Mini Project #1
Mini Project #2 Use Google’s deeplab v3++ to segment (semantic) MSCOCO database, obtain same/similar results with the state of the art, and modify the algorithm according to your own creativeness to improve the results via efficiency, accuracy, or both.
- Mini-project #2 (20%) Implement the following paper
Title: "Self-Supervised Representation Learning by Rotation Feature Decoupling" Authors: Zeyu Feng, Chang Xu, Dacheng Tao Institution: UBTECH Sydney AI Centre, School of Computer Science, FEIT, University of Sydney, Australia Code: https://github.com/philiptheother/FeatureDecoupling (Links to an external site.) Link: pdf and supp (Links to an external site.)
After reproducing the paper with the available code, consider this method as baseline, now try to improve the method with your creativity.Contributions can be as little as making the network deeper to changing the architecture using dense modules etc. or it can be novelties in the method itself (how to deal with rotations etc which are mentioned in the paper).
Final Project #1
Open images 2019 – visual relationship (detect pair of objects in particular relationship)
https://www.kaggle.com/c/open-images-2019-visual-relationship (Links to an external site.)
Open Images (Links to an external site.) is a collaborative release of ~9 million images annotated with image-level labels, object bounding boxes, object segmentation masks, and visual relationships. This uniquely large and diverse dataset is designed to spur state of the art advances in analyzing and understanding images. This year’s Open Images V5 (Links to an external site.) release enabled the second Open Images Challenge (Links to an external site.) to include the 3 tracks, you are supposed to work on Visual relationship detection track (Links to an external site.) for detecting pairs of objects in particular relations, also relaunched from 2018.