# [Paper] MixConv: Mixed Depthwise Convolutional Kernels (Image Classification)

## MixConv, Composes MixNets, Similar Performance With MobileNetV3; Outperforms ProxylessNAS, FBNet, DARTS, MnasNet, NASNet, MobileNetV2, ShuffleNet V2, ShuffleNet V1 & MobileNetV1

--

In this story, **MixConv: Mixed Depthwise Convolutional Kernels (MixConv)**, by Google Brain, is presented. In this paper:

**A new mixed depthwise convolution (MixConv)**, which naturally**mixes up multiple kernel sizes in a single convolution**.- By
**integrating MixConv into AutoML search space**, a new family of models is developed, named as**MixNets**.

This is a paper in **2019 BMCV **with over **60 citations**. (Sik-Ho Tsang @ Medium)

# Outline

**MixConv****MixConv Performance on MobileNets****Ablation Study****MixNet****MixNet Performance on ImageNet****Transfer Learning Performance**

# 1. MixConv

- Unlike vanilla depthwise convolution,
**MixConv partitions channels into groups and applies different kernel sizes to each group**.

- More concretely,
**the input tensor is partitioned into***g*groups of virtual tensors. **The convolutional kernel is also partitioned into**of virtual kernels.*g*groups**The final output tensor**is**a concatenation of all virtual output tensors**.

## 1.1. Group Size

- In the extreme case of
*g*= 1**equivalent to a vanilla depthwise convolution.** - In our experiments, we find
for MobileNets.*g*= 4 is generally a safe choice - But with the help of
**neural architecture search**, we find it can further benefit the model efficiency and accuracy with**a variety of group sizes from 1 to 5.**

## 1.2. Kernel Size Per Group

- Each group is restricted to have
**different kernel sizes**. - And kernel size is always restricted to be
**started from 3×3, and monotonically increases by 2 per group.** - For example, a 4-group MixConv always uses kernel sizes
**{3×3, 5×5, 7×7, 9×9}.**

## 1.3. Channel Size Per Group

- Two partition methods.
- For example, given a 4-group MixConv with total filter size 32, The
**equal partition**will divide the 32 channels into (8, 8, 8, 8), while the**exponential partition**will divide the channels into (16, 8, 4, 4).

## 1.4. Dilated Convolution

- Dilated convolution can increase receptive field without extra parameters and computations. However, dilated convolutions usually have
**inferior accuracy**than large kernel sizes.

# 2. MixConv Performance on MobileNets

- MixConv always starts with 3×3 kernel size and then monotonically increases by 2 per group, so the rightmost point for MixConv in the figure has six groups of filters with kernel size {3×3, 5×5, 7×7, 9×9, 11×11, 13×13}.
- In this figure, we can see that
**MixConv generally uses much less parameters and FLOPS**, but its accuracy is similar or better than vanilla depthwise convolution, suggesting**mixing different kernels can improve both efficiency and accuracy**.

- MixConv357 (with 3 groups of kernels {3×3, 5×5, 7×7}) achieves 0.6% higher mAP on MobileNetV1 and 1.1% higher mAP on MobileNetV2 using fewer parameters and FLOPS.

# 3. Ablation Study

## 3.1. MixConv for Single Layer

- Replace one of the 15 layers with either (1) vanilla DepthwiseConv9×9 with kernel size 9×9; or (2) MixConv3579 with 4 groups of kernels: {3×3, 5×5, 7×7, 9×9}.
- For most of layers, the accuracy doesn’t change much, but for certain layers with stride 2, a larger kernel can significantly improve the accuracy.
- Although MixConv3579 uses only half parameters and FLOPS than the vanilla DepthwiseConv9×9, MixConv achieves similar or slightly better performance for most of the layers.

## 3.2. Channel Partition Methods

- Exponential channel partition only performs slightly better than equal partition on MobileNetV1, but there is
**no clear winner**if considering both MobileNetV1 and MobileNetV2.

## 3.3. Dilated Convolution

- As shown above, dilated convolution has reasonable performance for small kernels, but the accuracy drops quickly for large kernels.
- The hypothesis is that when
**dilation rate is big for large kernels**, a dilated convolution will**skip a lot of local information**, which would**hurt the accuracy.**

# 4. MixNet

**The neural architecture search (NAS) settings are similar to recent****MnasNet****and****FBNet**, which use MobileNetV2 as the baseline network structure.- The search space also includes
**swish**activation,**squeeze-and-excitation**module, and**grouped convolutions**with group size 1 or 2 for 1×1 convolutions. **MixConv is also as the search options**. Five MixConv candidates with group size*g*= 1, …, 5, from 3×3, …, to 3×3, 5×5, 7×7, 9×9, 11×11.- Exponential channel partition or dilated convolutions is not included.
- The NAS directly search on ImageNet train set, and then pick a few top-performing models from search to verify their accuracy on ImageNet validation set and transfer learning datasets.

- It is observed that the bigger
**MixNet-M tends to use more large kernels and more layers**to pursuing higher accuracy. - MixNets are
**capable of utilizing very large kernels such as 9×9 and 11×11**to capture high-resolution patterns from input images, without hurting model accuracy and efficiency.

# 5. MixNet Performance on ImageNet

- MixNets improve top-1 accuracy by 4.2% than MobileNetV2 and 3.5% than ShuffleNet V2, under the same FLOPS constraint.
- Compared to the latest automated models, MixNets achieve better accuracy than MnasNet (+1.3%), FBNets (+2.0%), ProxylessNAS (+2.2%) under similar FLOPS constraint.
- MixNets also achieve similar performance as the latest MobileNetV3.
- MixNet-L achieves a new state-of-the-art 78.9% top-1 accuracy under typical mobile FLOPS (<600M) constraint.

# 6. Transfer Learning Performance

- For each model, it is first trained from scratch on ImageNet and than finetune all the weights on the target dataset.
- MixNets significantly outperform previous models on all these datasets.

# Reference

[2019 BMCV] [MixConv]MixConv: Mixed Depthwise Convolutional Kernels

## Image Classification

**1989–1998**: [LeNet]**2012–2014**: [AlexNet & CaffeNet] [Maxout] [Dropout] [NIN] [ZFNet] [SPPNet]**2015**: [VGGNet] [Highway] [PReLU-Net] [STN] [DeepImage] [GoogLeNet / Inception-v1] [BN-Inception / Inception-v2]**2016**: [SqueezeNet] [Inception-v3] [ResNet] [Pre-Activation ResNet] [RiR] [Stochastic Depth] [WRN] [Trimps-Soushen]**2017**: [Inception-v4] [Xception] [MobileNetV1] [Shake-Shake] [Cutout] [FractalNet] [PolyNet] [ResNeXt] [DenseNet] [PyramidNet] [DRN] [DPN] [Residual Attention Network] [IGCNet / IGCV1] [Deep Roots]**2018**: [RoR] [DMRNet / DFN-MR] [MSDNet] [ShuffleNet V1] [SENet] [NASNet] [MobileNetV2] [CondenseNet] [IGCV2] [IGCV3] [FishNet] [SqueezeNext] [ENAS] [PNASNet] [ShuffleNet V2] [BAM] [CBAM] [MorphNet] [NetAdapt] [mixup] [DropBlock]**2019**: [ResNet-38] [AmoebaNet] [ESPNetv2] [MnasNet] [Single-Path NAS] [DARTS] [ProxylessNAS] [MobileNetV3] [FBNet] [ShakeDrop] [CutMix] [MixConv]**2020**: [Random Erasing (RE)]