Home

Info Title: Rethinking the Inception Architecture for Computer Vision Author: C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna Arxiv: 1512.00567 Date: Dec. 2015 Highlights & Drawbacks This article is the author’s step 2.5 to advance the inception structure. In an earlier article, the same author proposed Batch Normaliz...

Info Title: YOLO9000: Better, Faster, Stronger Task: Object Detection Author: J. Redmon and A. Farhadi Arxiv: 1612.08242 Date: Dec. 2016 Highlights & Drawbacks A significant improvement for YOLO. Motivation & Design Add BN to the convolutional layer and discard Dropout Higher size input Use Anchor Boxes and replac...

Info Title: ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design Task: Image Classification Author: N. Ma, X. Zhang, H.-T. Zheng, and J. Sun Date: Jul. 2018 Arxiv: 1807.11164 Published: ECCV 2018 Highlights & Drawbacks Detailed analysis from hardware perspective Design guidelines for efficient CNN arc...

Info Title: Speed/accuracy trade-offs for modern convolutional object detectors Task: Object Detection Author: Jonathan Huang, Vivek Rathod, et al. Arxiv: 1611.10012 Date: Nov. 2016 Published: CVPR 2017 Highlights & Drawbacks This article is an empirical study. The feature extraction network is separated as a component of ...

Info Title: Feature Pyramid Networks for Object Detection Task: Object Detection Author: Tsung-Yi Lin, Piotr Dollár, Ross Girshick, Kaiming He, Bharath Hariharan, Serge Belongie Date: March 2016 Arxiv: 1612.03144 Published: CVPR 2017 Highlights Image pyramid to feature pyramid Motivation & Design The understanding of ...

Info Title: Training Region-based Object Detectors with Online Hard Example Mining Task: Object Detection Author: A. Shrivastava, A. Gupta, and R. Girshick Date: Apr. 2016 Arxiv: 1604.03540 Published: CVPR 2016 Highlights & Drawbacks Learning-based design for balancing examples for ROI in 2-stage detection network Plug-in...

Info Title: Focal loss for dense object detection Task: Object Detection Author: T. Lin, P. Goyal, R. B. Girshick, K. He, and P. Dollár Date: Aug. 2017 Arxiv: 1708.02002 Published: ICCV 2017(Best Student Paper) Highlights & Drawbacks Loss function improvement For Dense samples from single-stage models like SSD Motiv...

Info Title: Xception: Deep Learning with Depthwise Seperable Convolutions Author: F. Chollet Arxiv: 1610.02357 Date: Oct. 2016 Highlights & Drawbacks Replaced 1×1 convolution and 3×3 convolution in Inception unit with Depth-wise seperable convolution Motivation & Design The article points out that the assumption behind the...