Multi-scale Location-Aware Kernel Representation for Object Detection

By Hao Wang, Qilong Wang, Mingqi Gao, P. Li, Wangmeng Zuo. 2018

71 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Bridging the Gap Between Anchor-Based and Anchor-Free Detection via Adaptive Training Sample Selection (2019, methodology): “Method Data Backbone AP AP50 AP75 APS APM APL anchor-based two-stage: MLKP [58] trainval35 ResNet-101 28.”
Deep High-Resolution Representation Learning for Visual Recognition (2019, neutral): “MLKP [142] VGG16 28.”
Deep Regionlets for Object Detection (2017, methodology): “ing superior performance over state-of-the-art. 2. Related Work Many approaches have been proposed for object detection including both traditional ones [13, 47, 45] and deep learning-based approaches [17, 40, 31, 38, 8, 16, 19, 9, 35, 6, 21, 55, 56, 54, 52, 46, 44]. Traditional approaches mainly use”
Recent Advances in Deep Learning for Object Detection (2019, background): “938 proposed a novel framework Multi-scale Location-aware Kernel 939 Representation (MLKP) [103] which captured high-order statistics 940 of proposal features and generated more discriminative feature 941 representations efficiently.”
Deep Learning on Image Denoising: An overview (2019, background): “, VGG [189] and GoogLeNet [196]) were widely applied in the fields of image [225, 217, 119], video [138, 248], nature language processing [52] and speech processing [267], especially low-level computer vision [169, 204].”
High-Resolution Representations for Labeling Pixels and Regions (2019, unknown): “MLKP [98] VGG16 - 28.”
Global Second-Order Pooling Convolutional Networks (2018, unknown): “The global second-order pooling1 (GSoP), producing covariance matrices as image representations, has achieved state-of-the-art results in a variety of vision tasks [22, 3, 33, 36] such as object recognition, finegrained visual categorization, object detection and video classification.”
Deep Learning for Generic Object Detection: A Survey (2018, background): “代表的な手法として,SharpMask [214], Deconvolutional Single Shot Detector (DSSD) [77], Feature Pyramid Network (FPN) [167], Top Down Modulation (TDM) [247], Reverse connection with Objectness prior Network (RON) [136], ZIP [156], Scale Transfer Detection Network (STDN) [321], RefineDet [308], StairNet [283], ”
Attention-guided CNN for image denoising (2020, methodology): “[49] used higher-order statistics to direct the deep network to improve the performance and efficiency of object detection.”