Home

Info Title: Fast RCNN Task: Object Detection Author: Ross Girshick Arxiv: 1504.08083 Date: April 2015 Published: ICCV 2015 Highlights An improvement to [R-CNN] (https://blog.ddlee.cn/posts/415f4992/), ROI Pooling Design Article structure is clear Motivation & Design R-CNN’s Drawbacks Training is a multi-stage proc...

Info Title: R-FCN: Object Detection via Region-based Fully Convolutional Networks Task: Object Detection Author: Jifeng Dai, Yi Li, Kaiming He, and Jian Sun Arxiv: 1605.06409 Published: NIPS 2016 Highlights Full convolutional network, sharing weights across ROIs Motivation & Design The article points out that there is an un...

Info Title: Towards Instance-level Image-to-Image Translation Task: Image Translation Author: Zhiqiang Shen, Mingyang Huang, Jianping Shi, Xiangyang Xue, Thomas Huang Date: May 2019 Arxiv: 1905.01744 Published: CVPR 2019 Highlights & Drawbacks The instance-level objective loss can help learn a more accurate reconstruction a...

Info Title: DSOD: learning deeply supervised object detectors from scratch Task: Object Detection Author: Z. Shen, Z. Liu, J. Li, Y. Jiang, Y. Chen, and X. Xue Date: Aug. 2017 Arxiv: 1708.01241 Published: ICCV 2017 Highlights & Drawbacks Object Detection without pre-training DenseNet-like network Motivation & Desi...

Info Title: On-the-fly Operation Batching in Dynamic Computation Graphs Author: Graham Neubig, Yoav Goldberg, Chris Dyer Arxiv: 1705.07860 Date: May. 2017 Highlights & Drawbacks Batch computation on dynamic graph Motivation & Design Dynamic learning-based deep learning frameworks such as Pytorch, DyNet provide a more flexibl...

Info Title: GlyphGAN: Style-Consistent Font Generation Based on Generative Adversarial Networks Task: Font Generation Author: H. Hayashi, K. Abe, and S. Uchida Date: May 2019 Arxiv: 1905.12502 Highlights & Drawbacks Two encode vectors for character and style, respectively Motivation & Design The main frame work is a D...

Info Title: SNIPER: efficient multi-scale training Task: Object Detection Author: B. Singh, M. Najibi, and L. S. Davis Date: May 2018 Arxiv: 1805.09300 Published: NIPS 2018 Highlights & Drawbacks Efficient version of SNIP training strategy for object detection Select ROIs with proper size only inside a batch Motivatio...

Info Title: An analysis of scale invariance in object detection - SNIP Task: Object Detection Author: B. Singh and L. S. Davis Date: Nov. 2017 Arxiv: 1711.08189 Published: CVPR 2018 Highlights & Drawbacks Training strategy optimization, ready to integrate with other tricks Informing experiments for multi-scale training tr...

Info Title: Densely Connected Convolutional Network Task: Image Classification Author: Gao Huang, Zhuang Liu, Laurens van der Maaten and Kilian Weinberger Arxiv: 1608.06993 Published: CVPR 2017(Best Paper Award) Highlights DenseNet takes the idea of ​​shortcut-connection to its fullest. Inside a DenseBlock, the output of each layer...

Info Title: Aggregated Residual Transformations for Deep Neural Networks Task: Image Classification Author: S. Xie, R. Girshick, P. Dollár, Z. Tu, and K. H Arxiv: 1611.05431 Date: Nov. 2016 Published: CVPR 2017 1st Runner Up in ILSVRC 2016 Highlights & Drawbacks The core idea of ResNeXt is normalizing the multi-path structur...