Papers
Sat 18 Mar 2023
94 papers
- DeAR: Debiasing Vision-Language Models with Additive ResidualsMultimodal LLMs / vision-language models → Social bias and fairness in VLMs
- RCA: Region Conditioned Adaptation for Visual Abductive ReasoningLLM reasoning → Multimodal reasoning
- Whole-slide-imaging Cancer Metastases Detection and Localization with Limited Tumorous DataKnowledge distillation → Distillation for medical imaging
- Diff-UNet: A Diffusion Embedded Network for Volumetric SegmentationDiffusion models → Medical imaging and segmentation
- Remote Sensing Object Counting with Online Knowledge LearningKnowledge distillation → Detection and dense prediction distillation
- Study of Robust Adaptive Beamforming with Covariance Matrix Reconstruction Based on Power Spectral Estimation and Uncertainty Region
- Machine learning for discovering laws of nature
- Requirement Formalisation using Natural Language Processing and Machine Learning: A Systematic Review
- GBO:AMulti-Granularity Optimization Algorithm via Granular-ball for Continuous Problems
- DevelSet: Deep Neural Level Set for Instant Mask Optimization
- Mixing Backward- with Forward-Chaining for Metacognitive Skill Acquisition and Transfer
- The Power of Nudging: Exploring Three Interventions for Metacognitive Skills Instruction across Intelligent Tutoring Systems
- Vision Transformer-based Model for Severity Quantification of Lung Pneumonia Using Chest X-ray Images
- AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning
- Exploring Expression-related Self-supervised Learning for Affective Behaviour Analysis
- A Deep Learning System for Domain-specific Speech Recognition
- Neural Operators of Backstepping Controller and Observer Gain Functions for Reaction-Diffusion PDEs
- Revisiting the Plastic Surgery Hypothesis via Large Language Models
- Lossless Microarray Image Compression by Hardware Array Compactor
- Divide and Conquer: Answering Questions with Object Factorization and Compositional Reasoning
- Large Language Model Instruction Following: A Survey of Progresses and Challenges
- Report of the Medical Image De-Identification (MIDI) Task Group -- Best Practices and Recommendations
- Practical and Matching Gradient Variance Bounds for Black-Box Variational Bayesian Inference
- SPDF: Sparse Pre-training and Dense Fine-tuning for Large Language Models
- Machine learning with data assimilation and uncertainty quantification for dynamical systems: a review
- Multi-Modal Continual Test-Time Adaptation for 3D Semantic Segmentation
- Learn, Unlearn and Relearn: An Online Learning Paradigm for Deep Neural Networks
- Confidence Attention and Generalization Enhanced Distillation for Continuous Video Domain Adaptation
- Augmenting and Aligning Snippets for Few-Shot Video Domain Adaptation
- Uncertainty-Aware Optimal Transport for Semantically Coherent Out-of-Distribution Detection
- Content Adaptive Front End For Audio Classification
- EarCough: Enabling Continuous Subject Cough Event Detection on Hearables
- Stall Number Detection of Cow Teats Key Frames
- GazeReader: Detecting Unknown Word Using Webcam for English as a Second Language (ESL) Learners
- Stop Words for Processing Software Engineering Documents: Do they Matter?
- Spatial-Aware Token for Weakly Supervised Object Localization
- Grounding 3D Object Affordance from 2D Interactions in Images
- FD-Net: An Unsupervised Deep Forward-Distortion Model for Susceptibility Artifact Correction in EPI
- Modeling the Trade-off of Privacy Preservation and Activity Recognition on Low-Resolution Images
- Byzantine-Resilient Federated Learning at Edge
- NoisyHate: Mining Online Human-Written Perturbations for Realistic Robustness Benchmarking of Content Moderation Models
- Protein Sequence Design with Batch Bayesian Optimisation
- Discovering Predictable Latent Factors for Time Series Forecasting
- Identification of Novel Classes for Improving Few-Shot Object Detection
- Mutilmodal Feature Extraction and Attention-based Fusion for Emotion Estimation in Videos
- A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models
- Multi-Semantic Interactive Learning for Object Detection
- ExplainFix: Explainable Spatially Fixed Deep Networks
- 3DQD: Generalized Deep 3D Shape Prior via Part-Discretized Diffusion Process
- MotionTrack: Learning Robust Short-term and Long-term Motions for Multi-Object Tracking
- Smart ROI Detection for Alzheimer's disease prediction using explainable AI
- FedRight: An Effective Model Copyright Protection for Federated Learning
- Energy-Efficient Cellular-Connected UAV Swarm Control Optimization
- Towards Diverse Binary Segmentation via A Simple yet General Gated Network
- A Graph-Guided Reasoning Approach for Open-ended Commonsense Question Answering
- HIBMatch: Hypergraph Information Bottleneck for Semi-supervised Alzheimer's Progression
- Channel-Aware Distillation Transformer for Depth Estimation on Nano Drones
- Social Occlusion Inference with Vectorized Representation for Autonomous Driving
- Powerful and Extensible WFST Framework for RNN-Transducer Losses
- Adaptive Multi-source Predictor for Zero-shot Video Object Segmentation
- Interpretable Reinforcement Learning via Neural Additive Models for Inventory Management
- Client Selection for Generalization in Accelerated Federated Learning: A Multi-Armed Bandit Approach
- Just Noticeable Visual Redundancy Forecasting: A Deep Multimodal-driven Approach
- Geometric Imbalance in Semi-Supervised Node Classification
- Blind Multimodal Quality Assessment of Low-light Images
- An Empirical Study of Pre-trained Language Models in Simple Knowledge Graph Question Answering
- CroSel: Cross Selection of Confident Pseudo Labels for Partial-Label Learning
- DC-CCL: Device-Cloud Collaborative Controlled Learning for Large Vision Models
- Neural Frailty Machine: Beyond proportional hazard assumption in neural survival regressions
- Sharpness-Aware Gradient Matching for Domain Generalization
- Uncertainty-aware U-Net for Medical Landmark Detection
- SOCS: Semantically-aware Object Coordinate Space for Category-Level 6D Object Pose Estimation under Large Shape Variations
- Local-to-Global Panorama Inpainting for Locale-Aware Indoor Lighting Prediction
- Supervision Interpolation via LossMix: Generalizing Mixup for Object Detection and Beyond
- 3D Data Augmentation for Driving Scenes on Camera
- A general-purpose AI assistant embedded in an open-source radiology information system
- Recognizing Complex Gestures on Minimalistic Knitted Sensors: Toward Real-World Interactive Systems
- Extracting Class Activation Maps from Non-Discriminative Features as well
- HybridMIM: A Hybrid Masked Image Modeling Framework for 3D Medical Image Segmentation
- Exploring Partial Knowledge Base Inference in Biomedical Entity Linking
- Revisiting Automatic Question Summarization Evaluation in the Biomedical Domain
- Hybrid Systems Neural Control with Region-of-Attraction Planner
- Dynamic Graph Enhanced Contrastive Learning for Chest X-ray Report Generation
- Inverse Cubature and Quadrature Kalman filters
- ABC: Attention with Bilinear Correlation for Infrared Small Target Detection
- Lung segmentation with NASNet-Large-Decoder Net
- On the rise of fear speech in online social media
- Domain-knowledge Inspired Pseudo Supervision (DIPS) for Unsupervised Image-to-Image Translation Models to Support Cross-Domain Classification
- Edge-aware Plug-and-play Scheme for Semantic Segmentation
- The Challenge of Differentially Private Screening Rules
- Welfare Maximization Algorithm for Solving Budget-Constrained Multi-Component POMDPs
- Forecasting COVID-19 Case Counts Based on 2020 Ontario Data
- Detection of Uncertainty in Exceedance of Threshold (DUET): An Adversarial Patch Localizer
- Mobile Edge Adversarial Detection for Digital Twinning to the Metaverse with Deep Reinforcement Learning