31 citations · 35 across the 4 of their papers we have counts for
6 papers
Sparse Pose Trajectory Completion
Bo Liu, Mandar Dixit, Roland Kwitt +2
We propose a method to learn, even using a dataset where objects appear only in sparsely sampled views (e.g. Pix3D), the ability to synthesize a pose trajectory for an arbitrary re…
Connectivity-Optimized Representation Learning via Persistent Homology
Christoph Hofer, Roland Kwitt, Mandar Dixit +1
We study the problem of learning representations with controllable connectivity properties. This is beneficial in situations when the imposed structure can be leveraged upstream. I…
Semantic Fisher Scores for Task Transfer: Using Objects to Classify Scenes
Mandar Dixit, Yunsheng Li, Nuno Vasconcelos
The transfer of a neural network (CNN) trained to recognize objects to the task of scene classification is considered. A Bag-of-Semantics (BoS) representation is first induced, by…
Feature Space Transfer for Data Augmentation
Bo Liu, Xudong Wang, Mandar Dixit +2
The problem of data augmentation in feature space is considered. A new architecture, denoted the FeATure TransfEr Network (FATTEN), is proposed for the modeling of feature trajecto…
AGA: Attribute Guided Augmentation
Mandar Dixit, Roland Kwitt, Marc Niethammer +1
We consider the problem of data augmentation, i.e., generating artificial samples to extend a given corpus of training data. Specifically, we propose attributed-guided augmentation…
Semantic Clustering for Robust Fine-Grained Scene Recognition
Marian George, Mandar Dixit, Gábor Zogg +1
In domain generalization, the knowledge learnt from one or multiple source domains is transferred to an unseen target domain. In this work, we propose a novel domain generalization…