28 citations · 271 across the 94 of their papers we have counts for
5 papers · 1 filter
Towards a Unified Representation Evaluation Framework Beyond Downstream Tasks
Christos Plachouras, Julien Guinot, George Fazekas +3
Downstream probing has been the dominant method for evaluating model representations, an important process given the increasing prominence of self-supervised learning and foundatio…
Anomalous behaviour in loss-gradient based interpretability methods
Vinod Subramanian, Siddharth Gururani, Emmanouil Benetos +1
Loss-gradients are used to interpret the decision making process of deep learning models. In this work, we evaluate loss-gradient based attribution methods by occluding parts of th…
Adversarial Attacks in Sound Event Classification
Vinod Subramanian, Emmanouil Benetos, Ning Xu +2
Adversarial attacks refer to a set of methods that perturb the input to a classification model in order to fool the classifier. In this paper we apply different gradient based adve…
GAN-based Generation and Automatic Selection of Explanations for Neural Networks
Saumitra Mishra, Daniel Stoller, Emmanouil Benetos +2
One way to interpret trained deep neural networks (DNNs) is by inspecting characteristics that neurons in the model respond to, such as by iteratively optimising the model input (e…
A Hybrid Recurrent Neural Network For Music Transcription
Siddharth Sigtia, Emmanouil Benetos, Nicolas Boulanger-Lewandowski +3
We investigate the problem of incorporating higher-level symbolic score-like information into Automatic Music Transcription (AMT) systems to improve their performance. We use recur…