Our research paper has been accepted for the ECCV conference

Our research paper "Joint and Progressive Learning from High-Dimensional Data for Multi-Label Classification" by Hong D., Yokoya N., Xu J., Zhu X. is accepted for the ECCV 2018 conference. A short description of the paper is as follows.

Despite the fact that nonlinear subspace learning techniques (e.g. manifold learning) have successfully applied to data representation, there is still room for improvement in explainability (explicit mapping), generalization (out-of-samples), and cost-effectiveness (linearization). To this end, a novel linearized subspace learning technique is developed in a joint and progressive way, called joint and progressive learning strategy (J-Play), with its application to multi-label classification. The J-Play learns high-level and semantically meaningful feature representation from high-dimensional data by 1) jointly performing multiple subspace learning and classification to find a latent subspace where samples are expected to be better classified; 2) progressively learning multi-coupled projections to linearly approach the optimal mapping bridging the original space with the most discriminative subspace; 3) locally embedding manifold structure in each learnable latent subspace. Extensive experiments are performed to demonstrate the superiority and effectiveness of the proposed method in comparison with previous state-of-the-art methods.

Signal Processing in Earth Observation
Prof. Xiaoxiang Zhu

Technische Universität München
Arcisstr. 21
D-80333 München

 

Latest news

 

Upcoming Events

ESA Living Planet 2019 abstract deadline
11/11/2018