Papers
Tue 9 Feb 2021
171 papers
- NewsBERT: Distilling Pre-trained Language Model for Intelligent News ApplicationKnowledge distillation → Knowledge distillation for LLMs
- End-to-End Deep Learning of Lane Detection and Path Prediction for Real-Time Autonomous DrivingEnd-to-end autonomous driving → End-to-end system architecture
- Efficient Retrieval Augmented Generation from Unstructured Knowledge for Task-Oriented DialogRetrieval-augmented generation → Conversational and speech RAG
- Clustered Hierarchical Anomaly and Outlier Detection Algorithms
- RANP: Resource Aware Neuron Pruning at Initialization for 3D CNNs
- Robust Optimization and Validation of Echo State Networks for learning chaotic dynamics
- A Study on the Manifestation of Trust in Speech
- Modeling Visual Hallucination: A Generative Adversarial Network Framework
- Flow-Mixup: Classifying Multi-labeled Medical Images with Corrupted Labels
- Estimation and Applications of Quantiles in Deep Binary Classification
- Editorial: Introduction to the Issue on Deep Learning for Image/Video Restoration and Compression
- Sequence-based Machine Learning Models in Jet Physics
- STUaNet: Understanding uncertainty in spatiotemporal collective human mobility
- Roughsets-based Approach for Predicting Battery Life in IoT
- Large-Scale Training System for 100-Million Classification at Alibaba
- Making Paper Reviewing Robust to Bid Manipulation Attacks
- Reinforcement Learning For Constraint Satisfaction Game Agents (15-Puzzle, Minesweeper, 2048, and Sudoku)
- RIGOLETTO -- RIemannian GeOmetry LEarning: applicaTion To cOnnectivity. A contribution to the Clinical BCI Challenge -- WCCI2020
- Transfer Learning Approach for Arabic Offensive Language Detection System -- BERT-Based Model
- On the Robustness of Multi-View Rotation Averaging
- CaPC Learning: Confidential and Private Collaborative Learning
- Benchmarks, Algorithms, and Metrics for Hierarchical Disentanglement
- A Deep Learning Approach for Characterizing Major Galaxy Mergers
- Transfer learning based few-shot classification using optimal transport mapping from preprocessed latent space of backbone neural network
- On the Hardness of PAC-learning Stabilizer States with Noise
- Decontextualization: Making Sentences Stand-Alone
- Scheduling the NASA Deep Space Network with Deep Reinforcement Learning
- Nonstochastic Bandits with Infinitely Many Experts
- On Explainability of Graph Neural Networks via Subgraph Explorations
- Enhancing Audio Augmentation Methods with Consistency Learning
- RODNet: A Real-Time Radar Object Detection Network Cross-Supervised by Camera-Radar Fused Object 3D Localization
- Relational Dynamic Bayesian Network Modeling for Uncertainty Quantification and Propagation in Airline Disruption Management
- Classifier Calibration: with application to threat scores in cybersecurity
- Locally Adaptive Label Smoothing for Predictive Churn
- Regularization Strategies for Quantile Regression
- Local and Global Uniform Convexity Conditions
- Using Deep LSD to build operators in GANs latent space with meaning in real space
- Label Smoothed Embedding Hypothesis for Out-of-Distribution Detection
- AuGPT: Auxiliary Tasks and Data Augmentation for End-To-End Dialogue with Pre-Trained Language Models
- Backdoor Scanning for Deep Neural Networks through K-Arm Optimization
- Dynamic Mode Decomposition of inertial particle caustics in Taylor-Green flow
- DARE-SLAM: Degeneracy-Aware and Resilient Loop Closing in Perceptually-Degraded Environments
- Negative Data Augmentation
- Adversarial Perturbations Are Not So Weird: Entanglement of Robust and Non-Robust Features in Neural Network Classifiers
- CDPAM: Contrastive learning for perceptual audio similarity
- Sub-seasonal forecasting with a large ensemble of deep-learning weather prediction models
- Deep learning architectural designs for super-resolution of noisy images
- "What's in the box?!": Deflecting Adversarial Attacks by Randomly Deploying Adversarially-Disjoint Models
- Towards Bridging the gap between Empirical and Certified Robustness against Adversarial Examples
- Is Space-Time Attention All You Need for Video Understanding?
- Deep Multilabel CNN for Forensic Footwear Impression Descriptor Identification
- Domain Invariant Representation Learning with Domain Density Transformations
- Emotion Transfer Using Vector-Valued Infinite Task Learning
- Point Cloud Transformers applied to Collider Physics
- The Role of the Input in Natural Language Video Description
- Bounded Memory Active Learning through Enriched Queries
- SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networks
- Multi-Agent Coordination in Adversarial Environments through Signal Mediated Strategies
- Consensus Based Multi-Layer Perceptrons for Edge Computing
- Predictive Factors of Kinematics in Traumatic Brain Injury from Head Impacts Based on Statistical Interpretation
- Robust Bandit Learning with Imperfect Context
- Spherical Message Passing for 3D Graph Networks
- Mars Image Content Classification: Three Years of NASA Deployment and Recent Advances
- Equilibrium Refinements for Multi-Agent Influence Diagrams: Theory and Practice
- Bootstrapping Relation Extractors using Syntactic Search by Examples
- An application of a pseudo-parabolic modeling to texture image recognition
- Adaptive Pairwise Weights for Temporal Credit Assignment
- When does gradient descent with logistic loss interpolate using deep networks with smoothed ReLU activations?
- Deep Neural Network based Cough Detection using Bed-mounted Accelerometer Measurements
- Attention-Based Neural Networks for Chroma Intra Prediction in Video Coding
- In Defense of Scene Graphs for Image Captioning
- Telling the What while Pointing to the Where: Multimodal Queries for Image Retrieval
- Benchmarking Deep Graph Generative Models for Optimizing New Drug Molecules for COVID-19
- Principles of Explanation in Human-AI Systems
- How Unique Is a Face: An Investigative Study
- Hallmarks of Human-Machine Collaboration: A framework for assessment in the DARPA Communicating with Computers Program
- MISO-wiLDCosts: Multi Information Source Optimization with Location Dependent Costs
- On permutation invariant training for speech source separation
- Robust Motion In-betweening
- RL for Latent MDPs: Regret Guarantees and a Lower Bound
- Learning Multi-Modal Volumetric Prostate Registration with Weak Inter-Subject Spatial Correspondence
- Sparsification via Compressed Sensing for Automatic Speech Recognition
- More Is More -- Narrowing the Generalization Gap by Adding Classification Heads
- rl_reach: Reproducible Reinforcement Learning Experiments for Robotic Reaching Tasks
- Dynamic Neural Networks: A Survey
- Learning State Representations from Random Deep Action-conditional Predictions
- Leveraging cross-platform data to improve automated hate speech detection
- Moving Object Classification with a Sub-6 GHz Massive MIMO Array using Real Data
- On Theory-training Neural Networks to Infer the Solution of Highly Coupled Differential Equations
- BembaSpeech: A Speech Recognition Corpus for the Bemba Language
- Measuring Progress in Deep Reinforcement Learning Sample Efficiency
- Noisy Recurrent Neural Networks
- The Factory Must Grow: Automation in Factorio
- A Real-World Demonstration of Machine Learning Generalizability: Intracranial Hemorrhage Detection on Head CT
- Residue Density Segmentation for Monitoring and Optimizing Tillage Practices
- An underwater binocular stereo matching algorithm based on the best search domain
- Learning a powerful SVM using piece-wise linear loss functions
- Train a One-Million-Way Instance Classifier for Unsupervised Visual Representation Learning
- Target Training Does Adversarial Training Without Adversarial Samples
- Learning Modality-Specific Representations with Self-Supervised Multi-Task Learning for Multimodal Sentiment Analysis
All 171
- Consensus Control for Decentralized Deep Learning
- A Multi-Arm Bandit Approach To Subset Selection Under Constraints
- Facial Expression Recognition on a Quantum Computer
- Learning How to Search: Generating Effective Test Cases Through Adaptive Fitness Function Selection
- Classification of Handwritten Names of Cities and Handwritten Text Recognition using Various Deep Learning Models
- Broader terms curriculum mapping: Using natural language processing and visual-supported communication to create representative program planning experiences
- AI-based Blackbox Code Deobfuscation: Understand, Improve and Mitigate
- DetCo: Unsupervised Contrastive Learning for Object Detection
- Automatic variational inference with cascading flows
- Ensembling object detectors for image and video data analysis
- Distribution Adaptive INT8 Quantization for Training CNNs
- Fast discovery of multidimensional subsequences for robust trajectory classification
- Diverse Single Image Generation with Controllable Global Structure
- Generative Models as Distributions of Functions
- Structured Diversification Emergence via Reinforced Organization Control and Hierarchical Consensus Learning
- COLOGNE: Coordinated Local Graph Neighborhood Sampling
- Continuous-Time Model-Based Reinforcement Learning
- k-Anonymity in Practice: How Generalisation and Suppression Affect Machine Learning Classifiers
- Referring Segmentation in Images and Videos with Cross-Modal Self-Attention Network
- Quasi-Global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data
- Improving Scene Graph Classification by Exploiting Knowledge from Texts
- Bayesian Transformer Language Models for Speech Recognition
- Where is my hand? Deep hand segmentation for visual self-recognition in humanoid robots
- Federated Learning with Local Differential Privacy: Trade-offs between Privacy, Utility, and Communication
- Reverb: A Framework For Experience Replay
- A Provably Convergent Information Bottleneck Solution via ADMM
- Fashion Focus: Multi-modal Retrieval System for Video Commodity Localization in E-commerce
- On the Universal Transformation of Data-Driven Models to Control Systems
- Classification of Imbalanced Credit scoring data sets Based on Ensemble Method with the Weighted-Hybrid-Sampling
- Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training
- Interrogating the Black Box: Transparency through Information-Seeking Dialogues
- Conversational Query Rewriting with Self-supervised Learning
- Output Perturbation for Differentially Private Convex Optimization: Faster and More General
- Inapproximability of a Pair of Forms Defining a Partial Boolean Function
- AttDMM: An Attentive Deep Markov Model for Risk Scoring in Intensive Care Units
- Loss Function Discovery for Object Detection via Convergence-Simulation Driven Search
- Learning Unsupervised Cross-domain Image-to-Image Translation Using a Shared Discriminator
- Train your classifier first: Cascade Neural Networks Training from upper layers to lower layers
- Fine-Grained Gap-Dependent Bounds for Tabular MDPs via Adaptive Multi-Step Bootstrap
- Graph-Aided Online Multi-Kernel Learning
- CorrDetector: A Framework for Structural Corrosion Detection from Drone Images using Ensemble Deep Learning
- Meta-Learning for Koopman Spectral Analysis with Short Time-series
- Multi-GPU SNN Simulation with Static Load Balancing
- Tr"aumerAI: Dreaming Music with StyleGAN
- Visual Search at Alibaba
- A Single-Timescale Method for Stochastic Bilevel Optimization
- MALI: A memory efficient and reverse accurate integrator for Neural ODEs
- Virtual ID Discovery from E-commerce Media at Alibaba: Exploiting Richness of User Click Behavior for Visual Search Relevance
- CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation
- Security and Privacy for Artificial Intelligence: Opportunities and Challenges
- Large-Scale Visual Search with Binary Distributed Graph at Alibaba
- Training Federated GANs with Theoretical Guarantees: A Universal Aggregation Approach
- Proximal Gradient Descent-Ascent: Variable Convergence under KL Geometry
- Large Scale Long-tailed Product Recognition System at Alibaba
- Rethinking the Optimization of Average Precision: Only Penalizing Negative Instances before Positive Ones is Enough
- Absolute 3D Pose Estimation and Length Measurement of Severely Deformed Fish from Monocular Videos in Longline Fishing
- Federated Deep AUC Maximization for Heterogeneous Data with a Constant Communication Complexity
- Statistically Profiling Biases in Natural Language Reasoning Datasets and Models
- Physics-informed neural networks with hard constraints for inverse design
- WheaCha: A Method for Explaining the Predictions of Models of Code
- TraND: Transferable Neighborhood Discovery for Unsupervised Cross-domain Gait Recognition
- Benford's law: what does it say on adversarial images?
- A New Framework for Variance-Reduced Hamiltonian Monte Carlo
- Joint Intent Detection and Slot Filling with Wheel-Graph Attention Networks
- SwiftNet: Real-time Video Object Segmentation
- Graph Energy-based Model for Substructure Preserving Molecular Design
- Rationally Inattentive Utility Maximization for Interpretable Deep Image Classification
- Regularized Generative Adversarial Network
- UVTomo-GAN: An adversarial learning based approach for unknown view X-ray tomographic reconstruction
- A comparative study of two-dimensional vocal tract acoustic modeling based on Finite-Difference Time-Domain methods
- RMOPP: Robust Multi-Objective Post-Processing for Effective Object Detection