2018/11/27 by Xizhou Zhu, Han Hu, Zhu, Xizhou +5 · 182 citations
Computer Science · #Advanced Neural Network Applications #Artificial intelligence #Artificial neural network #Benchmark (surveying) #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Computer vision #Convolution (computer science) #Convolutional neural network #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Feature (linguistics) #Feature extraction #Focus (optics) #Image (mathematics) #Multimodal Machine Learning Applications #Object (grammar) #Object detection #Pattern recognition (psychology) #Segmentation #cs.CV
paper · pdf · doi:10.48550/arxiv.1811.11168
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2018/11/27 · arxiv created 2018/11/28 · arxiv updated 2018/11/29 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/06
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. To address this problem, we present a reformulation of Deformable ConvNets that improves its ability to focus on pertinent image regions, through increased modeling power and stronger training. The modeling power is enhanced through a more comprehensive integration of deformable convolution within the network, and by introducing a modulation mechanism that expands the scope of deformation modeling. To effectively harness this enriched modeling capability, we guide network training via a proposed feature mimicking scheme that helps the network to learn features that reflect the object focus and classification power of R-CNN features. With the proposed contributions, this new version of Deformable ConvNets yields significant performance gains over the original model and produces leading results on the COCO benchmark for object detection and instance segmentation.