- Read more about SparseBFA: Attacking Sparse Deep Neural Networks with the Worst-Case Bit Flips on Coordinates
- Log in to post comments
poster.pdf
- Categories:
- Read more about Towards Robust Visual Transformer Networks via K-Sparse Attention
- Log in to post comments
Transformer networks, originally developed in the community of machine translation to eliminate sequential nature of recurrent neural networks, have shown impressive results in other natural language processing and machine vision tasks. Self-attention is the core module behind visual transformers which globally mixes the image information. This module drastically reduces the intrinsic inductive bias imposed by CNNs, such as locality, while encountering insufficient robustness against some adversarial attacks.
- Categories:
- Read more about GlassoFormer: a Query-Sparse Transformer for Post-Fault Power Grid Voltage Prediction
- Log in to post comments
We propose GLassoformer, a novel and efficient transformer architecture leveraging group Lasso regularization to reduce the number of queries of the standard self-attention mechanism. Due to the sparsified queries, GLassoformer is more computationally efficient than the standard transformers. On the power grid post-fault voltage prediction task, GLassoformer shows remarkably better prediction than many existing benchmark algorithms in terms of accuracy and stability.
- Categories:
- Read more about CDX-Net: Cross-Domain Multi-Feature Fusion Modeling via Deep Neural Networks for Multivariate Time Series Forecasting in AIOps
- Log in to post comments
CDX-Net.pdf
- Categories:
- Read more about Slides of "LocUNet: Fast Urban Positioning Using Radio Maps and Deep Learning"
- Log in to post comments
This paper deals with the problem of localization in a cellular network in a dense urban scenario. Global Navigation Satellite Systems (GNSS) typically perform poorly in urban environments, where the likelihood of line-of-sight conditions is low, and thus alternative localization methods are required for good accuracy.
- Categories:
- Read more about Poster of "LocUNet: Fast Urban Positioning Using Radio Maps and Deep Learning"
- Log in to post comments
This paper deals with the problem of localization in a cellular network in a dense urban scenario. Global Navigation Satellite Systems (GNSS) typically perform poorly in urban environments, where the likelihood of line-of-sight conditions is low, and thus alternative localization methods are required for good accuracy.
- Categories:
- Read more about Adversarial Learning in Transformer Based Neural Network in Radio signal classification
- Log in to post comments
- Categories:
- Read more about THE POSTER OF WEAKLY SUPERVISED POINT CLOUD UPSAMPLING VIA OPTIMAL TRANSPORT
- Log in to post comments
poster.pdf
- Categories:
- Read more about THE SLIDE OF WEAKLY SUPERVISED POINT CLOUD UPSAMPLING VIA OPTIMAL TRANSPORT
- Log in to post comments
- Categories:
- Read more about SERAB: A MULTI-LINGUAL BENCHMARK FOR SPEECH EMOTION RECOGNITION
- Log in to post comments
The Speech Emotion Recognition Adaptation Benchmark (SERAB) is a new framework to evaluate the performance and generalization capacity of different approaches for utterance-level SER. The benchmark is composed of nine datasets for SER in six languages. We used the proposed framework to evaluate a selection of standard hand-crafted feature sets and state-of-the-art DNN representations. The results highlight that using only a subset of the data included in SERAB can result in biased evaluation, while compliance with the proposed protocol can circumvent this issue.
- Categories: