90 citations · 298 across the 31 of their papers we have counts for
22 papers · 1 filter
Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation
Guy Yariv, Itai Gat, Sagie Benaim +3
We consider the task of generating diverse and realistic videos guided by natural audio samples from a wide variety of semantic classes. For this task, the videos are required to b…
Centered Self-Attention Layers
Ameen Ali, Tomer Galanti, Lior Wolf
The self-attention mechanism in transformers and the message-passing mechanism in graph neural networks are repeatedly applied within deep learning architectures. We show that this…
On Disentangled and Locally Fair Representations
Yaron Gurovich, Sagie Benaim, Lior Wolf
We study the problem of performing classification in a manner that is fair for sensitive groups, such as race and gender. This problem is tackled through the lens of disentangled a…
Dynamically-Scaled Deep Canonical Correlation Analysis
Tomer Friedlander, Lior Wolf
Canonical Correlation Analysis (CCA) is a method for feature extraction of two views by finding maximally correlated linear projections of them. Several variants of CCA have been i…
Mixing between the Cross Entropy and the Expectation Loss Terms
Barak Battash, Lior Wolf, Tamir Hazan
The cross entropy loss is widely used due to its effectiveness and solid theoretical grounding. However, as training progresses, the loss tends to focus on hard to classify samples…
In Defense of the Learning Without Forgetting for Task Incremental Learning
Guy Oren, Lior Wolf
Catastrophic forgetting is one of the major challenges on the road for continual learning systems, which are presented with an on-line stream of tasks. The field has attracted cons…