Open in app
Sign inGet started
Discrete Optimization: beyond REINFORCE

Discrete Optimization: beyond REINFORCE

Gumbel Softmax (a.k.a. Concrete distribution)
Go to the profile of Kevin Shen
Kevin Shen
Effect of batch size on training dynamics

Effect of batch size on training dynamics

This is a longer blogpost where I discuss results of experiments I ran myself.
Go to the profile of Kevin Shen
Kevin Shen
(PPS) DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and…

(PPS) DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and…

This paper deals with semantic segmentation: the task of labeling pixels in an image by their object classes. The goal of semantic…
Go to the profile of Kevin Shen
Kevin Shen
(PPS) Efficient Deep Learning for Stereo Matching

(PPS) Efficient Deep Learning for Stereo Matching

This is another paper on stereo matching: the task of matching pixels from two different pictures to deduce depth information. A common…
Go to the profile of Kevin Shen
Kevin Shen
(PPS) Dynamic Routing Between Capsules

(PPS) Dynamic Routing Between Capsules

Capsules is one of the recent works coming from Geoff Hinton which is why it’s so hyped up (I think an independent implementation came out…
Go to the profile of Kevin Shen
Kevin Shen
(PPS) Deformable Convolutional Networks

(PPS) Deformable Convolutional Networks

The basic idea of this paper is to give the convolution and pooling layers the ability to model different orientations and scales of…
Go to the profile of Kevin Shen
Kevin Shen
(PPS) Cascade Residual Learning: A Two-stage Convolutional Neural Network for Stereo Matching

(PPS) Cascade Residual Learning: A Two-stage Convolutional Neural Network for Stereo Matching

This paper tackles stereo matching which is the task of matching pixels from two images taken with two different cameras to deduce depth…
Go to the profile of Kevin Shen
Kevin Shen
About Mini DistillLatest StoriesArchiveAbout MediumTermsPrivacyTeams