- Session 5: Computer Vision -- Day 3 (Nov.19), poster session: 11:30-14:00, talks: 14:10-15:25 (5th floor Hall 1)
- Poster number: Tue25
- Download paper
Jiaming Zhou (Beihang University); Yuqiao Tian (Beihang University); Weicheng Li (Beihang University); Rui Wang (Beihang University); Zhongzhi Luan (Beihang University); Depei Qian (Beihang University)
Scale variation is one of the most significant challenges for object detection task. In comparison with previous one-stage object detectors that simply make feature pyramid network deeper without consideration of speed, we propose a novel one-stage object detector called LADet, which consists of two parts, Adaptive Feature Pyramid Module(AFPM) and Light-weight Classification Function Module(LCFM). Adaptive Feature Pyramid Module generates complementary semantic information for each level feature map by jointly utilizing multi-level feature maps from backbone network, which is different from the top-down manner. Light-weight Classification Function Module is able to exploit more type of anchor boxes without a dramatic increase of parameters because of the utilization of interleaved group convolution. Extensive experiments on PASCAL VOC and MS COCO benchmark demonstrate that our model achieves a better trade-off between accuracy and efficiency over the comparable state-of-the-art detection methods.