By Xiang Li^[1,2], Wenhai Wang^[3,2], Xiaolin Hu^[4] and Jian Yang^[1]

[PCALab, Nanjing University of Science and Technology]^[1] Momenta^[2] [Nanjing University]^[3] [Tsinghua University]^[4].

Figure 1: The Diagram of a Selective Kernel Convolution module.

In this repository, all the models are implemented by Caffe.

We use the data augmentation strategies with SENet.

There are two new layers introduced for efficient training and inference, these are Axpy and CuDNNBatchNorm layers.

• The Axpy layer is already implemented in SENet.
• The [CuDNNBatchNorm] is mainly borrowed from GENet.

Table 2. Single crop validation error on ImageNet-1k (center 224x224/320x320 crop from resized image with shorter side = 256).

Download:

20190323_Update: SKNet-101 model is deleted by mistake. We are retraining a model and it will come soon in 2-3 days. 20190326_Update: SKNet-101 model is ready.

We look deep into the selection distributions from the perspective of classes on SK_2_3 (low), SK_3_4 (middle), SK_5_3 (high) layers:

Figure 2: Average mean attention difference (mean attention value of kernel 5x5 minus that of kernel 3x3) on SK units of SKNet-50, for each of 1,000 categories using all validation samples on ImageNet. On low or middle level SK units (e.g., SK\_2\_3, SK\_3\_4), 5x5 kernels are clearly imposed with more emphasis if the target object becomes larger (1.0x -> 1.5x).

More details of attention distributions on specific images are as follows:

If you use Selective Kernel Convolution in your research, please cite the paper:

@inproceedings{li2019selective,
  title={Selective Kernel Networks},
  author={Li, Xiang and Wang, Wenhai and Hu, Xiaolin and Yang, Jian},
  journal={IEEE Conference on Computer Vision and Pattern Recognition},
  year={2019}
}