Multi-scale Location-aware Kernel Representation for Object Detection
arXiv:1804.00428
Abstract
Although Faster R-CNN and its variants have shown promising performance in object detection, they only exploit simple first-order representation of object proposals for final classification and regression. Recent classification methods demonstrate that the integration of high-order statistics into deep convolutional neural networks can achieve impressive improvement, but their goal is to model whole images by discarding location information so that they cannot be directly adopted to object detection. In this paper, we make an attempt to exploit high-order statistics in object detection, aiming at generating more discriminative representations for proposals to enhance the performance of detectors. To this end, we propose a novel Multi-scale Location-aware Kernel Representation (MLKP) to capture high-order statistics of deep features in proposals. Our MLKP can be efficiently computed on a modified multi-scale feature map using a low-dimensional polynomial kernel approximation.Moreover, different from existing orderless global representations based on high-order statistics, our proposed MLKP is location retentive and sensitive so that it can be flexibly adopted to object detection. Through integrating into Faster R-CNN schema, the proposed MLKP achieves very competitive performance with state-of-the-art methods, and improves Faster R-CNN by 4.9% (mAP), 4.7% (mAP) and 5.0% (AP at IOU=[0.5:0.05:0.95]) on PASCAL VOC 2007, VOC 2012 and MS COCO benchmarks, respectively. Code is available at: https://github.com/Hwang64/MLKP.
arXiv commentAccepted by CVPR2018
References in corpus (14)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Deep Residual Learning for Image Recognition
- Caffe: Convolutional Architecture for Fast Feature Embedding
- R-FCN: Object Detection via Region-based Fully Convolutional Networks
- DSSD : Deconvolutional Single Shot Detector
- Rich feature hierarchies for accurate object detection and semantic segmentation
- Feature Pyramid Networks for Object Detection
- YOLO9000: Better, Faster, Stronger
- Beyond Skip Connections: Top-Down Modulation for Object Detection
- Speed/accuracy trade-offs for modern convolutional object detectors
- DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving
- HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection
- Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks
- Is Second-order Information Helpful for Large-scale Visual Recognition?