Deformable ConvNets v2: More Deformable, Better Results

CVPR 2019 Xizhou ZhuHan HuStephen LinJifeng Dai

The superior performance of Deformable Convolutional Networks arises from its ability to adapt to the geometric variations of objects. Through an examination of its adaptive behavior, we observe that while the spatial support for its neural features conforms more closely than regular ConvNets to object structure, this support may nevertheless extend well beyond the region of interest, causing features to be influenced by irrelevant image content... (read more)

PDF Abstract

Evaluation results from the paper


Task Dataset Model Metric name Metric value Global rank Compare
Object Detection COCO Deform-v2 Bounding Box AP 46.0 # 5