1. 程式人生 > >2016CVPR目標檢測論文簡介

2016CVPR目標檢測論文簡介

目標檢測的指標:

1)識別精度
2)識別效率
3)定位準確性

CVPR2016專題:

這裡寫圖片描述

CVPR/ICCV目標檢測最新論文

2016年的CVPR目標檢測(這裡討論的是2D的目標檢測)的方法主要是
基於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.

  1. Deep Residual Learning for Image Recognition
    這是kaiming組那篇影響力很大的文章,不用說了

  2. You Only Look Once: Unified, Real-Time Object Detection
    YOLO用純CNN來做檢測,可以達到實時的效果,雖然今年SSD的效果做的好很多,但YOLO確實起到了先驅的作用。

  3. Training Region-Based Object Detectors With Online Hard Example Mining
    這個工作比較新,他提供了在F-RCNN的框架下,在訓練過程中如何對樣本進行選擇的一種解決方案。而且確實work。

  4. Accurate Image Super-Resolution Using Very Deep Convolutional Networks
    這是做超解析度重建的一篇文章,主要的創新點在於在網路的最後用原圖來輔助重建,有點殘差網的意思,當然效果也很好。

  5. Inside-Outside Net: Detecting Objects in Context With Skip Pooling and Recurrent Neural Networks
    在F-RCNN的框架下如何對特徵進行增強,文章主要考慮了multi-layer fusion和context資訊。

  6. HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection
    通過對CNN的多層特徵進行融合提高定位準確性,利用類似於Faster-RCNN的方式進行目標檢測

  7. Exploit All the Layers: Fast and Accurate CNN Object Detector With Scale Dependent Pooling and Cascaded Rejection Classifiers.
    通過在CNN的多層建立級聯分類器來抑制負樣本(在目標檢測中對負樣本進行合理抑制起到了關鍵作用)