Papers
Sat 28 Aug 2021
49 papers
- Self-training Improves Pre-training for Few-shot Learning in Task-oriented Dialog SystemsSynthetic data and self-improvement for LLMs → Self-training for few-shot NLP
- Transfer Learning for Multi-lingual Tasks -- a Survey
- Impact of Surface and Pore Characteristics on Fatigue Life of Laser Powder Bed Fusion Ti-6Al-4V Alloy Described by Neural Network Models
- Towards Fine-grained Image Classification with Generative Adversarial Networks and Facial Landmark Detection
- Identifying Ransomware Actors in the Bitcoin Network
- Feature Extraction for Machine Learning-based Intrusion Detection in IoT Networks
- A Dual Adversarial Calibration Framework for Automatic Fetal Brain Biometry
- Accelerating Serverless Computing by Harvesting Idle Resources
- DeepFake Detection with Inconsistent Head Poses: Reproducibility and Analysis
- Learning to Track Objects from Unlabeled Videos
- CHAINGE: A Blockchain Solution to Automate Payment Detail Updates to Subscription Services
- Compact representations of convolutional neural networks via weight pruning and quantization
- Avoiding unwanted results in locally linear embedding: A new understanding of regularization
- DKM: Differentiable K-Means Clustering Layer for Neural Network Compression
- Variational Inference with NoFAS: Normalizing Flow with Adaptive Surrogate for Computationally Expensive Models
- DenseLiDAR: A Real-Time Pseudo Dense Depth Guided Depth Completion Network
- Self-supervised Neural Networks for Spectral Snapshot Compressive Imaging
- Master memory function for delay-based reservoir computers with single-variable dynamics
- Prototype-Guided Memory Replay for Continual Learning
- Oh My Mistake!: Toward Realistic Dialogue State Tracking including Turnback Utterances
- GroupFormer: Group Activity Recognition with Clustered Spatial-Temporal Transformer
- Generalized Huber Loss for Robust Learning and its Efficient Minimization for a Robust Statistics
- HeadlineCause: A Dataset of News Headlines for Detecting Causalities
- AP-10K: A Benchmark for Animal Pose Estimation in the Wild
- Uncertainty-Aware Model Adaptation for Unsupervised Cross-Domain Object Detection
- Stagewise Unsupervised Domain Adaptation with Adversarial Self-Training for Road Segmentation of Remote Sensing Images
- New Pruning Method Based on DenseNet Network for Image Classification
- WALNUT: A Benchmark on Semi-weakly Supervised Learning for Natural Language Understanding
- Mitigation of Diachronic Bias in Fake News Detection Dataset
- Smoothing Dialogue States for Open Conversational Machine Reading
- Representation Memorization for Fast Learning New Knowledge without Forgetting
- Layer-wise Model Pruning based on Mutual Information
- On the Significance of Question Encoder Sequence Model in the Out-of-Distribution Performance in Visual Question Answering
- Distilling the Knowledge of Large-scale Generative Models into Retrieval Models for Efficient Open-domain Conversation
- Influence-Based Reinforcement Learning for Intrinsically-Motivated Agents
- Power-Based Attacks on Spatial DNN Accelerators
- Goal-driven text descriptions for images
- An implementation of ROS Autonomous Navigation on Parallax Eddie platform
- Extracting Stochastic Governing Laws by Nonlocal Kramers-Moyal Formulas
- AMMASurv: Asymmetrical Multi-Modal Attention for Accurate Survival Analysis with Whole Slide Images and Gene Expression Data
- QACE: Asking Questions to Evaluate an Image Caption
- Dynamic Selection in Algorithmic Decision-making
- Improving Semi-Supervised and Domain-Adaptive Semantic Segmentation with Self-Supervised Depth Estimation
- High performing ensemble of convolutional neural networks for insect pest image detection
- An Anytime Hierarchical Approach for Stochastic Task and Motion Planning
- DASH: Modularized Human Manipulation Simulation with Vision and Language for Embodied AI
- SeeTheSeams: Localized Detection of Seam Carving based Image Forgery in Satellite Imagery
- Image-to-Graph Convolutional Network for Deformable Shape Reconstruction from a Single Projection Image
- Why and How Governments Should Monitor AI Development