8:45 - 12:45, Thursday 15 April 2021
On the Impact of Illumination-Invariant Image Pre-transformation for Contemporary Automotive Semantic Scene Understanding
Deep Fruit Detection in Orchards
Deep Learning-Based Multivariate Probabilistic Forecasting for Short-Term Scheduling in Power Markets
TransUnet: Transformers Make Strong Encoders for Medical Image Segmentation
A Deep Learning-based Radar and Camera Sensor Fusion Architecture for Object Detection
Semi-Supervised Medical Image Segmentation via Learning Consistency under Transformations
Deep Fruit detection in Orchards
Removing sensitive information from panoramic imagery
Optimal Textures
Invariant Information Clustering for Unsupervised Image Classification and Segmentation.
W-Net: A Deep Model for Fully Unsupervised Image Segmentation
ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness
Semi-Supervised Learning with Deep Generative Models
Influence-aware Memory Architectures for Deep Reinforcement Learning
Automated Pavement Crack Segmentation Using U-Net-Based Convolutional Neural Network
LambdaNetworks: Modeling Long-Range Interactions Without Attention
Rethinking Image Inpainting via a Mutual Encoder Decoder with Feature Equalizations.
Learning to learn by gradient descent by gradient descent
Rethinking Attention with Performers
Non-Lossy Ground Truth Comparison via Convolutional Auto-Encoders for Rethinking Image Inpainting via a Mutual Encoder-Decoder with Feature Equalizations
Hierarchical Image Classification using Entailment Cone Embeddings
Deep learning enables fast and dense single-molecule localization with high accuracy
Spatially-sparse convolutional neural networks
Learning to Learn by Gradient Descent by Gradient Descent - Andyrchowicz et al
Scale-Equivariant Steerable Networks
Adapting Neural Networks for the Estimation of Treatment Effects
Paper name: Scale-Equivariant Steerable Networks