Papers
Wed 6 Oct 2021
231 papers
- Inter-Domain Alignment for Predicting High-Resolution Brain Networks Using Teacher-Student LearningKnowledge distillation → General knowledge distillation methods
- DiffusionCLIP: Text-Guided Diffusion Models for Robust Image ManipulationDiffusion models → Image generation, text-to-image and editing
- Learning Sparse Masks for Diffusion-based Image InpaintingDiffusion models → 3D, point cloud and scene generation
- EdiTTS: Score-based Editing for Controllable Text-to-SpeechDiffusion models → Audio, speech and music
- BadPre: Task-agnostic Backdoor Attacks to Pre-trained NLP Foundation ModelsLLM safety and security → Backdoor and data poisoning attacks
- KNOT: Knowledge Distillation using Optimal Transport for Solving NLP TasksKnowledge distillation → Knowledge distillation for LLMs
- LIDSNet: A Lightweight on-device Intent Detection model using Deep Siamese Network
- HIRE-SNN: Harnessing the Inherent Robustness of Energy-Efficient Deep Spiking Neural Networks by Training with Crafted Input Noise
- One Representative-Shot Learning Using a Population-Driven Template with Application to Brain Connectivity Classification and Evolution Prediction
- Recurrent Brain Graph Mapper for Predicting Time-Dependent Brain Graph Evaluation Trajectory
- Tensor-to-Image: Image-to-Image Translation with Vision Transformers
- Two-level monotonic multistage recommender systems
- Precision and Fitness in Object-Centric Process Mining
- Internal Language Model Adaptation with Text-Only Data for End-to-End Speech Recognition
- A Theory of Tournament Representations
- Clustering Plotted Data by Image Segmentation
- StairwayGraphNet for Inter- and Intra-modality Multi-resolution Brain Graph Alignment and Synthesis
- Deep Slap Fingerprint Segmentation for Juveniles and Adults
- MToFNet: Object Anti-Spoofing with Mobile Time-of-Flight Data
- Test-time Batch Statistics Calibration for Covariate Shift
- A Neural Anthropometer Learning from Body Dimensions Computed on Human 3D Meshes
- A New Weakly Supervised Learning Approach for Real-time Iron Ore Feed Load Estimation
- QTN-VQC: An End-to-End Learning framework for Quantum Neural Networks
- A Few-shot Learning Graph Multi-Trajectory Evolution Network for Forecasting Multimodal Baby Connectivity Development from a Baseline Timepoint
- Use of Deterministic Transforms to Design Weight Matrices of a Neural Network
- Recurrent Multigraph Integrator Network for Predicting the Evolution of Population-Driven Brain Connectivity Templates
- Efficient and Private Federated Learning with Partially Trainable Networks
- A Hierarchical Variational Neural Uncertainty Model for Stochastic Video Prediction
- PWG-IDS: An Intrusion Detection Model for Solving Class Imbalance in IIoT Networks Using Generative Adversarial Networks
- Cloud Failure Prediction with Hierarchical Temporal Memory: An Empirical Assessment
- Disentangling deep neural networks with rectified linear units using duality
- GANtron: Emotional Speech Synthesis with Generative Adversarial Networks
- Unifying Likelihood-free Inference with Black-box Optimization and Beyond
- Cut the CARP: Fishing for zero-shot story evaluation
- Consistent Counterfactuals for Deep Models
- Multi-Trigger-Key: Towards Multi-Task Privacy Preserving In Deep Learning
- MetaCOG: A Hierarchical Probabilistic Model for Learning Meta-Cognitive Visual Representations
- Hybrid Pointer Networks for Traveling Salesman Problems Optimization
- SPEED+: Next-Generation Dataset for Spacecraft Pose Estimation across Domain Gap
- CTC Variations Through New WFST Topologies
- SWAT Watershed Model Calibration using Deep Learning
- Which Shortcut Cues Will DNNs Choose? A Study from the Parameter-Space Perspective
- Improving Pneumonia Localization via Cross-Attention on Medical Images and Reports
- A Uniform Framework for Anomaly Detection in Deep Neural Networks
- Improving Fractal Pre-training
- Player Tracking and Identification in Ice Hockey
- Construction Site Safety Monitoring and Excavator Activity Analysis System
- Large-Scale Topological Radar Localization Using Learned Descriptors
- DRAFT-What you always wanted to know but could not find about block-based environments
- FOD-A: A Dataset for Foreign Object Debris in Airports
- Robust Generalized Method of Moments: A Finite Sample Viewpoint
- Learning the Optimal Recommendation from Explorative Users
- On Neurons Invariant to Sentence Structural Changes in Neural Machine Translation
- FedTune: Automatic Tuning of Federated Learning Hyper-Parameters from System Perspective
- On the Privacy Risks of Deploying Recurrent Neural Networks in Machine Learning Models
- Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimation
- Physics-informed neural network simulation of multiphase poroelasticity using stress-split sequential training
- Integrating Categorical Features in End-to-End ASR
- Optimized Recommender Systems with Deep Reinforcement Learning
- The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation
- Learning Multi-Objective Curricula for Robotic Policy Learning
- RieszNet and ForestRiesz: Automatic Debiased Machine Learning with Neural Nets and Random Forests
- Dynamically Decoding Source Domain Knowledge for Domain Generalization
- A Fast Randomized Algorithm for Massive Text Normalization
- Tribuo: Machine Learning with Provenance in Java
- Efficient Methods for Online Multiclass Logistic Regression
- Two-Bit Aggregation for Communication Efficient and Differentially Private Federated Learning
- DeepBBS: Deep Best Buddies for Point Cloud Registration
- Active Learning of Markov Decision Processes using Baum-Welch algorithm (Extended)
- Emphasis control for parallel neural TTS
- Unsupervised Multimodal Language Representations using Convolutional Autoencoders
- Unsupervised Selective Labeling for More Effective Semi-Supervised Learning
- Multi-Scale Convolutional Neural Network for Automated AMD Classification using Retinal OCT Images
- Predictability and Fairness in Load Aggregation and Operations of Virtual Power Plants
- Generative Modeling with Optimal Transport Maps
- Federated Learning via Plurality Vote
- Learning Canonical Embedding for Non-rigid Shape Matching
- NUS-IDS at FinCausal 2021: Dependency Tree in Graph Neural Network for Better Cause-Effect Span Detection
- Distributed Optimization of Graph Convolutional Network using Subgraph Variance
- Hierarchical prosody modeling and control in non-autoregressive parallel neural TTS
- Video Autoencoder: self-supervised disentanglement of static 3D structure and motion
- Self-Supervised Knowledge Assimilation for Expert-Layman Text Style Transfer
- Topologically Consistent Multi-View Face Inference Using Volumetric Sampling
- Secure Byzantine-Robust Distributed Learning via Clustering
- On Cropped versus Uncropped Training Sets in Tabular Structure Detection
- Machine Learning Practices Outside Big Tech: How Resource Constraints Challenge Responsible Development
- Adversarial Attacks on Spiking Convolutional Neural Networks for Event-based Vision
- Data Twinning
- On the Global Convergence of Gradient Descent for multi-layer ResNets in the mean-field regime
- No-Press Diplomacy from Scratch
- Residual Overfit Method of Exploration
- Boosting RANSAC via Dual Principal Component Pursuit
- Unrolling Particles: Unsupervised Learning of Sampling Distributions
- Foolish Crowds Support Benign Overfitting
- Generative Optimization Networks for Memory Efficient Data Generation
- Shifting Capsule Networks from the Cloud to the Deep Edge
- Equivariant Subgraph Aggregation Networks
- Geometric and Physical Quantities Improve E(3) Equivariant Message Passing
- Grasp-Oriented Fine-grained Cloth Segmentation without Real Supervision
- SAIC_Cambridge-HuPBA-FBK Submission to the EPIC-Kitchens-100 Action Recognition Challenge 2021
All 231
- Meta Internal Learning
- Predicting the Popularity of Games on Steam
- Probabilistic Metamodels for an Efficient Characterization of Complex Driving Scenarios
- Style Equalization: Unsupervised Learning of Controllable Generative Sequence Models
- Using Optimal Transport as Alignment Objective for fine-tuning Multilingual Contextualized Embeddings
- Bayesian neural network unit priors and generalized Weibull-tail property
- Human-in-the-Loop Refinement of Word Embeddings
- Space-Time Graph Neural Networks
- Compositional Q-learning for electrolyte repletion with imbalanced patient sub-populations
- SDA-GAN: Unsupervised Image Translation Using Spectral Domain Attention-Guided Generative Adversarial Network
- ClimateGAN: Raising Climate Change Awareness by Generating Images of Floods
- Capturing Structural Locality in Non-parametric Language Models
- Sequence-to-Sequence Lexical Normalization with Multilingual Transformers
- Spike-inspired Rank Coding for Fast and Accurate Recurrent Neural Networks
- Exploring the Common Principal Subspace of Deep Features in Neural Networks
- 8-bit Optimizers via Block-wise Quantization
- Distribution Preserving Multiple Hypotheses Prediction for Uncertainty Modeling
- Fully Convolutional Cross-Scale-Flows for Image-based Defect Detection
- Pretrained Transformers for Offensive Language Identification in Tanglish
- Parallel Composition of Weighted Finite-State Transducers
- Seed Classification using Synthetic Image Datasets Generated from Low-Altitude UAV Imagery
- Automatic Identification of the End-Diastolic and End-Systolic Cardiac Frames from Invasive Coronary Angiography Videos
- Improving Generalization of Deep Reinforcement Learning-based TSP Solvers
- WHO-Hand Hygiene Gesture Classification System
- Census-Independent Population Estimation using Representation Learning
- Relation Prediction as an Auxiliary Training Objective for Improving Multi-Relational Graph Representations
- Shallow Features Guide Unsupervised Domain Adaptation for Semantic Segmentation at Class Boundaries
- Semantic Prediction: Which One Should Come First, Recognition or Prediction?
- Colmena: Scalable Machine-Learning-Based Steering of Ensemble Simulations for High Performance Computing
- Efficient and High-quality Prehensile Rearrangement in Cluttered and Confined Spaces
- Accelerated First Order Methods for Variational Imaging
- Adversarial Robustness Comparison of Vision Transformer and MLP-Mixer to CNNs
- An Unconstrained Layer-Peeled Perspective on Neural Collapse
- 3rd Place Solution to Google Landmark Recognition Competition 2021
- Multi-Agent Constrained Policy Optimisation
- Hierarchical Potential-based Reward Shaping from Task Specifications
- Spell my name: keyword boosted speech recognition
- Relative Entropy Gradient Sampler for Unnormalized Distributions
- Scalable Multi-Agent Reinforcement Learning for Residential Load Scheduling under Data Governance
- How BPE Affects Memorization in Transformers
- FTPipeHD: A Fault-Tolerant Pipeline-Parallel Distributed Training Framework for Heterogeneous Edge Devices
- Study on Transfer Learning Capabilities for Pneumonia Classification in Chest-X-Rays Image
- SIRe-Networks: Convolutional Neural Networks Architectural Extension for Information Preservation via Skip/Residual Connections and Interlaced Auto-Encoders
- Mismatched No More: Joint Model-Policy Optimization for Model-Based RL
- Semi-relaxed Gromov-Wasserstein divergence with applications on graphs
- Contrastive Learning for Unsupervised Radar Place Recognition
- On Margin Maximization in Linear and ReLU Networks
- ParaDiS: Parallelly Distributable Slimmable Neural Networks
- Graphon based Clustering and Testing of Networks: Algorithms and Theory
- The Information Geometry of Unsupervised Reinforcement Learning
- Generalizing Neural Networks by Reflecting Deviating Data in Production
- Knothe-Rosenblatt transport for Unsupervised Domain Adaptation
- Variance function estimation in regression model via aggregation procedures
- Application of the interactive Leipzig Corpus Miner as a generic research platform for the use in the social sciences
- Trustworthy Artificial Intelligence and Process Mining: Challenges and Opportunities
- Reversible Attack based on Local Visual Adversarial Perturbation
- Tuning Confidence Bound for Stochastic Bandits with Bandit Distance
- Objects in Semantic Topology
- Long-tailed Distribution Adaptation
- Scaling Up Machine Learning For Quantum Field Theory with Equivariant Continuous Flows
- Physics-Informed Neural Networks for AC Optimal Power Flow
- S-Extension Patch: A simple and efficient way to extend an object detection model
- Attentive Walk-Aggregating Graph Neural Networks
- PlumeCityNet: Multi-Resolution Air Quality Forecasting
- Towards Robotic Knee Arthroscopy: Multi-Scale Network for Tissue-Tool Segmentation
- Weak Novel Categories without Tears: A Survey on Weak-Shot Learning
- A Weighted Generalized Coherence Approach for Sensing Matrix Design
- Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy
- Bach Style Music Authoring System based on Deep Learning
- On The Transferability of Deep-Q Networks
- 2nd Place Solution to Google Landmark Recognition Competition 2021
- Heterogeneous Attentions for Solving Pickup and Delivery Problem via Deep Reinforcement Learning
- Inference Attacks Against Graph Neural Networks
- Deep Reinforcement Learning for Solving the Heterogeneous Capacitated Vehicle Routing Problem
- Characterizing Learning Dynamics of Deep Neural Networks via Complex Networks
- MovingFashion: a Benchmark for the Video-to-Shop Challenge
- CLIP-Forge: Towards Zero-Shot Text-to-Shape Generation
- Is An Image Worth Five Sentences? A New Look into Semantics for Image-Text Matching
- Focus on the Common Good: Group Distributional Robustness Follows
- Tackling the DM Challenges with cDMN: A Tight Integration of DMN and Constraint Reasoning
- Deep Classifiers with Label Noise Modeling and Distance Awareness
- Sequential Reptile: Inter-Task Gradient Alignment for Multilingual Learning
- Weakly-supervised Text Classification Based on Keyword Graph
- Simplicial Convolutional Neural Networks
- Deep Identification of Nonlinear Systems in Koopman Form
- FADNet++: Real-Time and Accurate Disparity Estimation with Configurable Networks
- Deep Transfer Learning for Land Use and Land Cover Classification: A Comparative Study
- Decoupled Adaptation for Cross-Domain Object Detection
- Efficient Multi-Modal Embeddings from Structured Data
- T-SNE Is Not Optimized to Reveal Clusters in Data
- Adaptive control of a mechatronic system using constrained residual reinforcement learning
- MTCD: Cataract Detection via Near Infrared Eye Images
- A Regularized Wasserstein Framework for Graph Kernels
- A Survey of Fish Tracking Techniques Based on Computer Vision
- CBP: Backpropagation with constraint on weight precision using a pseudo-Lagrange multiplier method
- See Yourself in Others: Attending Multiple Tasks for Own Failure Detection
- Learning to Iteratively Solve Routing Problems with Dual-Aspect Collaborative Transformer
- 3D-FCT: Simultaneous 3D Object Detection and Tracking Using Feature Correlation
- On the Importance of Firth Bias Reduction in Few-Shot Classification
- Coarse-to-Fine Reasoning for Visual Question Answering
- KNN-BERT: Fine-Tuning Pre-Trained Models with KNN Classifier
- ActiveMatch: End-to-end Semi-supervised Active Representation Learning
- Attack as the Best Defense: Nullifying Image-to-image Translation GANs via Limit-aware Adversarial Attack
- Cycle Representation Learning for Inductive Relation Prediction
- Online Hyperparameter Meta-Learning with Hypergradient Distillation
- On the Surrogate Gap between Contrastive and Supervised Losses
- Pretraining & Reinforcement Learning: Sharpening the Axe Before Cutting the Tree
- Data-Centric AI Requires Rethinking Data Notion
- The Variability of Model Specification
- ABC: Attention with Bounded-memory Control
- Shapley variable importance clouds for interpretable machine learning
- Detecting and Quantifying Malicious Activity with Simulation-based Inference
- Efficient Multi-agent Epistemic Planning: Teaching Planners About Nested Belief
- Exponentially Many Local Minima in Quantum Neural Networks
- TSN-CA: A Two-Stage Network with Channel Attention for Low-Light Image Enhancement
- Can an AI agent hit a moving target?
- The Power of Contrast for Feature Learning: A Theoretical Analysis
- SSFL: Tackling Label Deficiency in Federated Learning via Personalized Self-Supervision
- Post-hoc Models for Performance Estimation of Machine Learning Inference
- GDA-AM: On the effectiveness of solving minimax optimization via Anderson Acceleration
- VC dimension of partially quantized neural networks in the overparametrized regime
- Ripple Attention for Visual Perception with Sub-quadratic Complexity
- Reward-Punishment Symmetric Universal Intelligence
- Influence-Balanced Loss for Imbalanced Visual Classification
- Pedestrian Wind Factor Estimation in Complex Urban Environments
- PoNet: Pooling Network for Efficient Token Mixing in Long Sequences
- Replay-Guided Adversarial Environment Design
- A Deep Learning-based Audio-in-Image Watermarking Scheme
- Spectral Bias in Practice: The Role of Function Frequency in Generalization
- Geometric Transformers for Protein Interface Contact Prediction
- Explaining Off-Policy Actor-Critic From A Bias-Variance Perspective