, which integrates resources from data centers (servers) to end devices (IoT devices). We launch distributed analytics applications among the devices without sending everything to the data centers. We analyze challenges to implement such a platform and carefully adopt popular open-source projects to overcome the challenges. We then conduct comprehensive experiments on the implemented platform. The results show: (i) the benefits/limitations of distributed analytics, (ii) the importance of decisions on distributing an application across multiple devices, and (iii) the overhead caused by different components in our platform.</div>
</td>
</tr>
Teaching Experience
F2018 |
Computer Vision (NTHU EE 6485), TA |
Honors & Awards
2019 |
NovaTek Scholarship, NovaTek
|
2018 |
2nd Place, ECCV 2018 PIC Challenge
|
2018 |
Outstanding Student Award, National Tsing-Hua University
|
2017 |
First Prize, MeiChu Hackathon / IJoinG Inc.
|
2016 |
First Prize, MeiChu Hackathon / Asus Inc.
|
Service
Reviewer |
IEEE J-STSP, ICCV 2019, AAAI 2020, CVPR 2020, ECCV 2020
|
Program Committee |
NAS@ICLR 2020
|
Last updated on 2020-05-05
. Templated from Brandon Amos.
|
|