Hanjae Kim Sunghun Joung KIM, IG JAE Kwanghoon Sohn 2024-01-12T04:10:22Z 2024-01-12T04:10:22Z 2021-09-29 2020-09 1522-4880 https://pubs.kist.re.kr/handle/201004/77869 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. English IEEE 객체 검출 딥러닝 SHAPE-ADAPTIVE KERNEL NETWORK FOR DENSE OBJECT DETECTION Conference 10.1109/ICIP40778.2020.9190767 1 IEEE International Conference on Image Processing (ICIP), pp.2046 - 2050 IEEE International Conference on Image Processing (ICIP) 2046 2050 US 2020-09-25 2020 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) 000646178502031 2-s2.0-85098641446