arXiv subjects

Yihui He

Publications and source records attributed to Yihui He.

27 records · Page 2Linked to original sources

arXiv2019

AMC: AutoML for Model Compression and Acceleration on Mobile Devices

Model compression is a critical technique to efficiently deploy neural network models on mobile devices which have limited computation resources and tight power budgets. Conventional model compression techniques rely on hand-crafted heuristics and rule-based policies that require domain experts to explore the large design space trading off among model size, speed, and accuracy, which is usually sub-optimal and time-consuming. In this paper, we propose AutoML for Model Compression (AMC) which leverage reinforcement learning to provide the model compression policy. This learning-based compression policy outperforms conventional rule-based compression policy by having higher compression ratio, better preserving the accuracy and freeing human labor. Under 4x FLOPs reduction, we achieved 2.7% better accuracy than the handcrafted model compression policy for VGG-16 on ImageNet. We applied this automated, push-the-button compression pipeline to MobileNet and achieved 1.81x speedup of measured inference latency on an Android phone and 1.43x speedup on the Titan XP GPU, with only 0.1% loss of ImageNet Top-1 accuracy.

cs.CV↗

arXiv2018

An Empirical Analysis of Deep Audio-Visual Models for Speech Recognition

In this project, we worked on speech recognition, specifically predicting individual words based on both the video frames and audio. Empowered by convolutional neural networks, the recent speech recognition and lip reading models are comparable to human level performance. We re-implemented and made derivations of the state-of-the-art model. Then, we conducted rich experiments including the effectiveness of attention mechanism, more accurate residual network as the backbone with pre-trained weights and the sensitivity of our model with respect to audio input with/without noise.

cs.CV↗

arXiv2018

Ultrafast correlated charge and lattice motion in a hybrid metal halide perovskite

Hybrid organic-inorganic halide perovskites have shown remarkable optoelectronic properties (1-3), believed to originate from correlated motion of charge carriers and the polar lattice forming large polarons (4-7). Few experimental techniques are capable of probing these correlations directly, requiring simultaneous sub-meV energy and femtosecond temporal resolution after absorption of a photon (8). Here we use transient multi-THz spectroscopy, sensitive to the internal motions of charges within the polaron, to temporally and energetically resolve the coherent coupling of charges to longitudinal optical phonons in single crystal CH3NH3PbI3 (MAPI). We observe room temperature quantum beats arising from the coherent displacement of charge from the coupled phonon cloud. Our measurements provide unambiguous evidence of the existence of polarons in MAPI.

cond-mat.mtrl-sci↗

arXiv2018

Shift-based Primitives for Efficient Convolutional Neural Networks

We propose a collection of three shift-based primitives for building efficient compact CNN-based networks. These three primitives (channel shift, address shift, shortcut shift) can reduce the inference time on GPU while maintains the prediction accuracy. These shift-based primitives only moves the pointer but avoids memory copy, thus very fast. For example, the channel shift operation is 12.7x faster compared to channel shuffle in ShuffleNet but achieves the same accuracy. The address shift and channel shift can be merged into the point-wise group convolution and invokes only a single kernel call, taking little time to perform spatial convolution and channel shift. Shortcut shift requires no time to realize residual connection through allocating space in advance. We blend these shift-based primitives with point-wise group convolution and built two inference-efficient CNN architectures named AddressNet and Enhanced AddressNet. Experiments on CIFAR100 and ImageNet datasets show that our models are faster and achieve comparable or better accuracy.

cs.CV↗

arXiv2018

Vehicle Traffic Driven Camera Placement for Better Metropolis Security Surveillance

Security surveillance is one of the most important issues in smart cities, especially in an era of terrorism. Deploying a number of (video) cameras is a common surveillance approach. Given the never-ending power offered by vehicles to metropolises, exploiting vehicle traffic to design camera placement strategies could potentially facilitate security surveillance. This article constitutes the first effort toward building the linkage between vehicle traffic and security surveillance, which is a critical problem for smart cities. We expect our study could influence the decision making of surveillance camera placement, and foster more research of principled ways of security surveillance beneficial to our physical-world life. Code has been made publicly available.

cs.CY↗

arXiv2017

Single Image Super-resolution via a Lightweight Residual Convolutional Neural Network

Recent years have witnessed great success of convolutional neural network (CNN) for various problems both in low and high level visions. Especially noteworthy is the residual network which was originally proposed to handle high-level vision problems and enjoys several merits. This paper aims to extend the merits of residual network, such as skip connection induced fast training, for a typical low-level vision problem, i.e., single image super-resolution. In general, the two main challenges of existing deep CNN for supper-resolution lie in the gradient exploding/vanishing problem and large numbers of parameters or computational cost as CNN goes deeper. Correspondingly, the skip connections or identity mapping shortcuts are utilized to avoid gradient exploding/vanishing problem. In addition, the skip connections have naturally centered the activation which led to better performance. To tackle with the second problem, a lightweight CNN architecture which has carefully designed width, depth and skip connections was proposed. In particular, a strategy of gradually varying the shape of network has been proposed for residual network. Different residual architectures for image super-resolution have also been compared. Experimental results have demonstrated that the proposed CNN model can not only achieve state-of-the-art PSNR and SSIM results for single image super-resolution but also produce visually pleasant results. This paper has extended the mmm 2017 oral conference paper with a considerable new analyses and more experiments especially from the perspective of centering activations and ensemble behaviors of residual network.

cs.CV↗

arXiv2017

Estimated Depth Map Helps Image Classification

We consider image classification with estimated depth. This problem falls into the domain of transfer learning, since we are using a model trained on a set of depth images to generate depth maps (additional features) for use in another classification problem using another disjoint set of images. It's challenging as no direct depth information is provided. Though depth estimation has been well studied, none have attempted to aid image classification with estimated depth. Therefore, we present a way of transferring domain knowledge on depth estimation to a separate image classification task over a disjoint set of train, and test data. We build a RGBD dataset based on RGB dataset and do image classification on it. Then evaluation the performance of neural networks on the RGBD dataset compared to the RGB dataset. From our experiments, the benefit is significant with shallow and deep networks. It improves ResNet-20 by 0.55% and ResNet-56 by 0.53%. Our code and dataset are available publicly.

cs.CV↗

arXiv2017

Channel Pruning for Accelerating Very Deep Neural Networks

In this paper, we introduce a new channel pruning method to accelerate very deep convolutional neural networks.Given a trained CNN model, we propose an iterative two-step algorithm to effectively prune each layer, by a LASSO regression based channel selection and least square reconstruction. We further generalize this algorithm to multi-layer and multi-branch cases. Our method reduces the accumulated error and enhance the compatibility with various architectures. Our pruned VGG-16 achieves the state-of-the-art results by 5x speed-up along with only 0.3% increase of error. More importantly, our method is able to accelerate modern networks like ResNet, Xception and suffers only 1.4%, 1.0% accuracy loss under 2x speed-up respectively, which is significant. Code has been made publicly available.

cs.CV↗

arXiv2017

An Empirical Analysis of Approximation Algorithms for the Euclidean Traveling Salesman Problem

With applications to many disciplines, the traveling salesman problem (TSP) is a classical computer science optimization problem with applications to industrial engineering, theoretical computer science, bioinformatics, and several other disciplines. In recent years, there have been a plethora of novel approaches for approximate solutions ranging from simplistic greedy to cooperative distributed algorithms derived from artificial intelligence. In this paper, we perform an evaluation and analysis of cornerstone algorithms for the Euclidean TSP. We evaluate greedy, 2-opt, and genetic algorithms. We use several datasets as input for the algorithms including a small dataset, a mediumsized dataset representing cities in the United States, and a synthetic dataset consisting of 200 cities to test algorithm scalability. We discover that the greedy and 2-opt algorithms efficiently calculate solutions for smaller datasets. Genetic algorithm has the best performance for optimality for medium to large datasets, but generally have longer runtime. Our implementations is public available.

cs.AI↗