BCNet: Searching for Network Width with Bilaterally Coupled Network

by   Xiu Su, et al.

Searching for a more compact network width recently serves as an effective way of channel pruning for the deployment of convolutional neural networks (CNNs) under hardware constraints. To fulfill the searching, a one-shot supernet is usually leveraged to efficiently evaluate the performance  different network widths. However, current methods mainly follow a unilaterally augmented (UA) principle for the evaluation of each width, which induces the training unfairness of channels in supernet. In this paper, we introduce a new supernet called Bilaterally Coupled Network (BCNet) to address this issue. In BCNet, each channel is fairly trained and responsible for the same amount of network widths, thus each network width can be evaluated more accurately. Besides, we leverage a stochastic complementary strategy for training the BCNet, and propose a prior initial population sampling method to boost the performance of the evolutionary search. Extensive experiments on benchmark CIFAR-10 and ImageNet datasets indicate that our method can achieve state-of-the-art or competing performance over other baseline methods. Moreover, our method turns out to further boost the performance of NAS models by refining their network widths. For example, with the same FLOPs budget, our obtained EfficientNet-B0 achieves 77.36% Top-1 accuracy on ImageNet dataset, surpassing the performance of original setting by 0.48%.


page 8

page 13

page 16


Searching for Network Width with Bilaterally Coupled Network

Searching for a more compact network width recently serves as an effecti...

Locally Free Weight Sharing for Network Width Search

Searching for network width is an effective way to slim deep neural netw...

BWCP: Probabilistic Learning-to-Prune Channels for ConvNets via Batch Whitening

This work presents a probabilistic channel pruning method to accelerate ...

Revisiting Random Channel Pruning for Neural Network Compression

Channel (or 3D filter) pruning serves as an effective way to accelerate ...

AOWS: Adaptive and optimal network width search with latency constraints

Neural architecture search (NAS) approaches aim at automatically finding...

SparseNet: A Sparse DenseNet for Image Classification

Deep neural networks have made remarkable progresses on various computer...

Width Transfer: On the (In)variance of Width Optimization

Optimizing the channel counts for different layers of a CNN has shown gr...

Please sign up or login with your details

Forgot password? Click here to reset