DeepLab: Deep Labelling for Semantic Image Segmentation
“DeepLab: Deep Labelling for Semantic Image Segmentation” is a state-of-the-art deep learning model from Google for sementic image segmentation task, where t...
Recent Posts
Gradient Acceleration in Activation Functions
“Gradient Acceleration in Activation Functions” argues that the dropout is not a regularizer but an optimization technique and propose better way to obtain t...
CBAM: Convolutional Block Attention Module
“CBAM: Convolutional Block Attention Module” proposes a simple and effective attention module for CNN which can be seen as descendant of Sqeeze and Excitatio...
Re-ID done right
“Re-ID done right: towards good practices for person re-identification” proposes a different approach to use deep network on person re-identification task. I...
DeepIR
“Deep image retrieval: learning global representations for image search” proposes an approach for instance-level image retrieval. It was presented in the ECC...
SENet
“Squeeze-and-Excitation Networks” suggests simple and powerful layer block to improve general convolutional neural network. It was presented in the conferenc...
Regularization and Optimization
This post is a summary and paper skimming on regularization and optimization. So, this post will be keep updating by the time.
Scale-Invariant Feature Transform (SIFT)
Scale-Invariant Feature Transform (SIFT) is an old algorithm presented in 2004, D.Lowe, University of British Columbia. However, it is one of the most famous...