My Paper Lib 2019

Author: zengzeyu

Date: 2019.01-2019.06

No. PAPER SOURCE
1 Visualizing the Loss Landscape of Neural Nets PDF/video/code
2 3D Backbone Network for 3D Object Detection PDF/video/code
3 PersonLab : Person Pose Estimation and Instance Segmentation with a Bottom-Up , Part-Based , Geometric Embedding Model PDF/video/code
4 DeeperLab : Single-Shot Image Parser PDF/video/code
5 Multi-Task Learning as Multi-Objective Optimization PDF/video/code
6 Rethinking on Multi-Stage Networks for Human Pose Estimation PDF/video/code
7 RePr: Improved Training of Convolutional Filters PDF/video/code
——— Date: 03-24 ———-
8 Group Normalization PDF/video/code
9 Weight Standardization PDF/video/code
10 Pruning Filters for Efficient ConvNets PDF/video/code
11 High Performance Convolutional Neural Networks for Document Processing PDF/video/code
12 Group normalization PDF/video/code
13 Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks(DCGAN) PDF/video/code
14 Generative Adversarial Networks(GAN) PDF/video/code
15 Adversarial Learning for Semi-Supervised Semantic Segmentation PDF/video/code
16 Wasserstein GAN PDF/video/code
17 FVNet: 3D Front-View Proposal Generation for Real-Time Object Detection from Point Clouds PDF/video/code
18 YOLOv3: An Incremental Improvement PDF/video/code
———- Date: 05-03 ———-
19 TextField: Learning A Deep Direction Field for Irregular Scene Text Detection PDF/video/code
20 PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud PDF/video/code
21 Deep learning on point clouds for 3D scene understanding PDF/video/code
22 YOLO9000: Better, faster, stronger PDF/video/code
23 LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving PDF/video/code
24 DEEP LEARNING ON POINT CLOUDS FOR 3D SCENE UNDERSTANDING(Ph.D Thesis) PDF/video/code
25 Multi-View 3D Object Detection Network for Autonomous Driving PDF/video/code
26 Deep 3d Representation Learning(Ph.D Thesis) PDF/video/code
———- Date: 06-29 ———- -