amrit110 / active-learning-papers

A list of papers on Active Learning and Uncertainty Estimation for Neural Networks.

Active-Learning-Papers

A list of papers on Active Learning and Uncertainty Estimation for Neural Networks.

• Deep Bayesian active learning with image data (ICML 2017), Yarin Gal et al. [arxiv]
• Active Learning for Convolutional Neural Networks: A Core-Set Approach (ICLR 2018), Ozan Sener, Silvio Savarese. [arxiv]
• CEREALS - Cost-Effective REgion-based Active Learning for Semantic Segmentation (BMVC 2018), Radek Mackowiak et al. [arxiv]
• Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles (NIPS 2017), Balaji Lakshminarayanan et al. [arxiv]
• Large-Scale Visual Active Learning with Deep Probabilistic Ensembles, Kashyap Chitta, Jose M. Alvarez, Adam Lesnikowski. [arxiv]
• Cost-Effective Active Learning for Deep Image Classification (TCSVT - 2016), Keze Wang et al. [arxiv]
• Localization-Aware Active Learning for Object Detection (ACCV 2018), Chieh-Chi Kao et al. [arxiv]
• Deep Active Learning for Video-based Person Re-identification, Menglin Wang et al. [arxiv]
• Deep Active Learning for Efficient Training of a LiDAR 3D Object Detector (30th IEEE Intelligent Vehicles Symposium) Di Feng et al. [arxiv]
• Weight Uncertainty in Neural Networks (ICML 2015), Charles Blundell et al. [arxiv].
• What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision? (NIPS 2017), Alex Kendall, Yarin Gal. [arxiv].
• Learning Loss for Active Learning (CVPR 2019), Donggeun Yoo, In So Kweon. [arxiv]
• Bayesian Generative Active Deep Learning (ICML 2019), Toan Tran et al. [arxiv]
• Active Learning for Visual Question Answering: An Empirical Study, Xiao Lin, Devi Parikh. [arxiv]
• Understanding Black-box Predictions via Influence Functions (ICML 2017), Pang Wei Koh, Percy Liang. [arxiv]
• On the Relationship between Data Efficiency and Error for Uncertainty Sampling, Stephen Mussmann, Percy Liang. [arxiv]
• Active Learning Literature Survey (2010), Burr Settles. [link]
• Dataset Culling: Towards Efficient Training Of Distillation-Based Domain Specific Models (IEEE ICIP 2019), Kentaro Yoshioka et al. [arxiv]
• Introducing Geometry in Active Learning for Image Segmentation, Ksenia Konyushkova et al. [arxiv]
• Towards Human-Machine Cooperation: Self-supervised Sample Mining for Object Detection (CVPR 2018), Keze Wang et al. [arxiv]
• BayesOD: A Bayesian Approach for Uncertainty Estimation in Deep Object Detectors, Ali Harakeh et al. [arxiv]
• Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding (BMVC 2017), Alex Kendall et al. [arxiv]
• Variational Adversarial Active Learning, Samarth Sinha, Sayna Ebrahimi, Trevor Darrell. [arxiv]
• Uncertainty Estimation in One-Stage Object Detection, Florian Kraus, Klaus Dietmayer. [arxiv]
• Modeling Uncertainty by Learning a Hierarchy of Deep Neural Connections, Raanan Y. Rohekar et al. [arxiv]
• Scalable Active Learning for Object Detection, Elmar Haussmann, Michele Fenzi et al. [arxiv]