2000 character limit reached
Reinforcement-based Display-size Selection for Frugal Satellite Image Change Detection (2312.16965v1)
Published 28 Dec 2023 in cs.CV
Abstract: We introduce a novel interactive satellite image change detection algorithm based on active learning. The proposed method is iterative and consists in frugally probing the user (oracle) about the labels of the most critical images, and according to the oracle's annotations, it updates change detection results. First, we consider a probabilistic framework which assigns to each unlabeled sample a relevance measure modeling how critical is that sample when training change detection functions. We obtain these relevance measures by minimizing an objective function mixing diversity, representativity and uncertainty. These criteria when combined allow exploring different data modes and also refining change detections. Then, we further explore the potential of this objective function, by considering a reinforcement learning approach that finds the best combination of diversity, representativity and uncertainty as well as display-sizes through active learning iterations, leading to better generalization as shown through experiments in interactive satellite image change detection.
- P. Vo and H. Sahbi. ”Transductive kernel map learning and its application to image annotation.” BMVC. 2012.
- Q. Oliveau and H. Sahbi. ”Learning attribute representations for remote sensing ship category classification.” IEEE JSTARS 10.6 (2017): 2830-2840.
- M. Jiu and H. Sahbi. Nonlinear deep kernel learning for image annotation. IEEE Transactions on Image Processing 26 (4), 1820-1832.
- H. Sahbi. ”Relevance feedback for satellite image change detection.” IEEE ICASSP, 2013.
- Dasgupta, Sanjoy. ”Analysis of a greedy active learning strategy.” Advances in neural information processing systems 17 (2004).
- H. Sahbi. ”Coarse-to-fine deep kernel networks.” IEEE ICCV-W, 2017.
- Burr, Settles. ”Active learning.” Synthesis Lectures on Artificial Intelligence and Machine Learning 6.1 (2012).
- Settles & Craven. An analysis of active learning strategies for sequence labeling tasks. 2008.
- Campbell & Broderick, Automated scalable Bayesian inference via Hilbert coresets. 2019.
- M. Jiu and H. Sahbi. ”Laplacian deep kernel learning for image annotation.” IEEE ICASSP, 2016.
- N. Bourdis, D. Marraud and H. Sahbi. ”Camera pose estimation using visual servoing for aerial video change detection.” IEEE IGARSS 2012.
- H. Sahbi and N. Boujemaa. ”Robust matching by dynamic space warping for accurate face recognition.” Proceedings 2001 International Conference on Image Processing (Cat. No. 01CH37205). Vol. 1. IEEE, 2001.
- H. Sahbi. A particular Gaussian mixture model for clustering and its application to image retrieval. Soft Computing 12 (7), 667-676
- A. Mazari and H. Sahbi. ”MLGCN: Multi-Laplacian graph convolutional networks for human action recognition.” The British Machine Vision Conference (BMVC). 2019.
- M. Ferecatu and H. Sahbi. ”TELECOM ParisTech at ImageClefphoto 2008: Bi-Modal Text and Image Retrieval with Diversity Enhancement.” CLEF (Working Notes). 2008.
- M. Jiu and H. Sahbi. ”Deep representation design from deep kernel networks.” Pattern Recognition 88 (2019): 447-457.
- H. Sahbi. ”Imageclef annotation with explicit context-aware kernel maps.” International Journal of Multimedia Information Retrieval 4.2 (2015): 113-128.
- H. Sahbi. ”Learning laplacians in chebyshev graph convolutional networks.” Proceedings of the IEEE/CVF International Conference on Computer Vision. 2021.
- L. Wang and H. Sahbi. ”Bags-of-daglets for action recognition.” 2014 IEEE International Conference on Image Processing (ICIP). IEEE, 2014.
- H. Sahbi. ”Lightweight Connectivity In Graph Convolutional Networks For Skeleton-Based Recognition.” 2021 IEEE International Conference on Image Processing (ICIP). IEEE, 2021.
- H. Sahbi. ”CNRS-TELECOM ParisTech at ImageCLEF 2013 Scalable Concept Image Annotation Task: Winning Annotations with Context Dependent SVMs.” CLEF (Working Notes). 2013.
- Sachin Ravi and Hugo Larochelle. Meta-learning for batch mode active learning. 2018. In URL https://openreview. net/forum, 2018.
- H. Sahbi, D. Geman. A Hierarchy of Support Vector Machines for Pattern Detection. Journal of Machine Learning Research 7 (10).
- H. Sahbi and N. Boujemaa. ”Coarse-to-fine support vector classifiers for face detection.” Object recognition supported by user interaction for service robots. Vol. 3. IEEE, 2002.
- Longlong Jing and Yingli Tian. Self-supervised visual feature learning with deep neural networks: A survey. IEEE transactions on pattern analysis and machine intelligence, 2020.
- Yarin Gal and Zoubin Ghahramani. Dropout as a bayesian approximation: Representing model uncertainty in deep learning, 2016.
- H. Sahbi. ”Misalignment resilient cca for interactive satellite image change detection.” 2016 23rd International Conference on Pattern Recognition (ICPR). IEEE, 2016.
- T. Napoléon and H. Sahbi. ”From 2D silhouettes to 3D object retrieval: contributions and benchmarking.” EURASIP Journal on Image and Video Processing 2010 (2010): 1-17.
- H. Sahbi. Kernel PCA for similarity invariant shape recognition. Neurocomputing 70 (16-18), 3034-3045.
- H. Sahbi and N. Boujemaa. ”From coarse to fine skin and face detection.” Proceedings of the eighth ACM international conference on Multimedia. 2000.
- H. Sahbi and F. Fleuret. Kernel methods and scale invariance using the triangular kernel. Diss. INRIA, 2004.
- H. Sahbi and F. Fleuret. Scale-invariance of support vector machines based on the triangular kernel. Diss. INRIA, 2002.
- M. Ferecatu and H. Sahbi. ”Multi-view object matching and tracking using canonical correlation analysis.” 2009 16th IEEE International Conference on Image Processing (ICIP). IEEE, 2009.
- T. Ma, J. Chen, and C. Xiao, “Constrained generation of semantically valid graphs via regularizing variational autoencoders,” in Proc. of NeurIPS, 2018, pp. 7110–7121.
- H. Sahbi. ”Learning Connectivity with Graph Convolutional Networks.” 2020 25th International Conference on Pattern Recognition (ICPR). IEEE, 2021.
- S. Pan, R. Hu, G. Long, J. Jiang, L. Yao, and C. Zhang, “Adversarially regularized graph autoencoder for graph embedding.” in Proc. of IJCAI 2018, pp. 2609–2615.
Sponsor
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.