Deep Learning Paper Reading Notes

creation date: 2018-01-11, latest update: 2020-06-17

Background

Based on Awesome Deep Learning Papers plus my own addition of literature summary

Famous Machine Learning Conferences

Famous Challenges / Dataset

list: https://competitions.codalab.org/

Activity Monitoring / Recognition

Human Related

Baby Related

Depth Estimation

Depth Fusion

RGB-D data and its usage

6D pose estimation

Others

Grasping

Dataset

Papers

Body pose estimation

Dataset

big list of both body and hand dataset

Papers

===================================================================

Hand pose estimation

The most challenging part about this is not the architecture, but the lack of large, clean, public dataset.

Dataset

list of more datasets here

Hand Papers

Most of the papers use Depth-only or RGB+D data to estimate hand-pose... It is probably possible to convert RGB to depth with another model, but it might be even slower.

Anomaly Detection (Images / Videos)

Anomaly Detection (Time Series)

Generative Adversarial Networks (GANs)

Style Transfers

Understanding / Generalization / Transfer

Optimization / Training Techniques

Unsupervised / Generative Models

CNN Feature Extractors

Image: Object Detection

Image: Segmentation

Image / Video / Etc

Natural Language Processing / RNNs

Speech / Other Domain

Reinforcement Learning / Robotics

Credit card fraud detection

Weather Classification

There are no agreed upon public dataset and very few DL papers dedicated to the topic.

The common dataset used is (2014) sunny/cloudy dataset with 10k images. Other recent papers (2018) have contructed their own dataset which are not opened to public yet. However, BDD100K dataset also has weather attribute labeled, so we should consider using that.

There are 3 type of models proposed thus far.

  1. (2014) traditional feature engineering then use SVM/other clustering methods.
  2. (2015) pure CNN feature extraction then classify
  3. (2018) CNN-RNN and/or the combination of DL and traditional features.

so far the DL method did out-perform traditional ones.

New alternative would be to add new sensor data (temperature/humidity) and ensemble with CNN model. For that matter, how accurate would predictions from sensor data alone be?

Autonomous Driving

Face Detection

Own discovery of Research Papers

Other papers still unassorted

Articles and Videos

Classic Paperspublished before 2012

HW / SW / Dataset

Book / Survey / Review

Video Lectures / Tutorials / Blogs

(Lectures)

(Tutorials)

(Blogs)