4/19/21 – 4/25/21
- Multi Task Learning: Soft parameter sharing vs Hard parameter sharing. Hard parameter sharing is preferred.
- Multi Task Learning with attention: See reference 1 below. Code is also available at: https://github.com/lorenmt/mtan
- https://shikun.io/projects/multi-task-attention-network (Project page)
- Object Detection: One stage (YOLO) versus 2 stage detectors (R-CNN based)
- Object detection: Labelling data
- Adding constraints in a deep learning framework
References
- (paper) End-to-End Multi-Task Learning with Attention – not yet read
- (paper) Multi-Task Deep Learning for Depth-based Person Perception in Mobile Robotics – not yet read
- (paper) QuadroNet: Multi-Task Learning for Real-Time Semantic Depth Aware Instance Segmentation – not yet read
- (paper) Learning to Segment Every Thing – partially read
- An Overview of Multi-Task Learning in Deep Neural Networks (blog/paper – read)
- (paper) A Hierarchical Multi-task Approach for Learning Embeddings from Semantic Tasks (introduces proportional sampling for MTL)
- (video) Integrating Constraints into Deep Learning Architectures with Structured Layers
- (paper) A Survey on Multi-Task Learning
- (MUST read paper for Multi Task Learning) Multitask Learning
4/12/2021 – 4/18/2021
- Ordinal labels in Machine Learning
- Multi Task Learning
- Transfer Learning
- Is Faster R-CNN an example of Multi Task Learning?
References
- (paper) A Multi-Task Learning Model for Better Representation of Clothing Images
- (thesis) Multi Task Learning in Computer Vision
- (paper) A multitask deep learning model for real-time deployment in embedded systems
- (paper) Tackling ordinal regression problem for heterogeneous data: sparse and deep multi-task learning approaches
4/5/2021 – 4/11/2021
- coco-annotator labelling tool: This week, I spent most of the time labelling data. It is possible to extract portion of the categories from the labelled data.
- Detectron2 training on a custom dataset
- Training SOLOv2 AdelaiDet on a custom dataset:
References
- Breakdown of Detecton2 trainer code
- How do I scale SOLVER.STEPS with SOLVER.MAX_ITER – Detectron2
- Roboflow blog on using the Detctron2 framework
3/29/2021 – 4/4/2021
- Scene Text Detection: There are generally two phases to it – Text Detection and Text Recognition.
- For Text detection, any available object detection model can be used. EAST is one of them. Others include, Faster R-CNN, YOLO, etc. Reference 2 reviews various methods
- For Text recognition, there are few methods available such as Tesseract. Reference 2 reviews various methods.
- Additionally, there are end to end systems also available.
- How to label data for Scene Text detection?
- COCO Text detection dataset. See reference 1 and Figure 1 below.
- COCO- annotation tool: This is a very easy to use tool to annotate images. I explored it this week and used it to annotate images.
References
- https://vision.cornell.edu/se3/coco-text-2/ – COCO Text detection annotation format
- Deep Learning Based OCR for Text in the Wild
- OpenCV OCR and text recognition with Tesseract – tutorial with code (EAST + Tesseract)
- (paper) ABCNet – end to end text spotting framework. ABCNet is an efficient end-to-end scene text spotting framework over 10x faster than previous state of the art. It’s published in IEEE Conf. Comp Vis Pattern Recogn.’2020 as an oral paper.
- CRAFT:
- How to use COCO annotator – video walkthrough