5 papers
Orthogonal Projection Loss
Kanchana Ranasinghe, Muzammal Naseer, Munawar Hayat +2
Deep neural networks have achieved remarkable performance on a range of classification tasks, with softmax cross-entropy (CE) loss emerging as the de-facto objective function. The…
Conditional Generative Modeling via Learning the Latent Space
Sameera Ramasinghe, Kanchana Ranasinghe, Salman Khan +2
Although deep learning has achieved appealing results on several machine learning tasks, most of the models are deterministic at inference, limiting their application to single-mod…
Extending Multi-Object Tracking systems to better exploit appearance and 3D information
Kanchana Ranasinghe, Sahan Liyanaarachchi, Harsha Ranasinghe +1
Tracking multiple objects in real time is essential for a variety of real-world applications, with self-driving industry being at the foremost. This work involves exploiting tempor…
Bipartite Conditional Random Fields for Panoptic Segmentation
Sadeep Jayasumana, Kanchana Ranasinghe, Mayuka Jayawardhana +2
We tackle the panoptic segmentation problem with a conditional random field (CRF) model. Panoptic segmentation involves assigning a semantic label and an instance label to each pix…
Combined Static and Motion Features for Deep-Networks Based Activity Recognition in Videos
Sameera Ramasinghe, Jathushan Rajasegaran, Vinoj Jayasundara +3
Activity recognition in videos in a deep-learning setting---or otherwise---uses both static and pre-computed motion components. The method of combining the two components, whilst k…