Computer vision and object detection
Selective Multi-Scale Learning for Object Detection
DRENet: Giving Full Scope to Detection and Regression-based Estimation for Video Crowd Counting
Sisfrutos Papaya: a Dataset for Detection and Classification of Diseases in Papaya
Faster-LTN: a neuro-symbolic, end-to-end object detection architecture
GC-MRNet: Gated Cascade Multi-stage Regression Network for Crowd Counting
Latent Feature-Aware and Local Structure-Preserving Network for 3D Completion from a single depth view
Facial Expression Recognition by Expression-Specific Representation Swapping
Iterative Error Removal for Time-of-Flight Depth Imaging
Blurred Image Recognition: A Joint Motion Deblurring and Classification Loss-Aware Approach
Learning How to Zoom in: Weakly Supervised ROI-based-DAM for Fine-Grained Visual Classification
Convolutional neural networks and kernel methods
(Input) Size Matters for CNN Classifiers
Accelerating Depthwise Separable Convolutions with Vector Processor
KCNet: Kernel-based Canonicalization Network for entities in Recruitment Domain
Deep Unitary Convolutional Neural Networks
Deep learning and optimization I
DPWTE: A Deep Learning Approach to Survival Analysis using a Parsimonious Mixture of Weibull Distributions
First-order and second-order variants of the gradient descent in a unified framework
Bayesian optimization for backpropagation in Monte-Carlo tree search
Growing Neural Networks Achieve Flatter Minima
Dynamic Neural Diversification: Path to Computationally Sustainable Neural Networks
Curved SDE-Net Leads to Better Generalization for Uncertainty Estimates of DNNs
EIS
Efficient and Trainable Activation Functions for Better Accuracy and Performance
Deep learning and optimization II
Why Mixup Improves the Model Performance
Mixup gamblers: Learning to abstain with auto-calibrated reward for mixed samples
Non-Iterative Phase Retrieval With Cascaded Neural Networks
Incorporating Discrete Wavelet Transformation Decomposition Convolution into Deep Network to Achieve Light Training
MMF: A loss extension for feature learning in open set recognition
On the selection of loss functions under known weak label models
Distributed and continual learning
Bilevel Online Deep Learning in Non-stationary Environment
A Blockchain Based Decentralized Gradient Aggregation Design for Federated Learning
Continual Learning for Fake News Detection from Social Media
Balanced Softmax Cross-Entropy for Incremental Learning
Generalised Controller Design using Continual Learning
DRILL: Dynamic Representations for Imbalanced Lifelong Learning
Principal Gradient Direction and Confidence Reservoir Sampling for Continual Learning
Explainable methods
Spontaneous Symmetry Breaking in Data Visualization
Deep NLP Explainer: Using Prediction Slope To Explain NLP Models
Empirically explaining SGD from a line search perspective
Towards Ontologically Explainable Classifiers
Few-shot learning
Leveraging the Feature Distribution in Transfer-based Few-Shot Learning
One-Shot Meta-Learning for Radar-Based Gesture Sequences Recognition
Few-Shot Learning With Random Erasing and Task-Relevant Feature Transforming
Fostering Compositionality in Latent, Generative Encodings to Solve the Omniglot Challenge
Better Few-shot Text Classification with Pre-trained Language Model
Generative adversarial networks
Leveraging GANs via Non-local Features
On Mode Collapse in Generative Adversarial Networks
Image Inpainting Using Wasserstein Generative Adversarial Imputation Network
COViT-GAN: Vision Transformer for COVID-19 Detection in CT Scan Images with Self-Attention GAN for Data Augmentation
PhonicsGAN: Synthesizing Graphical Videos from Phonics Songs
A Progressive Image Inpainting Algorithm with a Mask Auto-update Branch
Hybrid Generative Models for Two-Dimensional Datasets
Towards Compressing Efficient Generative Adversarial Networks for Image Translation via Pruning and Distilling.