VITALab
Publications Members Webinars Categories Posts Search

Categories

  • Bayesian Methods for Machine Learning
  • CS294: Deep Reinforcement Learning
  • CS229: Machine Learning
  • CS231n: Convolutional Neural Networks for Visual Recognition

  • DreamerV3: Mastering Diverse Domains through World Models
  • Improving Explainability of Disentangled Representations using Multipath-Attribution Mappings
  • White Matter Tracts are Point Clouds: Neuropsychological Score Prediction and Critical region Localization via Geometric Deep Learning
  • Learning Optimal White Matter Tract Representations from Tractography using a Deep Generative Model for Population Analyses
  • ResMLP: Feedforward networks for image classification with data-efficient training
  • What Matters in Learning from Offline Human Demonstrations for Robot Manipulation
  • Class Anchor Clustering: A Loss for Distance-based Open Set Recognition
  • Escaping the Big Data Paradigm with Compact Transformers
  • Consistency Regularization for Variational Auto-Encoders
  • ComTriplet: Deep Clustering via Center-Oriented Margin Free-Triplet Loss for Skin Lesion Detection in Highly Imbalanced Datasets
  • Self-Supervised MultiModal Versatile Networks
  • Sparse Multi-Channel Variational Autoencoder for the Joint Analysis of Heterogeneous Data
  • Scanner invariant representations for diffusion MRI harmonization
  • Context-aware virtual adversarial training for anatomically-plausible segmentation
  • Data-driven discovery of coordinates and governing equations
  • From Variational to Deterministic Autoencoders
  • Emerging Properties in Self-Supervised Vision Transformers
  • The Diffusion-Simulated Connectivity (DiSCo) Challenge
  • AAVAE: Augmentation-Augmented Variational Autoencoders
  • Deep Fiber Clustering: Anatomically Informed Unsupervised Deep Learning for Fast and Effective White Matter Parcellation
  • Perceiver: General Perception with Iterative Attention
  • Cooperative Training and Latent Space Data Augmentation for Robust Medical Image Segmentation
  • Simple and Effective VAE Training with Calibrated Decoders
  • Modelling the Distribution of 3D Brain MRI using a 2D Slice VAE
  • TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation
  • Unadversarial examples: designing objects for robust vision
  • Conservative Q-Learning for Offline Reinforcement Learning
  • A generative modeling approach for interpreting population-level variability in brain structure
  • Dataset distillation
  • CLIP : Learning Transferable Visual Models From Natural Language Supervision
  • Distributional Reinforcement Learning with Quantile Regression
  • Diminishing Uncertainty within the Training Pool: Active Learning for Medical Image Segmentation
  • Intriguing properties of neural networks
  • Evasion attacks against machine learning at test time
  • FOD-Net: A Deep Learning Method for Fiber Orientation Distribution Angular Super Resolution
  • A Distributional Perspective on Reinforcement Learning
  • Similarity of Neural Network Representations Revisited
  • MedAL: Accurate and Robust Deep Active Learning for Medical Image Analysis
  • Fader Networks: Manipulating Images by Sliding Attributes
  • Attribute-based regularization of latent spaces for variational auto-encoders
  • AlphaGo/AlphaGoZero/AlphaZero/MuZero: Mastering games using progressively fewer priors
  • Domain Generalization via Model-Agnostic Learning of Semantic Features
  • EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
  • AC-VAE: Learning Semantic Representation with VAE for Adaptive Clustering
  • A Deep Neural Network's Loss Surface Contains Every Low-dimensional Pattern
  • An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
  • Diva: Domain invariant variational autoencoders
  • Phasic Policy Gradient
  • G-SGD: Optimizing ReLU neural networks in its positively scale-invariant space
  • Path-SGD: Path-Normalized Optimization in Deep Neural Networks
  • Munchausen Reinforcement Learning
  • Disentangled Representation Learning in Cardiac Image Analysis
  • InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
  • Temporal Consistency Objectives Regularize the Learning of Disentangled Representations
  • Isolating Sources of Disentanglement in VAEs
  • Disentangling by Factorising
  • Using Generative Models for Pediatric wbMRI
  • Dynamics-Aware Unsupervised Discovery of Skills
  • OnceCycleLR: Super-Convergence: Very Fast Training of NeuralNetworks Using Large Learning Rates
  • Self-Attention Generative Adversarial Networks
  • Accelerating Online Reinforcement Learning with Offline Datasets
  • A machine learning-based method for estimating the number and orientations of major fascicles in diffusion-weighted magnetic resonance imaging
  • What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study
  • Deep Learning: A philosophical introduction
  • Feature-robustness, flatness and generalization error for deep neural networks
  • Sharp Minima can Generalize for Deep Nets
  • Agent57: Outperforming the human Atari benchmark
  • Demystifying Parallel and Distributed Deep Learning
  • Neuro4Neuro: A neural network approach for neural tract segmentation using large-scale population-based diffusion imaging
  • Never Give Up: Learning Directed Exploration Strategies
  • An exponential learning rate schedule for deep learning
  • Visualizing the Loss Landscape of Neural Nets
  • BEAR (Bootstrapping Error Accumulation Reduction)
  • Superfast Diffusion Tensor Imaging and Fiber Tractography Using Deep Learning
  • Classifyber, a robust streamline-based linear classifier for white matter bundle segmentation
  • Representational drift in Recurrent Reinforcement Learning
  • Learning Latent Subspaces in Variational Autoencoders
  • L2 Regularization versus Batch and Weight Normalization
  • PHiSeg - Capturing Uncertainty in Medical Image Segmentation
  • Learning Macroscopic Brain Connectomes via Group-Sparse Factorization
  • Implementation Matters in Deep RL: A Case Study on PPO and TRPO
  • Upside-Down Reinforcement-Learning
  • Rigging the Lottery: Making All Tickets Winners
  • Deep learning reveals untapped information for local white-matter fiber reconstruction in diffusion-weighted MRI
  • SPECTRAL GRAPH TRANSFORMER NETWORKS FOR BRAIN SURFACE PARCELLATION
  • Artifact Disentanglement Network for Unsupervised Metal Artifact Reduction
  • Single Headed Attention RNN: Stop Thinking With Your Head
  • Associative Compression Networks for Representation Learning
  • Stealing Machine Learning Models via Prediction APIs
  • Entrack: A Data-Driven Maximum-Entropy Approach to Fiber Tractography
  • Estimating localized complexity of white-matter wiring with GANs
  • Meta-Learning Deep Energy-Based Memory Models
  • ETNet - Error Transition Network for Arbitrary Style Transfer
  • Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution
  • Manifold mixup: Encouraging meaningful on-manifold interpolation as a regularizer
  • Cardiac Segmentation from LGE MRI Using Deep Neural Network Incorporating Shape and Spatial Priors
  • ipA-MedGAN: INPAINTING OF ARBITRARILY REGIONS IN MEDICAL MODALITIES
  • On the Utility of Learning about Humans for Human-AI Coordination
  • Straight to the point: reinforcement learning for user guidance in ultrasound
  • Pick-and-Learn: Automatic Quality Evaluation for Noisy-Labeled Image Segmentation
  • Learning shape priors for robust cardiac MR segmentation from multi-view images
  • Multi-stage prediction networks for data harmonization
  • Lookahead Optimizer: k steps forward, 1 step back
  • Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning
  • On Boosting Semantic Street Scene Segmentation with Weak Supervision
  • Neural Discrete Representation Learning
  • Context-encoding Variational Autoencoder for Unsupervised Anomaly Detection
  • Reconciling modern machine learning practice and the bias-variance trade-off
  • Emergent Tool Use from Multi-Agent Interaction
  • State-Regularized Recurrent Neural Networks
  • Synergistic Image and Feature Adaptation Towards Cross-Modality Domain Adaptation for Medical Image Segmentation
  • State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations
  • Reproducible White Matter Tract Segmentation Using 3D U-Net on a Large-scale DTI Dataset
  • Anatomical Priors for Image Segmentation via Post-Processing with Denoising Autoencoders
  • A Generalized Framework for Population Based Training
  • Evaluating the Search Phase of Neural Architecture Search
  • Don't Worry About the Weather Unsupervised Condition-Dependent Domain Adaptation
  • Compound–protein interaction prediction with end-to-end learning of neural networks for graphs and sequences
  • Cortical Surface Parcellation using Spherical Convolutional Neural Networks
  • End-to-End Multi-Task Learning with Attention
  • d-SNE: Domain Adaptation Using Stochastic Neighborhood Embedding
  • Superhuman AI for multiplayer poker
  • Iterative Projection and Matching
  • Attention Branch Network: Learning of Attention Mechanism for Visual Explanation
  • Striving for Simplicity in Off-policy Deep Reinforcement Learning
  • Graph-Based Global Reasoning Networks
  • Deep Active Learning for Axon-Myelin Segmentation on Histology Data
  • Hardness-Aware Deep Metric Learning
  • CrDoCo Pixel-Level Domain Transfer With Cross-Domain Consistency
  • Why ReLU Networks Yield High-Confidence Predictions Far Away From the Training Data and How to Mitigate the Problem
  • Unsupervised Detection of White Matter Fiber Bundles with Stochastic Neural Networks
  • Towards Universal Object Detection by Domain Attention
  • Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation
  • Degenerative Adversarial NeuroImage Nets: Generating Images that Mimic Disease Progression
  • Deep Virtual Networks for Memory Efficient Inference of Multiple Tasks
  • Learning Loss for Active Learning
  • Continuous Dice Coefficient: a Method for Evaluating Probabilistic Segmentations
  • Combined tract segmentation and orientation mapping for bundle-specific tractography
  • Residual Policy Learning
  • A General and Adaptive Robust Loss Function
  • DeepBundle: Fiber Bundle Parcellation with Graph Convolution Neural Networks
  • Multi-branch Convolutional Neural Network for Multiple Sclerosis Lesion Segmentation
  • Batch Policy Gradient Methods for Improving Neural Conversation Models
  • Embedded hyper-parameter tuning by Simulated Annealing
  • q-Space Novelty Detection with Variational Autoencoders
  • Pretraining Deep Actor-Critic Reinforcement Learning Algorithms With Expert Demonstrations
  • Multisource and Multitemporal Data Fusion in Remote Sensing
  • Speech2Face: Learning the Face Behind a Voice
  • Synthesized b0 for diffusion distortion correction (Synb0-DisCo)
  • [sketchRNN] A Neural Representation of Sketch Drawings
  • The power of ensembles for active learning in image classification
  • Generative Adversarial Imitation Learning
  • Adversarial Examples Are Not Bugs, They Are Features
  • A deep learning approach to detecting volcano deformation from satellite imagery using synthetic datasets
  • Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
  • DeepAtlas: Joint Semi-Supervised Learning of Image Registration and Segmentation
  • [Contrastive Loss] Dimensionality Reduction by Learning an Invariant Mapping
  • Clipped Proximal Policy Optimization Algorithm
  • Learning Structured Output Representation using Deep Conditional Generative Models
  • Open Questions about Generative Adversarial Networks
  • ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
  • Missing MRI Pulse Sequence Synthesis using Multi-Modal Generative Adversarial Network
  • GeoSay: A Geometric Saliency for Extracting Buildings in Remote Sensing Images
  • Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations
  • Exploring Randomly Wired Neural Networks for Image Recognition
  • Learning how to Active Learn: A Deep Reinforcement Learning Approach
  • 3D Whole Brain Segmentation using Spatially Localized Atlas Network Tiles
  • Deep Neural Networks Improve Radiologists' Performance in Breast Cancer Screening
  • Semantic Image Synthesis with Spatially-Adaptive Normalization
  • Joint Learning of Brain Lesion and Anatomy Segmentation from Heterogeneous Datasets
  • Unsupervised Domain Adaptation using Feature-Whitening and Consensus Loss
  • Data augmentation using learned transforms for one-shot medical image segmentation
  • Prototypical Networks for Few-shot Learning
  • Reverse Curriculum Generation for Reinforcement Learning
  • PlaNet: Learning Latent Dynamics for Planning from Pixels
  • Co-trained convolutional neural networks for automated detection of prostate cancer in multi-parametric MRI
  • Adversarial Autoencoders
  • Novel deep learning-based method for prostate segmentation in T2-weighted magnetic resonance imaging
  • Cross-scanner and cross-protocol diffusion MRI data harmonisation: A benchmark database and evaluation of algorithms
  • Towards increased trustworthiness of deep learning segmentation methods on cardiac MRI
  • Spherical Harmonic Residual Network for Diffusion Signal Harmonization
  • An (almost) instant brain atlas segmentation for large-scale studies
  • Diversity in Faces
  • Character-level Convolutional Networks for Text Classification
  • Deep Multi-Structural Shape Analysis: Application to Neuroanatomy
  • Learning multiple visual domains with residual adapters
  • Harmonizing Diffusion MRI Data Across Multiple Sites and Scanners
  • Fully Convolutional Network with Multi-Step Reinforcement Learning for Image Processing
  • A Style-Based Generator Architecture for Generative Adversarial Networks
  • Deep Learning with Mixed Supervision for Brain Tumor Segmentation
  • h-detach: Modifying the LSTM Gradient Towards Better Optimization
  • Adaptive Fusion for RGB-D Salient Object Detection
  • Combined Reinforcement Learning via Abstract Representations
  • DeepTract: A Probabilistic Deep Learning Framework for White Matter Fiber Tractography
  • PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
  • UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
  • Improved Image Captioning via Policy Gradient optimization of SPIDEr
  • ACN: Associative Compression Networks for Representation Learning
  • Strike (with) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects
  • Metropolis-Hastings Generative Adversarial Networks
  • Go-Explore
  • NAG: Network for Adversary Generation
  • NeuroNet: Fast and Robust Reproduction of Multiple Brain Image Segmentation Pipelines
  • Unsupervised brain lesion segmentation from MRI using a convolutional autoencoder
  • Memory Replay GANs
  • The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
  • From Recognition to Cognition: Visual Commonsense Reasoning
  • Structured Pruning of Neural Networks with Budget-Aware Regularization
  • OBELISK – One Kernel to Solve Nearly Everything: Unified 3D Binary Convolutions for Image Analysis
  • Label Refinement Network for Coarse-to-Fine Semantic Segmentation
  • Learning to reinforcement learn
  • Low-Shot Learning from Imaginary Data
  • Automatically Designing CNN Architectures for Medical Image Segmentation
  • Learning Implicit Brain MRI Manifolds with Deep Learning
  • Incremental Learning for Semantic Segmentation of Large-Scale Remote Sensing Data
  • SDRL: Interpretable and Data-efficient Deep Reinforcement Learning Leveraging Symbolic Planning
  • Mapping connectomes with diffusion MRI: deterministic or probabilistic tractography?
  • UNet-VAE: A Probabilistic U-Net for Segmentation of Ambiguous Images
  • Privacy-preserving generative deep neural networks support clinical data sharing
  • Episodic curiosity through reachability
  • Cascaded Transforming Multi-task Networks For Abdominal Biometric Estimation from Ultrasound
  • SeedNet: Automatic Seed Generation with Deep Reinforcement Learning for Robust Interactive Segmentation
  • Progressive Weight Pruning of DNNs using ADMM
  • Domain Adaptive Segmentation in Volume Electron Microscopy Imaging
  • Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image Deraining
  • Visual semantic navigation using scene priors
  • HeMIS: Hetero-Modal Image Segmentation
  • Residual Connections Encourage Iterative Inference
  • CBAM: Convolutional Block Attention Module
  • A Few Useful Things to Know about Machine Learning
  • Exploiting Semantics in Adversarial Training for Image-Level Domain Adaptation
  • Rethinking the Value of Network Pruning
  • Deep Extreme Cut: From Extreme Points to Object Segmentation
  • Divide-and-Conquer Reinforcement Learning
  • Tversky loss function for image segmentation using 3D fully convolutional deep networks
  • Super-resolution of Sentinel-2 images: Learning a globally applicable deep neural network
  • PixelSNAIL: An Improved Autoregressive Generative Model
  • TreeSegNet: Adaptive Tree CNNs for Subdecimeter Aerial Image Segmentation
  • Binarized Neural Networks
  • Batch normalization sampling
  • Learning Discriminators as Energy Networks in Adversarial Learning
  • Exclusive Independent Probability Estimation using Deep 3D Fully Convolutional DenseNets for IsoIntense Infant Brain MRI Segmentation
  • Predicting Parameters in Deep Learning
  • Large Scale GAN Training for High Fidelity Natural Image Synthesis
  • Suggestive Annotation: A Deep Active Learning Framework for Biomedical Image Segmentation
  • Feature Selective Networks for Object Detection
  • The Elephant in the Room
  • Towards the first adversarially robust neural network model on MNIST
  • Kronecker Recurrent Units
  • CLIP-Q: Deep Network Compression Learning by In-Parallel Pruning-Quantization
  • Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation
  • Automatic 3D bi-ventricular segmentation of cardiac images by a shape-constrained multi-task deep learning approach
  • PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning
  • Shallow vs deep learning architectures for white matter lesion segmentation in the early stages of multiple sclerosis
  • Multi-Modal Convolutional Neural Network for Brain Tumor Segmentation
  • Style Augmentation: Data Augmentation via Style Randomization
  • On Multiplicative Integration with Recurrent Neural Networks
  • MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks
  • Dual Attention Network for Scene Segmentation
  • DSSLIC: Deep Semantic Segmentation-based Layered Image Compression
  • TRAFIC: Fiber Tract Classification Using Deep Learning
  • All You Need is Love: Evading Hate-speech Detection
  • Learning Shape Priors for Single-View 3D Completion and Reconstruction
  • Data-driven Fiber Tractography With Neural Networks
  • What do Deep Networks Like to See?
  • Attentive Generative Adversarial Network for Raindrop Removal from A Single Image
  • Efficient Interactive Annotation of Segmentation Datasets with Polygon-RNN++
  • BlockDrop: Dynamic Inference Paths in Residual Networks
  • CNN with Alternately Updated Clique
  • Functional Map of the World
  • Neural Processes
  • Learning a Discriminative Feature Network for Semantic Segmentation
  • HAMLET: Hierarchical Harmonic Filters for Learning Tracts from Diffusion MRI
  • Learning a Spatial Activation Function Restoration
  • Learning to Segment Every Thing
  • Scale equivariance in CNNs with vector fields
  • Mining on Manifolds: Metric Learning without Labels
  • Adaptive Neural Trees
  • Rethinking the Faster R-CNN Architecture for Temporal Action Localization
  • Rotation Equivariant CNNs
  • Lightweight Probabilistic Deep Networks
  • MaskLab: Instance Segmentation by Refining Object Detection with Semantic and Direction Features
  • Learning Transferable Deep Models for Land-Use Classification with High-Resolution Remote Sensing Images
  • Pose estimation with a Riemannian Geometry loss
  • “Learning-Compression” Algorithms for Neural Net Pruning
  • Cascade R-CNN: Delving into High Quality Object Detection
  • Autofocus layer
  • Squeeze-and-Excitation Networks (2017 ImageNet winner)
  • Deep Layer Aggregation
  • Training of Convolutional Networks on Multiple Heterogeneous Datasets for Street Scene Semantic Segmentation
  • Tensor-Train Recurrent Neural Networks for Video Classification
  • Burst Denoising with Kernel Prediction Networks
  • ClusterNet: Detecting Small Objects in Large Scenes by Exploiting Spatio-Temporal Information
  • Star shape Prior
  • Normalized Cut Loss for Weakly-supervised CNN Segmentation
  • Guide Me: Interacting with Deep Networks
  • Deep Networks With Shape Priors for Nucleus Detection
  • Domain Shift for Semantic Segmentation
  • Learning Longer-term Dependencies in RNNs with Auxiliary Losses
  • EnhanceNet : Classification Driven Dynamic Image Enhancement
  • Ship wake-detection procedure using conjugate gradient trained artificial neural networks
  • The Method of Auxiliary Coordinates
  • Beyond the Pixel-Wise Loss for Topology-Aware Delineation
  • Simple Does It: Weakly Supervised Instance and Semantic Segmentation
  • Budgeted Super Networks
  • DOTA: A Large-scale Dataset for Object Detection in Aerial Images
  • Siamese LSTM-based fiber structural similarity network (FS2NET) for rotation invariant brain tractography segmentation
  • Anatomical Priors for Unsupervised Biomedical Segmentation
  • Interactive Image Segmentation with Latent Diversity
  • Adversarial Structure Matching Loss for Image Segmentation
  • Knowledge Distillation by On-the-Fly Native Ensemble
  • Dense labeling of large remote sensing imagery with convolutional neural networks: a simple and faster alternative to stitching output label maps
  • Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
  • Automatic Cardiac Disease Assessment on cine-MRI via Time-Series Segmentation and Domain Specific Features
  • Joint Learning from Earth Observation and OpenStreetMap Data to Get Faster Better Semantic Maps
  • Indoor Scene Labeling
  • Densely Connected Bidirectional LSTM
  • Anatomically Constrained Neural Networks (ACNN): Application to Cardiac Image Enhancement and Segmentation
  • Monotonic Chunkwise Attention
  • DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
  • Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentation
  • The Lottery Ticket Hypothesis: Training Pruned Neural Network Architectures
  • MEnet: A Metric Expression Network for Salient Object Segmentation
  • The Intrinsic Dimension of Objective Landscapes
  • Deep Complex Networks
  • Select, Attend, and Transfer: Light, Learnable Skip Connections
  • Adaptive Cost-sensitive Online Classification
  • An Anchor-Free Region Proposal Network for Faster R-CNN based Text Detection Approaches
  • Survey: Network compression and speedup
  • Multi-Stage Multi-Task Neural Network for Aerial Scene Interpretation and Geolocalization
  • Locally Adaptive Learning Loss for Semantic Image Segmentation
  • Between-class Learning for Image Classification
  • Learning Sparse Structured Ensembles with SG-MCMC and Network Pruning
  • GMM-Based Synthetic Samples for Classification of Hyperspectral Images With Limited Training Data
  • On Characterizing the Capacity of Neural Networks Using Algebraic Topology
  • Optimal Transport for Deep Joint Transfer Learning
  • On the importance of single directions for generalization
  • RetinaNet: Focal Loss for Dense Object Detection
  • Knowledg Distillation on Object Detection
  • Deep Semantic Face Deblurring
  • Generative Adversarial Networks and Probabilistic Graph Models for Hyperspectral Image Classification
  • On the insufficiency of existing momentum schemes for Stochastic Optimization
  • Segment-before-Detect: Vehicle Detection and Classification through Semantic Segmentation of Aerial Images
  • SqueezeNet: AlexNet-Level Accuracy with 50X Fewer Parameters and <0.5MB Model Size
  • Recurrent Autoregressive Networks for Online Multi-Object Tracking
  • The Building Blocks of Interpretability
  • IM2HEIGHT: Height Estimation from Single Monocular Imagery via Fully Residual Convolutional-Deconvolutional Network
  • Snapshot Ensembles: Train 1, get M for free
  • Vector Field Based Neural Networks
  • An Unsupervised Learning Model for Deformable Medical Image Registration
  • Learning both Weights and Connections for Efficient Neural Networks
  • Building Instance Classification Using Street View Images
  • Data Distillation: Towards Omni-Supervised Learning
  • Bayesian image quality transfer with CNNs: Exploring uncertainty in dMRI super-resolution
  • Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting
  • Neural Architecture Search with Reinforcement Learning
  • 2D-3D CNN for Cardiac Segmentation
  • Learning Aerial Image Segmentation from Online Maps
  • FiberNET: An Ensemble Deep Learning Framework for Clustering White Matter Fibers
  • Faster R-CNN
  • SegFlow
  • Two-frame motion estimation based on polynomial expansion
  • Synthesizing the preferred inputs for neurons in neural networks via deep generator networks
  • Designing Deep Convolutional Neural Networks for Continuous Object Orientation Estimation
  • Clustering with Deep Learning: Taxonomy and New Methods
  • Convolutional Recurrent Neural Networks for Hyperspectral Data Classification
  • Matching Networks for One Shot Learning
  • Gradients explode - Deep Networks are shallow - ResNet explained
  • Dynamic Routing Between Capsules
  • (NiN) Network In Network
  • SB-Net: Sparse Block Network for Fast Inference
  • Hyperspectral Image Spatial Super-Resolution via 3D Full Convolutional Neural Network
  • Unsupervised Transformation Learning via Convex Relaxations
  • Direct White Matter Bundle Segmentation using Stacked U-Nets
  • Transforming Auto-encoders
  • Deep Reinforcement Learning-based Image Captioning with Embedding Reward
  • Full-CNN : Striving for Simplicity: The All Convolutional Net
  • Simultaneous Super-Resolution and Cross-Modality Synthesis of 3D Medical Images using Weakly-Supervised Joint Convolutional Sparse Coding
  • Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach
  • Convolutional neural network architecture for geometric matching
  • Aggregated Residual Transformations for Deep Neural Networks
  • WILDCAT: Weakly Supervised Learning of Deep ConvNets for Image Classification, Pointwise Localization and Segmentation
  • SVP : Surveillance Video Parsing with Single Frame Supervision
  • Deep Pyramidal Residual Networks
  • Learning from Simulated and Unsupervised Images through Adversarial Training
  • DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents
  • Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
  • Gated Feedback Refinement Network for Dense Image Labeling
  • Joint Sequence Learning and Cross-Modality Convolution for 3D Biomedical Segmentation
  • Universal adversarial perturbations
  • GSNN : The More You Know: Using Knowledge Graphs for Image Classification
  • Mask R-CNN
  • Growing a Brain: Fine-Tuning by Increasing Model Capacity
  • Speed/accuracy trade-offs for modern convolutional object detectors
  • Episodic CAMN: Contextual Attention-based Memory Networks With Iterative Feedback For Scene Labeling
  • Semi-Supervised Monocular Depth Map Prediction
  • PolyNet: A Pursuit of Structural Diversity in Very Deep Networks
  • Unsupervised Learning of Depth and Ego-Motion from Video
  • Mimicking Very Efficient Network for Object Detection
  • Oriented Response Networks
  • Multigrid Neural Architectures
  • Inverse Compositional Spatial Transformer Networks
  • Stacked Generative Adversarial Networks
  • FRNN: Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes
  • Pixelwise Instance Segmentation with a Dynamically Instantiated Network
  • LCNN: Lookup-based CNN
  • Deep Watershed Transform for Instance Segmentation
  • Boundary-aware Instance Segmentation
  • Instance-Level Salient Object Segmentation
  • Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs
  • Kernel pooling for Convolutional Neural Network
  • FusionSeg: Learning to Combine Motion and Appearance for Fully Automatic Segmentation of Generic Objects in Videos
  • Deep Level Sets for Salient Object Detection
  • Full Resolution Image Compression with Recurrent Neural Networks
  • Scene Parsing through ADE20K dataset
  • S3Pool - Pooling with stochastic Spatial Sampling
  • A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection
  • Video Propagation Networks
  • Dilated Residual Networks
  • Scale-Aware Face Detection
  • Evolving Neural Networks Through Augmenting Topologies
  • The Marginal Value of Adaptive Gradient Methods
  • Tiramisu-Net: The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation
  • Inception-v3 : Rethinking the Inception Architecture for Computer Vision
  • DelugeNet : Deep Networks with Massive and Flexible Cross-layer Information Inflows
  • Fast R-CNN
  • U-Net + ResNet : The Importance of Skip Connections in Biomedical Image Segmentation
  • RCNN : Rich feature hierarchies for accurate object detection and semantic segmentation
  • Overfeat : Integrated Recognition, Localization and Detection using Convolutional Networks
  • SharpMask : Learning to Refine Object Segments
  • DeepMask : Learning to Segment Object Candidates
  • Codebook: Background modeling and subtraction by codebook construction
  • K-means: Real-Time Adaptive Foreground/Background Segmentation
  • Feature Pyramid Networks for Object Detection
  • PCA: A Bayesian Computer Vision System for Modeling Human Interactions
  • Learning a similarity metric discriminatively, with application to face verification
  • DenseNet : Densely Connected Convolutional Networks
  • Learning Deconvolution Network for Semantic Segmentation
  • KDE: Non-parametric model for background subtraction
  • FCNN: Fully Convolutional Networks for Semantic Segmentation
  • GMM: Learning patterns of activity using real-time tracking
  • LeNet : Gradient-Based Learning Applied to Document Recognition
  • GoogLeNet, Inception (Going Deeper with Convolutions)
  • Layer Normalization
  • Xception: Deep Learning with Depthwise Separable Convolutions
  • VggNet: Very Deep Convolutional Networks for Large-Scale Image Recognition
  • ResNet: Deep Residual Learning for Image Recognition
  • Image-to-Image Translation with Conditional Adversarial Networks
  • AlexNet: ImageNet Classification with Deep Convolutional Neural Networks
  • You Only Look Once: Unified, Real-Time Object Detection (YOLO)
  • A Survey on Deep Learning in Medical Image Analysis
  • SSD: Single Shot MultiBox Detector
  • U-Net Convolutional Networks for Biomedical Image Segmentation
  • V-Net : Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation
  • Batch normalization: Accelerating deep network training by reducing internal covariate shift

  • Uncertainty Estimation Review
  • Self supervised learning
  • Reinforcement learning crash course

  • Deep Learning with Compute Canada
  • Active learning tutorials

VITALab

Website of the VITALab (Videos & Images Theory and Analytics Laboratory) of Sherbrooke University.

  • GitHub