Shape-Adaptive Kernel Network for Dense Object Detection

Shape-Adaptive Kernel Network for Dense Object Detection
김익재Hanjae KimSunghun JoungKwanghoon Sohn
Dense object detection; dynamic kernel; single stage object detection; object deformation
Issue Date
International Conference on Image Processing
Dense object detectors that are applied over a regular, dense grid have advanced and drawn their attention in recent days. Their fully convolutional nature greatly advances the computational efficiency of object detectors compared to the two-stage detectors. However, the lack of the ability to adjust shape variation on a regular grid is still limited. In this paper we introduce a new framework, shape-adaptive kernel network, to handle spatial manipulation of input data in convolutional kernel space. At the heart of out approach is to align the original kernel space recovering shape variation of each input feature on regular grid. To this end, we propose a shape-adaptive kernel sampler to adjust dynamic convolutional kernel conditioned on input. To increase the flexibility of geometric transformation, a cascade refinement module is designed, which first estimates the global transformation grid and then estimates local offset in convolutional kernel space. Our experiments demonstrate the effectiveness of the shape-adaptive kernel network for dense object detection on various benchmarks.
Appears in Collections:
KIST Publication > Conference Paper
Files in This Item:
There are no files associated with this item.
RIS (EndNote)
XLS (Excel)


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.