ChamNet: Towards Efficient Network Design Through Platform-Aware Model Adaptation

By Xiaoliang Dai, Peizhao Zhang, Bichen Wu, Hongxu Yin, Fei Sun, Yanghan Wang, Marat Dukhan, Yunqing Hu, Yiming Wu, Yangqing Jia and 3 more. 2018

294 citations recorded by the source corpus.

This paper proposes an efficient neural network (NN) architecture design methodology called Chameleon that honors given resource constraints. Instead of developing new building blocks or using computationally-intensive reinforcement learning algorithms, our approach leverages existing efficient network building blocks and focuses on exploiting hardware traits and adapting computation resources to fit target latency and/or energy constraints. We formulate platform-aware NN architecture search in an optimization framework and propose a novel algorithm to search for optimal architectures aided by efficient accuracy and resource (latency and/or energy) predictors. At the core of our algorithm lies an accuracy predictor built atop Gaussian Process with Bayesian optimization for iterative sampling. With a one-time building cost for the predictors, our algorithm produces state-of-the-art model architectures on different platforms under given constraints in just minutes. Our results show that adapting computation resources to building blocks is critical to model performance. Without the addition of any special features, our models achieve significant accuracy improvements relative to state-of-the-art handcrafted and automatically designed architectures. We achieve 73.8% and 75.3% top-1 accuracy on ImageNet at 20ms latency on a mobile CPU and DSP. At reduced latency, our models achieve up to 8.2% (4.8%) and 6.7% (9.3%) absolute top-1 accuracy improvements compared to MobileNetV2 and MnasNet, respectively, on a mobile CPU (DSP), and 2.7% (4.6%) and 5.6% (2.6%) accuracy gains over ResNet-101 and ResNet-152, respectively, on an Nvidia GPU (Intel CPU).

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Efficiency & Compression

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Efficiency & Compression

Citations in the corpus

Visual Transformers: Token-based Image Representation and Processing for Computer Vision (2020, background): “Recently, people use neural architecture search [42, 10, 38, 9, 36, 35] to optimize network’s performance within a search space that consists of existing convolution operators.”
A Comprehensive Survey of Neural Architecture Search (2020, background): “object detection [65, 75, 111, 118], semantic segmentation [63, 64, 120], adversarial learning [53], architectural scaling [114, 122, 124], multi-objective optimization [39, 115, 125], platform-aware [28, 34, 103, 117], data augmentation [121, 123] and so on. In addition, there is some work to consi”
Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hours (2019, methodology): “, the FBNet-B and ChamNet-B networks [6,21], since the authors use these ConvNets to compare against the MnasNet model).”
Dreaming to Distill: Data-Free Knowledge Transfer via DeepInversion (2019, background): “For example, one might want to use a more resource-efficient architecture for deployment on edge inference devices [44, 66, 76], or to adapt the network to the inference hardware [9, 63, 71], or for continually learning to classify new image classes [29, 34], etc.”
Searching for MobileNetV3 (2019, methodology): “Focusing on adapting existing networks to constrained mobile platforms, [48, 15, 12] proposed more efficient automated network simplification algorithms.”
Neural Predictor for Neural Architecture Search (2019, methodology): “Another popular approach combined a predictor with Bayesian Optimization [6].”
Densely Connected Search Space for More Flexible Neural Architecture Search (2019, background): “Some works [4, 14, 45, 9] simplify the search space by searching for the expansion ratios and kernel sizes of MBConv layers.”
Can Weight Sharing Outperform Random Architecture Search? An Investigation With TuNAS (2020, methodology): “Recently, Neural Architecture Search has been used intensively to find architectures that have better tradeoff between accuracy and latency [36, 39, 8, 5, 35], FLOPS [37], power consumption [14], and memory usage [9].”
Incremental Learning Using a Grow-and-Prune Paradigm With Efficient Neural Networks (2019, methodology): “develop an automated architecture adaptation and search framework based on efficient performance predictors [28].”
Hardware-Guided Symbiotic Training for Compact, Accurate, yet Execution-Efficient LSTM (2019, background): “Chameleon [24] can effectively adapt CNNs to target platforms and deliver ChamNets that achieve consistent accuracy gains across various latency constraints relative to MobileNetV2 [25], MnasNet [26], and ShuffleNetV2 [27].”
SqueezeWave: Extremely Lightweight Vocoders for On-device Speech Synthesis (2020, background): “Previous work (Iandola et al., 2016; Wu et al., 2016; 2017; 2018a;b; Yang et al., 2018; Gholami et al., 2018; Wu, 2019; Wu et al., 2019; Dai et al., 2019) have shown that optimizing the neural network architecture can lead to significant efficiency improvement in many applications.”
FasterSeg: Searching for Faster Real-time Semantic Segmentation (2019, methodology): “These works optimize both accuracy and resource utilization, via a combined loss function (Wu et al., 2019), or a hybrid reward signal for policy learning (Tan et al., 2019; Cheng et al., 2018), or a constrained optimization formulation (Dai et al., 2019).”
Single-Path Mobile AutoML: Efficient ConvNet Design and NAS Hyperparameter Optimization (2019, methodology): “prior NAS methods in this mobile latency range [16], [1], [15], as well as manually designed models (MobileNetV2 [11]) and ConvNets that combine both AutoML and manual-design”
Review of Image Classification Algorithms Based on Convolutional Neural Networks (2021, methodology): “[164,165,213,214] proposed more efficient automated network simplification algorithms.”
NAT: Neural Architecture Transformer for Accurate and Compact Architectures (2019, methodology): “Several methods [48, 7, 6] have been proposed to obtain compact architectures by learning the optimal settings of each convolution, including kernel size, stride and the number of filters.”
AutoSpeech: Neural Architecture Search for Speaker Recognition (2020, unknown): “To improve its efﬁciency, [30, 31, 32] adopts a sequential-based search space, beneﬁting a lot in reducing latency and FLOPs inherently.”