Artificial neural networks and machine learning -- ICANN 2022 [electronic resource] : 31st International Conference on Artificial Neural Networks, Bristol, UK, September 6-9, 2022, Proceedings. Part I / Elias Pimenidis, Plamen Angelov, Chrisina Jayne, Antonios Papaleonidas, Mehmet Aydin (eds.).

Intro
Preface
Organization
Contents
Part I
A Novel Deep Learning Based Method for Doppler Spectral Curve Detection
1 Introduction
2 Proposed Method
2.1 Preprocessing and Coarse Segmentation
2.2 Curve Correction
2.3 Curve Filling
2.4 Curve Fusion
2.5 Objective Function
3 Experiment
3.1 Dataset
3.2 Implementation Details
3.3 Quantitative Evaluation
3.4 Performance Evaluation of Proposed Model Combined with U-net
3.5 Comparison of Model Efficiency
4 Conclusion
References

A Unified Multiple Inducible Co-attentions and Edge Guidance Network for Co-saliency Detection
1 Introduction
2 Proposed Method
2.1 Classified Inducible Co-Attention
2.2 Focal Inducible Co-attention
2.3 Individual Extraction
2.4 Loss Function
3 Experiments
3.1 Datasets and Evaluation Metrics
3.2 Implementation Details
3.3 Comparison with the State-of-the-Art
3.4 Ablation Studies
4 Conclusion
References
Attention Guided Network for Salient Object Detection in Optical Remote Sensing Images
1 Introduction
2 Related Work

2.1 Attention Mechanism for SOD
2.2 Salient Object Detection for RSIs
3 Approach
3.1 Feature Encoding Backbone
3.2 Position Enhancement Stage
3.3 Detail Refinement Stage
3.4 Hybrid Loss of AGNet
4 Experiment
4.1 Implementation Details
4.2 Ablation Studies
4.3 Comparison with State-of-the-arts
5 Conclusion
References
BiSMSM: A Hybrid MLP-Based Model of Global Self-Attention Processes for EEG-Based Emotion Recognition
1 Introduction
2 Related Work
3 Methods
3.1 Spatial/Temporal Stream
3.2 MLP-SA Mixer
4 Experiments
4.1 Datasets

4.2 Experimental Setup
4.3 Performance
5 Conclusion
References
Boosting Both Robustness and Hardware Efficiency via Random Pruning Mask Selection
1 Introduction
2 Background and Related Works
2.1 Adversarial Attacks and Adversarial Training
2.2 Double-Win Network Pruning
3 Method
3.1 Random Mask Selection (RMS) Strategy
3.2 Iterative Retraining Framework
3.3 Hardware-Aware RMS (HW-RMS)
4 Experiments
4.1 Experiment Setup
4.2 Benchmark with SOTA Methods
4.3 Comparison with RST
4.4 Ablation Study of FSP and Adversarial Gaps
5 Conclusion