Official implementation of Scale Adaptive Network (SAN) as described in Learning to Learn Parameterized Classification Networks for Scalable Input Images (ECCV'20) by Duo Li, Anbang Yao and Qifeng Chen on the ILSVRC 2012 benchmark.

We present a meta learning framework which dynamically parameterizes main networks conditioned on its input resolution at runtime, leading to efficient and flexible inference for arbitrarily switchable input resolutions.

• PyTorch 1.0+
• NVIDIA-DALI (in development, not recommended)

Download the ImageNet dataset and move validation images to labeled subfolders. To do this, you can use the following script: https://raw.githubusercontent.com/soumith/imagenetloader.torch/master/valprep.sh

Please visit my repository mobilenetv2.pytorch.

python imagenet.py \
    -a meta_resnet18/50 \
    -d <path-to-ILSVRC2012-data> \
    --epochs 120 \
    --lr-decay cos \
    -c <path-to-save-checkpoints> \
    --sizes <list-of-input-resolutions> \ # default is 224, 192, 160, 128, 96
    -j <num-workers>
    --kd

python imagenet.py \
    -a meta_mobilenetv2 \
    -d <path-to-ILSVRC2012-data> \
    --epochs 150 \
    --lr-decay cos \
    --lr 0.05 \
    --wd 4e-5 \
    -c <path-to-save-checkpoints> \
    --sizes <list-of-input-resolutions> \ # default is 224, 192, 160, 128, 96
    -j <num-workers>
    --kd

python imagenet.py \
    -a <arch> \
    -d <path-to-ILSVRC2012-data> \
    --resume <checkpoint-file> \
    --sizes <list-of-input-resolutions> \
    -e
    -j <num-workers>

Arguments are:

• checkpoint-file: previously downloaded checkpoint file from here.
• list-of-input-resolutions: test resolutions using different privatized BNs.

which gives Table 1 in the main paper and Table 5 in the supplementary materials.

Manually set the scale encoding here, which gives the left panel of Table 2 in the main paper.

Uncomment this line in the main script to enable post-hoc BN calibration, which gives the middle panel of Table 2 in the main paper.

Manually set the scale encoding here and its corresponding shift here, then uncomment this line to replace its above line, which gives Table 6 in the supplementary materials.

If you find our work useful in your research, please consider citing:

@InProceedings{Li_2020_ECCV,
author = {Li, Duo and Yao, Anbang and Chen, Qifeng},
title = {Learning to Learn Parameterized Classification Networks for Scalable Input Images},
booktitle = {The European Conference on Computer Vision (ECCV)},
month = {August},
year = {2020}
}