167 citations · 507 across the 7 of their papers we have counts for
7 papers
TransCAM: Transformer Attention-based CAM Refinement for Weakly Supervised Semantic Segmentation
Ruiwen Li, Zheda Mai, Chiheb Trabelsi +3
Weakly supervised semantic segmentation (WSSS) with only image-level supervision is a challenging task. Most existing methods exploit Class Activation Maps (CAM) to generate pixel-…
ExCon: Explanation-driven Supervised Contrastive Learning for Image Classification
Zhibo Zhang, Jongseong Jang, Chiheb Trabelsi +4
Contrastive learning has led to substantial improvements in the quality of learned embedding representations for tasks such as image classification. However, a key drawback of exis…
EDDA: Explanation-driven Data Augmentation to Improve Explanation Faithfulness
Ruiwen Li, Zhibo Zhang, Jiani Li +5
Recent years have seen the introduction of a range of methods for post-hoc explainability of image classifier predictions. However, these post-hoc explanations may not always be fa…
Quaternion Convolutional Neural Networks for End-to-End Automatic Speech Recognition
Titouan Parcollet, Ying Zhang, Mohamed Morchid +4
Recently, the connectionist temporal classification (CTC) model coupled with recurrent (RNN) or convolutional neural networks (CNN), made it easier to train speech recognition syst…
Quaternion Recurrent Neural Networks
Titouan Parcollet, Mirco Ravanelli, Mohamed Morchid +4
Recurrent neural networks (RNNs) are powerful architectures to model sequential data, due to their capability to learn short and long-term dependencies between the basic elements o…
Deep Complex Networks
Chiheb Trabelsi, Olexa Bilaniuk, Ying Zhang +7
At present, the vast majority of building blocks, techniques, and architectures for deep learning are based on real-valued operations and representations. However, recent work on r…
On orthogonality and learning recurrent networks with long term dependencies
Eugene Vorontsov, Chiheb Trabelsi, Samuel Kadoury +1
It is well known that it is challenging to train deep neural networks and recurrent neural networks for tasks that exhibit long term dependencies. The vanishing or exploding gradie…