Ting-Wu Chin

Ahmet Inci, Siri Garudanagiri Virupaksha, Aman Jain et al.

As the machine learning and systems communities strive to achieve higher energy-efficiency through custom deep neural network (DNN) accelerators, varied precision or quantization levels, and model compression techniques, there is a need for design space exploration frameworks that incorporate quantization-aware processing elements into the accelerator design space while having accurate and fast power, performance, and area models. In this work, we present QUIDAM, a highly parameterized quantization-aware DNN accelerator and model co-exploration framework. Our framework can facilitate future research on design space exploration of DNN accelerators for various design choices such as bit precision, processing element type, scratchpad sizes of processing elements, global buffer size, number of total processing elements, and DNN configurations. Our results show that different bit precisions and processing element types lead to significant differences in terms of performance per area and energy. Specifically, our framework identifies a wide range of design points where performance per area and energy varies more than 5x and 35x, respectively. With the proposed framework, we show that lightweight processing elements achieve on par accuracy results and up to 5.7x more performance per area and energy improvement when compared to the best INT16 based implementation. Finally, due to the efficiency of the pre-characterized power, performance, and area models, QUIDAM can speed up the design exploration process by 3-4 orders of magnitude as it removes the need for expensive synthesis and characterization of each design.

Yang Zhou, Feng Liang, Ting-wu Chin et al.

Machine learning (ML) has entered the mobile era where an enormous number of ML models are deployed on edge devices. However, running common ML models on edge devices continuously may generate excessive heat from the computation, forcing the device to "slow down" to prevent overheating, a phenomenon called thermal throttling. This paper studies the impact of thermal throttling on mobile phones: when it occurs, the CPU clock frequency is reduced, and the model inference latency may increase dramatically. This unpleasant inconsistent behavior has a substantial negative effect on user experience, but it has been overlooked for a long time. To counter thermal throttling, we propose to utilize dynamic networks with shared weights and dynamically shift between large and small ML models seamlessly according to their thermal profile, i.e., shifting to a small model when the system is about to throttle. With the proposed dynamic shifting, the application runs consistently without experiencing CPU clock frequency degradation and latency increase. In addition, we also study the resulting accuracy when dynamic shifting is deployed and show that our approach provides a reasonable trade-off between model latency and model accuracy.

Ting-Wu Chin, Ari S. Morcos, Diana Marculescu

Slimmable neural networks provide a flexible trade-off front between prediction error and computational requirement (such as the number of floating-point operations or FLOPs) with the same storage requirement as a single model. They are useful for reducing maintenance overhead for deploying models to devices with different memory constraints and are useful for optimizing the efficiency of a system with many CNNs. However, existing slimmable network approaches either do not optimize layer-wise widths or optimize the shared-weights and layer-wise widths independently, thereby leaving significant room for improvement by joint width and weight optimization. In this work, we propose a general framework to enable joint optimization for both width configurations and weights of slimmable networks. Our framework subsumes conventional and NAS-based slimmable methods as special cases and provides flexibility to improve over existing methods. From a practical standpoint, we propose Joslim, an algorithm that jointly optimizes both the widths and weights for slimmable nets, which outperforms existing methods for optimizing slimmable networks across various networks, datasets, and objectives. Quantitatively, improvements up to 1.7% and 8% in top-1 accuracy on the ImageNet dataset can be attained for MobileNetV2 considering FLOPs and memory footprint, respectively. Our results highlight the potential of optimizing the channel counts for different layers jointly with the weights for slimmable networks. Code available at https://github.com/cmu-enyac/Joslim.

Ting-Wu Chin, Cha Zhang, Diana Marculescu

Fine-tuning through knowledge transfer from a pre-trained model on a large-scale dataset is a widely spread approach to effectively build models on small-scale datasets. In this work, we show that a recent adversarial attack designed for transfer learning via re-training the last linear layer can successfully deceive models trained with transfer learning via end-to-end fine-tuning. This raises security concerns for many industrial applications. In contrast, models trained with random initialization without transfer are much more robust to such attacks, although these models often exhibit much lower accuracy. To this end, we propose noisy feature distillation, a new transfer learning method that trains a network from random initialization while achieving clean-data performance competitive with fine-tuning. Code available at https://github.com/cmu-enyac/Renofeation.

Ting-Wu Chin, Ruizhou Ding, Cha Zhang et al.

Pruning convolutional filters has demonstrated its effectiveness in compressing ConvNets. Prior art in filter pruning requires users to specify a target model complexity (e.g., model size or FLOP count) for the resulting architecture. However, determining a target model complexity can be difficult for optimizing various embodied AI applications such as autonomous robots, drones, and user-facing applications. First, both the accuracy and the speed of ConvNets can affect the performance of the application. Second, the performance of the application can be hard to assess without evaluating ConvNets during inference. As a consequence, finding a sweet-spot between the accuracy and speed via filter pruning, which needs to be done in a trial-and-error fashion, can be time-consuming. This work takes a first step toward making this process more efficient by altering the goal of model compression to producing a set of ConvNets with various accuracy and latency trade-offs instead of producing one ConvNet targeting some pre-defined latency constraint. To this end, we propose to learn a global ranking of the filters across different layers of the ConvNet, which is used to obtain a set of ConvNet architectures that have different accuracy/latency trade-offs by pruning the bottom-ranked filters. Our proposed algorithm, LeGR, is shown to be 2x to 3x faster than prior work while having comparable or better performance when targeting seven pruned ResNet-56 with different accuracy/FLOPs profiles on the CIFAR-100 dataset. Additionally, we have evaluated LeGR on ImageNet and Bird-200 with ResNet-50 and MobileNetV2 to demonstrate its effectiveness. Code available at https://github.com/cmu-enyac/LeGR.

Zhuo Chen, Ruizhou Ding, Ting-Wu Chin et al.

In recent years, supervised learning using Convolutional Neural Networks (CNNs) has achieved great success in image classification tasks, and large scale labeled datasets have contributed significantly to this achievement. However, the definition of a label is often application dependent. For example, an image of a cat can be labeled as "cat" or perhaps more specifically "Persian cat." We refer to this as label granularity. In this paper, we conduct extensive experiments using various datasets to demonstrate and analyze how and why training based on fine-grain labeling, such as "Persian cat" can improve CNN accuracy on classifying coarse-grain classes, in this case "cat." The experimental results show that training CNNs with fine-grain labels improves both network's optimization and generalization capabilities, as intuitively it encourages the network to learn more features, and hence increases classification accuracy on coarse-grain classes under all datasets considered. Moreover, fine-grain labels enhance data efficiency in CNN training. For example, a CNN trained with fine-grain labels and only 40% of the total training data can achieve higher accuracy than a CNN trained with the full training dataset and coarse-grain labels. These results point to two possible applications of this work: (i) with sufficient human resources, one can improve CNN performance by re-labeling the dataset with fine-grain labels, and (ii) with limited human resources, to improve CNN performance, rather than collecting more training data, one may instead use fine-grain labels for the dataset. We further propose a metric called Average Confusion Ratio to characterize the effectiveness of fine-grain labeling, and show its use through extensive experimentation. Code is available at https://github.com/cmu-enyac/Label-Granularity.

Ting-Wu Chin, Diana Marculescu, Ari S. Morcos

Optimizing the channel counts for different layers of a CNN has shown great promise in improving the efficiency of CNNs at test-time. However, these methods often introduce large computational overhead (e.g., an additional 2x FLOPs of standard training). Minimizing this overhead could therefore significantly speed up training. In this work, we propose width transfer, a technique that harnesses the assumptions that the optimized widths (or channel counts) are regular across sizes and depths. We show that width transfer works well across various width optimization algorithms and networks. Specifically, we can achieve up to 320x reduction in width optimization overhead without compromising the top-1 accuracy on ImageNet, making the additional cost of width optimization negligible relative to initial training. Our findings not only suggest an efficient way to conduct width optimization but also highlight that the widths that lead to better accuracy are invariant to various aspects of network architectures and training data.

Ting-Wu Chin, Pierce I-Jen Chuang, Vikas Chandra et al.

Weight quantization for deep ConvNets has shown promising results for applications such as image classification and semantic segmentation and is especially important for applications where memory storage is limited. However, when aiming for quantization without accuracy degradation, different tasks may end up with different bitwidths. This creates complexity for software and hardware support and the complexity accumulates when one considers mixed-precision quantization, in which case each layer's weights use a different bitwidth. Our key insight is that optimizing for the least bitwidth subject to no accuracy degradation is not necessarily an optimal strategy. This is because one cannot decide optimality between two bitwidths if one has a smaller model size while the other has better accuracy. In this work, we take the first step to understand if some weight bitwidth is better than others by aligning all to the same model size using a width-multiplier. Under this setting, somewhat surprisingly, we show that using a single bitwidth for the whole network can achieve better accuracy compared to mixed-precision quantization targeting zero accuracy degradation when both have the same model size. In particular, our results suggest that when the number of channels becomes a target hyperparameter, a single weight bitwidth throughout the network shows superior results for model compression.

Ruizhou Ding, Zeye Liu, Ting-Wu Chin et al.

To improve the throughput and energy efficiency of Deep Neural Networks (DNNs) on customized hardware, lightweight neural networks constrain the weights of DNNs to be a limited combination (denoted as $k\in\{1,2\}$) of powers of 2. In such networks, the multiply-accumulate operation can be replaced with a single shift operation, or two shifts and an add operation. To provide even more design flexibility, the $k$ for each convolutional filter can be optimally chosen instead of being fixed for every filter. In this paper, we formulate the selection of $k$ to be differentiable, and describe model training for determining $k$-based weights on a per-filter basis. Over 46 FPGA-design experiments involving eight configurations and four data sets reveal that lightweight neural networks with a flexible $k$ value (dubbed FLightNNs) fully utilize the hardware resources on Field Programmable Gate Arrays (FPGAs), our experimental results show that FLightNNs can achieve 2$\times$ speedup when compared to lightweight NNs with $k=2$, with only 0.1\% accuracy degradation. Compared to a 4-bit fixed-point quantization, FLightNNs achieve higher accuracy and up to 2$\times$ inference speedup, due to their lightweight shift operations. In addition, our experiments also demonstrate that FLightNNs can achieve higher computational energy efficiency for ASIC implementation.

Ruizhou Ding, Ting-Wu Chin, Zeye Liu et al.

Binarized Neural Networks (BNNs) can significantly reduce the inference latency and energy consumption in resource-constrained devices due to their pure-logical computation and fewer memory accesses. However, training BNNs is difficult since the activation flow encounters degeneration, saturation, and gradient mismatch problems. Prior work alleviates these issues by increasing activation bits and adding floating-point scaling factors, thereby sacrificing BNN's energy efficiency. In this paper, we propose to use distribution loss to explicitly regularize the activation flow, and develop a framework to systematically formulate the loss. Our experiments show that the distribution loss can consistently improve the accuracy of BNNs without losing their energy benefits. Moreover, equipped with the proposed regularization, BNN training is shown to be robust to the selection of hyper-parameters including optimizer and learning rate.

Ting-Wu Chin, Ruizhou Ding, Diana Marculescu

In vision-enabled autonomous systems such as robots and autonomous cars, video object detection plays a crucial role, and both its speed and accuracy are important factors to provide reliable operation. The key insight we show in this paper is that speed and accuracy are not necessarily a trade-off when it comes to image scaling. Our results show that re-scaling the image to a lower resolution will sometimes produce better accuracy. Based on this observation, we propose a novel approach, dubbed AdaScale, which adaptively selects the input image scale that improves both accuracy and speed for video object detection. To this end, our results on ImageNet VID and mini YouTube-BoundingBoxes datasets demonstrate 1.3 points and 2.7 points mAP improvement with 1.6x and 1.8x speedup, respectively. Additionally, we improve state-of-the-art video acceleration work by an extra 1.25x speedup with slightly better mAP on ImageNet VID dataset.

Ting-Wu Chin, Chia-Lin Yu, Matthew Halpern et al.

There is growing interest in object detection in advanced driver assistance systems and autonomous robots and vehicles. To enable such innovative systems, we need faster object detection. In this work, we investigate the trade-off between accuracy and speed with domain-specific approximations, i.e. category-aware image size scaling and proposals scaling, for two state-of-the-art deep learning-based object detection meta-architectures. We study the effectiveness of applying approximation both statically and dynamically to understand the potential and the applicability of them. By conducting experiments on the ImageNet VID dataset, we show that domain-specific approximation has great potential to improve the speed of the system without deteriorating the accuracy of object detectors, i.e. up to 7.5x speedup for dynamic domain-specific approximation. To this end, we present our insights toward harvesting domain-specific approximation as well as devise a proof-of-concept runtime, AutoFocus, that exploits dynamic domain-specific approximation.

Ting-Wu Chin, Cha Zhang, Diana Marculescu

Resource-efficient convolution neural networks enable not only the intelligence on edge devices but also opportunities in system-level optimization such as scheduling. In this work, we aim to improve the performance of resource-constrained filter pruning by merging two sub-problems commonly considered, i.e., (i) how many filters to prune for each layer and (ii) which filters to prune given a per-layer pruning budget, into a global filter ranking problem. Our framework entails a novel algorithm, dubbed layer-compensated pruning, where meta-learning is involved to determine better solutions. We show empirically that the proposed algorithm is superior to prior art in both effectiveness and efficiency. Specifically, we reduce the accuracy gap between the pruned and original networks from 0.9% to 0.7% with 8x reduction in time needed for meta-learning, i.e., from 1 hour down to 7 minutes. To this end, we demonstrate the effectiveness of our algorithm using ResNet and MobileNetV2 networks under CIFAR-10, ImageNet, and Bird-200 datasets.

Dimitrios Stamoulis, Ting-Wu Chin, Anand Krishnan Prakash et al.

As convolutional neural networks (CNNs) enable state-of-the-art computer vision applications, their high energy consumption has emerged as a key impediment to their deployment on embedded and mobile devices. Towards efficient image classification under hardware constraints, prior work has proposed adaptive CNNs, i.e., systems of networks with different accuracy and computation characteristics, where a selection scheme adaptively selects the network to be evaluated for each input image. While previous efforts have investigated different network selection schemes, we find that they do not necessarily result in energy savings when deployed on mobile systems. The key limitation of existing methods is that they learn only how data should be processed among the CNNs and not the network architectures, with each network being treated as a blackbox. To address this limitation, we pursue a more powerful design paradigm where the architecture settings of the CNNs are treated as hyper-parameters to be globally optimized. We cast the design of adaptive CNNs as a hyper-parameter optimization problem with respect to energy, accuracy, and communication constraints imposed by the mobile device. To efficiently solve this problem, we adapt Bayesian optimization to the properties of the design space, reaching near-optimal configurations in few tens of function evaluations. Our method reduces the energy consumed for image classification on a mobile device by up to 6x, compared to the best previously published work that uses CNNs as blackboxes. Finally, we evaluate two image classification practices, i.e., classifying all images locally versus over the cloud under energy and communication constraints.