paper-with-me

Papers

Feature Selective Networks for Object Detection

2017-11-24 · CVPR 2018 6 · Yao Zhai, Jingjing Fu, Yan Lu, Houqiang Li

Objects for detection usually have distinct characteristics in different sub-regions and different aspect ratios. However, in prevalent two-stage object detection methods, Region-of-Interest (RoI) features are extracted by RoI pooling with little emphasis on these translation-variant feature components. We present feature selective networks to reform the feature representations of RoIs by exploiting their disparities among sub-regions and aspect ratios. Our network produces the sub-region attention bank and aspect ratio attention bank for the whole image. The RoI-based sub-region attention map and aspect ratio attention map are selectively pooled from the banks, and then used to refine the original RoI features for RoI classification. Equipped with a light-weight detection subnetwork, our network gets a consistent boost in detection performance based on general ConvNet backbones (ResNet-101, GoogLeNet and VGG-16). Without bells and whistles, our detectors equipped with ResNet-101 achieve more than 3% mAP improvement compared to counterparts on PASCAL VOC 2007, PASCAL VOC 2012 and MS COCO datasets.

📄 PDF Abstract BibTeX arXiv:1711.08879

Code (0)

등록된 구현이 없습니다.

Tasks

Objectobject-detectionObject DetectionTranslation

Methods 이 논문이 사용한 방법론

1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Average Pooling 설명 없음
Local Response Normalization Local Response Normalization is a normalization layer that implements the idea of lateral inhibition. Lateral inhibition is a concept in neurobiology that refers to the…
Auxiliary Classifier Auxiliary Classifiers are type of architectural component that seek to improve the convergence of very deep networks. They are classifier heads we attach to layers before the…
Inception Module An Inception Module is an image model block that aims to approximate an optimal local sparse structure in a CNN. Put simply, it allows for us to use multiple types of filter…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Salient Structure Detection by Context-Guided Visual Search

2015-05-17 · Kai-Fu Yang, Hui Li, Chao-Yi Li, Yong-Jie Li

We define the task of salient structure (SS) detection to unify the saliency-related tasks like fixation prediction, salient object detection, and other detection of structures of interest. In this study, we propose a un…

Bayesian InferenceObjectobject-detectionObject Detection+3

Selective Multi-Scale Learning for Object Detection

2022-06-16 · Junliang Chen, Weizeng Lu, Linlin Shen

Pyramidal networks are standard methods for multi-scale object detection. Current researches on feature pyramid networks usually adopt layer connections to collect features from certain levels of the feature hierarchy, a…

Objectobject-detectionObject Detection

SPOT: Selective Point Cloud Voting for Better Proposal in Point Cloud Object Detection

2020-08-01 · ECCV 2020 8 · Hongyuan Du, Linjun Li, Bo Liu, Nuno Vasconcelos

The sparsity of point clouds limits deep learning models on capturing long-range dependencies, which makes features extracted by the models ambiguous. In point cloud object detection, ambiguous features make it hard for …

DiversityObjectobject-detectionObject Detection

Keypoint Density-based Region Proposal for Fine-Grained Object Detection and Classification using Regions with Convolutional Neural Network Features

2016-03-01 · JT Turner, Kalyan Gupta, Brendan Morris, David W. Aha

Although recent advances in regional Convolutional Neural Networks (CNNs) enable them to outperform conventional techniques on standard object detection and classification tasks, their response time is still slow for rea…

ClassificationGeneral ClassificationObjectobject-detection+2

Selective Transfer Learning of Cross-Modality Distillation for Monocular 3D Object Detection

2026-03-08 · Rui Ding, Meng Yang, Nanning Zheng arxiv

Monocular 3D object detection is a promising yet ill-posed task for autonomous vehicles due to the lack of accurate depth information. Cross-modality knowledge distillation could effectively transfer depth information fr…

Monocular 3D Object DetectionKnowledge DistillationAutonomous VehiclesTransfer Learning