There are 3 special sessions, which are:

  1. Advances in deep and shallow machine learning algorithms for biomedical data and imaging and Randomization-based deep and shallow learning algorithms. (SS 1-1, SS 2-1, SS 3-1)
  2. Reliable, Robust, and Secure Machine Learning Algorithms. (SS 1-2, SS 2-2, SS 3-2)
  3. Theory and Applications of Natural Computing Paradigms. (SS 1-3)


Special Sessions ICONIP 2021
11 December 2021 – TS 6
SS 1-1 1005 Neural network pruning based on improved constrained particle swarm optimization
453 PoseGate-Former: Transformer Encoder WithTrainable Gate For 3D Human Pose EstimationBy Weakly Supervised Learning Approach
593 Deformable Convolution and Semi-Supervised Learning in Point Clouds for Aneurysm Classification and Segmentation
663 Coordinate Attention Residual Deformable U-Net for Vessel Segmentation
764 Overcoming Data Scarcity for Coronary Vessel Segmentation Through Self-Supervised Pre-Training
274 FetalNet: Multi-task deep learning framework for fetal ultrasound biometric measurements


SS 1-2 221 Partial Classification Based on Pre-Trained CNN-Based Model Outputs
374 Multi-branch Fusion Fully Convolutional Network for Person Re-Identification
1000 Developing GCN: Graph Convolutional Network with Evolving Parameters for Dynamic Graphs
145 On robustness of generative representations against catastrophic forgetting
544 Combat Unit Selection Based on Hybrid Neural Network in Real-time Strategy Games
678 Dy-Drl2Op: Learning Heuristics for TSP on the Dynamic Graph via Deep Reinforcement Learning


SS 1-3 59 Compositional Committees of Tiny Networks
323 EEG-based classification of lower limb motor imagery with STFT and CNN
554 Brain-mimetic Kernel: A Kernel Constructed from Human fMRI Signals Enabling a Brain-mimetic Visual Recognition Algorithm
679 Predominant Sense Acquisition with a neural random walk model
986 Processing-response dependence on the on-chip readout positions in spin-wave reservoir computing
994 Recurrent Neural Network with Adaptive Gating Timescales Mechanisms for Language and Action Learning


11 December 2021 – TS 7
SS 2-1 92 A multi-task learning scheme for Motor Imagery Signal Classification
Session Chair: 170 An End-to-End Hemisphere Discrepancy Network for Subject-Independent Motor Imagery Classification
758 EEG-based Human Decision Confidence Measurement Using Graph Neural Networks
802 Self-attention long-term dependency modelling in electroencephalography sleep stage prediction
993 Deep learning models with time delay embedding for EEG-based attentive state classification
658 Ensembles of Randomized Neural Networks for Pattern-based Time Series Forecasting
1031 Grouped Echo State Network with Late Fusion for Speech Emotion Recognition


SS 2-2 152 Continual Learning with Differential Privacy
531 EvoBA: An Evolution Strategy as a Strong Baseline for Black-Box Adversarial Attacks
629 A novel oversampling technique for imbalanced learning based on SMOTE and genetic algorithm
869 On the Importance of Regularisation & Auxiliary Information in OOD Detection
961 Alleviating Catastrophic Interference in Online Learning via Varying Scale of Backward Queried Data
972 Construction and Reasoning for Interval-Valued EBRB Systems
1025 Dual Feature Distributional Regularization for Defending against Adversarial Attacks
11 December 2021 – TS 8
SS 3-1 246 OADA: an Online Data Augmentation Method for Processing Histopathology Images from Raw Medical Records
461 Pancreatic Neoplasm Image Translation Based on Feature Correlation Analysis of Cross-phase Image
464 Multi-domain Abdomen Image Alignment Based on Joint Network of Registration and Synthesis
743 Gated Channel Attention Network for Cataract Classification on AS-OCT Image
841 Marginal Spectrum Modulated Hilbert-Huang Transform: Application to Time Courses Extracted by Independent Vector Analysis of Resting-State fMRI Data
848 ReCal-Net: Joint Region-Channel-Wise Calibrated Network for Semantic Segmentation in Cataract Surgery Videos
1086 Enhancing Dermoscopic Features Classification in Images Using Invariant Dataset Augmentation and Convolutional Neural Networks


SS 3-2 409 Fast Organization of Objects’ Spatial Positions in Manipulator Space from Single RGB-D Camera
719 Multi-label classification of hyperspectral images based on label-specific feature fusion
759 A Novel Multi-Scale Key-Point Detector Using Residual Dense Block and Coordinate Attention
789 A Scan-to-Locality Map Strategy for 2D LiDAR and RGB-D Data Fusion
167 How Much Do Synthetic Datasets Matter In Handwritten Text Recognition?
108 Open-Set Recognition with Dual Probability Learning