Home

Awesome

Efficient Decoder-free Object Detection with Transformers

image

ECCV2022: Paper

This code is based on mmdetection

Results

Backbonebox mAPGFLOPs
$DFFT_{NANO}$42.842
$DFFT_{TINY}$43.557
$DFFT_{SMALL}$44.562
$DFFT_{MEDIUM}$45.767
$DFFT_{LARGE}$46.0101

Models

ImageNet Pretrained

MS COCO Detection

Runs

python3 setup.py develop && ./tools/dist_train.sh configs/dfft/dfft.py [num_gpus] \
--cfg-options model.pretrained=pretrained.pth