Pith. sign in

REVIEW 5 cited by

MixConv: Mixed Depthwise Convolutional Kernels

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1907.09595 v3 pith:46NG3CIC submitted 2019-07-22 cs.CV cs.LG

Mingxing Tan , Quoc V. Le This is my paper · ORCID
classification cs.CVcs.LG
keywords accuracyconvolutiondepthwisekernelmixconvimagenetmodelssizes
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Depthwise convolution is becoming increasingly popular in modern efficient ConvNets, but its kernel size is often overlooked. In this paper, we systematically study the impact of different kernel sizes, and observe that combining the benefits of multiple kernel sizes can lead to better accuracy and efficiency. Based on this observation, we propose a new mixed depthwise convolution (MixConv), which naturally mixes up multiple kernel sizes in a single convolution. As a simple drop-in replacement of vanilla depthwise convolution, our MixConv improves the accuracy and efficiency for existing MobileNets on both ImageNet classification and COCO object detection. To demonstrate the effectiveness of MixConv, we integrate it into AutoML search space and develop a new family of models, named as MixNets, which outperform previous mobile models including MobileNetV2 [20] (ImageNet top-1 accuracy +4.2%), ShuffleNetV2 [16] (+3.5%), MnasNet [26] (+1.3%), ProxylessNAS [2] (+2.2%), and FBNet [27] (+2.0%). In particular, our MixNet-L achieves a new state-of-the-art 78.9% ImageNet top-1 accuracy under typical mobile settings (<600M FLOPS). Code is at https://github.com/ tensorflow/tpu/tree/master/models/official/mnasnet/mixnet

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. CompactFlowNet: Efficient Real-time Optical Flow Estimation on Mobile Devices

    cs.CV 2024-12 conditional novelty 6.0 of 10

    A mobile-optimized optical flow network hits about 25 FPS on an iPhone 8 at 512x512 while staying competitive on KITTI and Sintel.

  2. Efficient Nonlinear Function Approximation in Analog Resistive Crossbars for Recurrent Neural Networks

    cs.AR 2024-11 conditional novelty 6.0 of 10

    A memristor column programmed with the inverse of a desired nonlinear function lets a ramp ADC output that function directly, eliminating the digital activation processing step in RNN inference.

  3. ACM-UNet: Adaptive Integration of CNNs and Mamba for Efficient Medical Image Segmentation

    cs.CV 2025-05 conditional novelty 5.0 of 10

    ACM-UNet, a UNet variant combining pretrained CNN and Mamba backbones via lightweight adapters and a wavelet decoder module, reports 85.12% Dice on Synapse and 92.29% on ACDC.

  4. Pinwheel-shaped Convolution and Scale-based Dynamic Loss for Infrared Small Target Detection

    cs.CV 2024-12 conditional novelty 4.0 of 10

    A pinwheel convolution and a scale-based dynamic loss give small but consistent gains for infrared small-target detection, along with a new drone and bird benchmark.

  5. AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices

    cs.AI 2024-12 conditional novelty 4.0 of 10

    AdaScale continuously rescales a deployed neural network to match a mobile device's fluctuating resources, reporting faster inference and lower energy use while keeping accuracy loss small.

Pith tools