您的位置:首页 > 其它

2016CVPR目标检测论文简介

2016-10-24 13:09 961 查看

目标检测的指标:

1)识别精度

2)识别效率

3)定位准确性

CVPR2016专题:



CVPR/ICCV目标检测最新论文

2016年的CVPR目标检测(这里讨论的是2D的目标检测)的方法主要是

基于CNN的框架,代表性的工作有

ResNet[1](Kaiming He等)、

YOLO[5](Joseph Redmon等)、

LocNet[7](Spyros Gidaris等)、

HyperNet[3](Tao Kong等)、

ION[2](Sean Bell等)、

G-CNN[6](Mahyar Najibi等)。

[1] He K, Zhang X, Ren S, et al. Deep residual learning for image recognition. In CVPR 2016

[2] Bell S, Zitnick C L, Bala K, et al. Inside-outside net: Detecting objects in context with skip pooling and recurrent neural networks. In CVPR 2016

[3] Kong T, Yao A, Chen Y, et al. HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection. In CVPR 2016

[4] Cheng M M, Zhang Z, Lin W Y, et al. BING: Binarized normed gradients for objectness estimation at 300fps. In CVPR 2014

[5] Redmon J, Divvala S, Girshick R, et al. You only look once: Unified, real-time object detection. In CVPR 2016

[6] Najibi M, Rastegari M, Davis L S. G-CNN: an Iterative Grid Based Object Detector. In CVPR 2016

[7] Gidaris S, Komodakis N. LocNet: Improving Localization Accuracy for Object Detection. In CVPR 2016

[8] Shrivastava A, Gupta A, Girshick R. Training region-based object detectors with online hard example mining. In CVPR 2016

[9] Girshick R. Fast R-CNN. In ICCV 2015

[10] Ren S, He K, Girshick R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks. In NIPS 2015

[11] Liu W, Anguelov D, Erhan D, et al. SSD: Single Shot MultiBox Detector[J]. arXiv preprint arXiv:1512.02325, 2015.

Deep Residual Learning for Image Recognition

这是kaiming组那篇影响力很大的文章,不用说了

You Only Look Once: Unified, Real-Time Object Detection

YOLO用纯CNN来做检测,可以达到实时的效果,虽然今年SSD的效果做的好很多,但YOLO确实起到了先驱的作用。

Training Region-Based Object Detectors With Online Hard Example Mining

这个工作比较新,他提供了在F-RCNN的框架下,在训练过程中如何对样本进行选择的一种解决方案。而且确实work。

Accurate Image Super-Resolution Using Very Deep Convolutional Networks

这是做超分辨率重建的一篇文章,主要的创新点在于在网络的最后用原图来辅助重建,有点残差网的意思,当然效果也很好。

Inside-Outside Net: Detecting Objects in Context With Skip Pooling and Recurrent Neural Networks

在F-RCNN的框架下如何对特征进行增强,文章主要考虑了multi-layer fusion和context信息。

HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection

通过对CNN的多层特征进行融合提高定位准确性,利用类似于Faster-RCNN的方式进行目标检测

Exploit All the Layers: Fast and Accurate CNN Object Detector With Scale Dependent Pooling and Cascaded Rejection Classifiers.

通过在CNN的多层建立级联分类器来抑制负样本(在目标检测中对负样本进行合理抑制起到了关键作用)
内容来自用户分享和网络整理,不保证内容的准确性,如有侵权内容,可联系管理员处理 点击这里给我发消息
标签: