Last year in 2018, I took couple of online courses to get me upto speed to the recent advances made in field of Deep learning.
Since, I was primarily interested in application of Deep learning, I picked Computer vision as a domain to apply these techniques. Deep application has numerous application like Text, Speech etc.
While taking these courses, I had the opportunity to read many papers published in this field from 2013. They varied from
- Deep learning vanilla architecture,
- Application of Computer vision in
- classification
- Detection,
- Segmentation.
You can find the list of Papers I read here
Computer Vision Paper Reading
List of papers read un/read
- [x] Traffic Sign Recognition using Multi-scale convolution network
- [ ] Detecting Small Signs from Large Images
- [x] End to End Learning for Self Driving Cars
- [x] DeepPose: Human Pose Estimation via Deep Neural Networks
- [ ] OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
- [x] R-CNN: Rich feature hierarchies for accurate object detection and semantic segmentation
Vanial Architecture
- [x] Network In Network
- [x] AlexNet: ImageNet Classification with Deep Convolutional Neural Networks
- [x] ZfNet: Visualizing and Understanding Convolutional Networks
- [x] VggNet: Very Deep Convolutional Networks for Large-Scale Image Recognition
- [x] ResNet: Deep Residual Learning for Image Recognition
- [x] GoogLenet v1 Going Deeper with Convolutions
- [x] Inception v3: Rethinking the Inception Architecture for Computer Vision
- [x] Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
- [x] Densely Connected Convolutional Networks
- [x] Fast R-CNN
- [ ] Region of Intertest Pooling
- [x] Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- [x] You Only Look Once:
Unified, Real-Time Object Detection
Detection Task
- [x] MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- [x] SSD: Single Shot MultiBox Detector
Segmentation
- [x] Semnatic Segmentation
- [ ] A Review on Deep Learning Techniques
Applied to Semantic Segmentation - [x] Fully Convolutional Networks for Semantic Segmentation
- [x] Learning Deconvolution Network for Semantic Segmentation
- [ ] A Review on Deep Learning Techniques
Applied to Semantic Segmentation - [ ] Simultaneous Detection and Segmentation
- [ ] Hypercolumns for Object Segmentation and Fine-grained Localization
- [ ] Convolutional Feature Masking for Joint Object and Stuff Segmentation
- [x] Instanse Segmentation
- [x] Instance-aware Semantic Segmentation via Multi-task Network Cascades
- [x] U-Net: Convolutional Networks for Biomedical Image Segmentation
- [x] Show and Tell: A Neural Image Caption Generator
Autonomous Driving
- [ ] Toward Low-Flying Autonomous MAV Trail Navigation using Deep Neural Networks for Environmental Awareness
- [x] Pushing the “Speed Limit”: High-Accuracy U.S. Traffic Sign Recognition with Convolutional Neural Networks
There are still many papers to read in domain of Unsupervised learning. Keep reading.