Search Results for author:
Found 7 papers, 2 papers with code
BACS: Background Aware Continual Semantic Segmentation
Besides the common problem of classical catastrophic forgetting in the continual learning setting, CSS suffers from the inherent ambiguity of the background, a phenomenon we refer to as the "background shift'', since pixels labeled as background could correspond to future classes (forward background shift) or previous classes (backward background shift).
Layerwise Early Stopping for Test Time Adaptation
In this paper, we propose Layerwise EArly STopping (LEAST) for TTA to address this problem.
GROOD: GRadient-aware Out-Of-Distribution detection in interpolated manifolds
To build this space, GROOD relies on class prototypes together with a prototype that specifically captures OOD characteristics.
Towards Lifelong Self-Supervision For Unpaired Image-to-Image Translation
Unpaired Image-to-Image Translation (I2IT) tasks often suffer from lack of data, a problem which self-supervised learning (SSL) has recently been very popular and successful at tackling.
Identifying Critical Neurons in ANN Architectures using Mixed Integer Programming
We introduce a mixed integer program (MIP) for assigning importance scores to each neuron in deep neural network architectures which is guided by the impact of their simultaneous pruning on the main learning task of the network.
Gender Aware Spoken Language Translation Applied to English-Arabic
One of the challenges of SLT is the translation from a language without gender agreement to a language with gender agreement such as English to Arabic.
Synthetic Data for Neural Machine Translation of Spoken-Dialects
Our approach is language independent and can be used to generate data for any variant of the source language such as slang or spoken dialect or even for a different language that is closely related to the source language.
