Home

Info Title: Mocycle-GAN: Unpaired Video-to-Video Translation Task: Video-to-Video Translation Author: Yang Chen, Yingwei Pan, Ting Yao, Xinmei Tian and Tao Mei Date: Aug. 2019 Arxiv: 1908.09514 Published: ACM MM 2019 Affiliation: USTC! Abstract Unsupervised image-to-image translation is the task of translating an image from on...

Focal Loss for Object Detection: Idea The loss function is reshaped to down-weight easy examples and thus focus training on hard negatives. A modulating factor (1-pt)^ γ is added to the cross entropy loss where γ is tested from [0,5] in the experiment. There are two properties of the FL: When an example is misclassified and pt is sm...

Info Title: Video Generation from Single Semantic Label Map Task: Video Generation Author: Junting Pan, Chengyu Wang, Xu Jia, Jing Shao, Lu Sheng, Junjie Yan, and Xiaogang Wang Date: Mar. 2019 Arxiv: 1903.04480 Published: CVPR 2019 Abstract This paper proposes the novel task of video generation conditioned on a SINGLE semantic l...

Deformable Convolution: Idea Deformable convolution consists of 2 parts: regular conv. layer and another conv. layer to learn 2D offset for each input. In this diagram, the regular conv. layer is fed in the blue squares instead of the green squares. If you are confused (like I was), you can think of deformable convolution as a “learnable...

Info Title: U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation Task: Image-to-Image Translation Author: Junho Kim, Minjae Kim, Hyeonwoo Kang, Kwanghee Le Date: July. 2019 Arxiv: 1907.10830 Highlights & Drawbacks Where earlier image-to-image translatio...

Non-maximum suppression(NMS): Idea Non-maximum suppression (NMS) solves this problem by clustering proposals by spatial closeness measured with IoU and keeping only the most confident proposals among each cluster. Algorithm and Soft NMS The proposal is rejected if the IoU crosses the threshold. The problem occurs when highly confident pro...

Info Title: Recycle-GAN: Unsupervised Video Retargeting Task: Video-to-Video Translation Author: Aayush Bansal, Shugao Ma, Deva Ramanan, and Yaser Sheikh Arxiv: 1808.05174 Published: ECCV 2018 Highlights Introduce a new approach that incorporates spatiotemporal cues with conditional generative adversarial networks for video retarg...

FPN is a simple but powerful design for mix the low-level and high-level features in object detector. Its main arch is as follows: Bottom-Up Pathway The bottom-up pathway is the feedforward computation of the backbone ConvNet. It is defined that one pyramid level is for each stage. The output of the last layer of each stage will be used a...