Proceedings Article10.1109/ICCV.2015.325
Multi-class Multi-annotator Active Learning with Robust Gaussian Process for Visual Recognition
Chengjiang Long,Gang Hua +1 more
- 07 Dec 2015
- pp 2839-2847
TL;DR: A novel Gaussian process classifier model with multiple annotators for multi-class visual recognition that incorporates the idea of reinforcement learning to actively select both the informative samples and the high-quality annotators, which better explores the trade-off between exploitation and exploration.
read more
Abstract: Active learning is an effective way to relieve the tedious work of manual annotation in many applications of visual recognition. However, less research attention has been focused on multi-class active learning. In this paper, we propose a novel Gaussian process classifier model with multiple annotators for multi-class visual recognition. Expectation propagation (EP) is adopted for efficient approximate Bayesian inference of our probabilistic model for classification. Based on the EP approximation inference, a generalized Expectation Maximization (GEM) algorithm is derived to estimate both the parameters for instances and the quality of each individual annotator. Also, we incorporate the idea of reinforcement learning to actively select both the informative samples and the high-quality annotators, which better explores the trade-off between exploitation and exploration. The experiments clearly demonstrate the efficacy of the proposed model.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Learning From Noisy Labels by Regularized Estimation of Annotator Confusion
Ryutaro Tanno,Ardavan Saeedi,Swami Sankaranarayanan,Daniel C. Alexander,Nathan Silberman +4 more
- 15 Jun 2019
TL;DR: In this paper, a regularization term is added to the loss function that encourages convergence to the true annotator confusion matrix, which is a confusion matrix that is jointly estimated along with the classifier predictions.
•Proceedings Article
A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Prediction
Zhian Liu,Yongwei Nie,Chengjiang Long,Zhang Qing,Guiqing Li +4 more
- 01 Jan 2021
TL;DR: Wang et al. as mentioned in this paper proposed a hybrid framework that integrates flow reconstruction and frame prediction seamlessly to handle Video Anomaly Detection, where the network of ML-MemAE-SC (Multi-Level Memory modules in an Autoencoder with Skip Connections) was designed to memorize normal patterns for optical flow reconstruction so that abnormal events can be sensitively identified with larger flow reconstruction errors.
DOA-GAN: Dual-Order Attentive Generative Adversarial Network for Image Copy-Move Forgery Detection and Localization
Ashraful Islam,Chengjiang Long,Arslan Basharat,Anthony Hoogs +3 more
- 14 Jun 2020
TL;DR: This paper proposes a Generative Adversarial Network with a dual-order attention model to detect and localize copy-move forgeries, and is the first to propose such a network architecture with the 1st-orders attention mechanism from the affinity matrix.
ARGAN: Attentive Recurrent Generative Adversarial Network for Shadow Detection and Removal
Bin Ding,Chengjiang Long,Ling Zhang,Chunxia Xiao +3 more
- 01 Oct 2019
TL;DR: An attentive recurrent generative adversarial network (ARGAN) to detect and remove shadows in an image that outperforms the state-of-the-art methods, especially in detail of recovering shadow areas.
155
•Proceedings Article
Deep active learning for object detection
Soumya Roy,Asim Unmesh,Vinay P. Namboodiri +2 more
- 01 Jan 2018
TL;DR: A novel active learning method is developed which poses the layered architecture used in object detection as a ‘query by committee’ paradigm to choose the set of images to be queried and these methods outperform classical uncertainty-based active learning algorithms like maximum entropy.
155
References
•Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
Alex Krizhevsky,Ilya Sutskever,Geoffrey E. Hinton +2 more
- 03 Dec 2012
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
ImageNet: A large-scale hierarchical image database
Jia Deng,Wei Dong,Richard Socher,Li-Jia Li,Kai Li,Li Fei-Fei +5 more
- 20 Jun 2009
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
LabelMe: A Database and Web-Based Tool for Image Annotation
TL;DR: In this article, a large collection of images with ground truth labels is built to be used for object detection and recognition research, such data is useful for supervised learning and quantitative evaluation.
Algorithm 778: L-BFGS-B: Fortran subroutines for large-scale bound-constrained optimization
TL;DR: L-BFGS-B is a limited-memory algorithm for solving large nonlinear optimization problems subject to simple bounds on the variables, intended for problems in which information on the Hessian matrix is difficult to obtain, or for large dense problems.
3.5K
•Journal Article
On the algorithmic implementation of multiclass kernel-based vector machines
Koby Crammer,Yoram Singer +1 more
TL;DR: This paper describes the algorithmic implementation of multiclass kernel-based vector machines using a generalized notion of the margin to multiclass problems, and describes an efficient fixed-point algorithm for solving the reduced optimization problems and proves its convergence.