Iterative Projection and Matching: Finding Structure-preserving Representatives and Its Application to Computer Vision
This work addresses data selection challenges in computer vision, offering a fast and parameter-free method for applications like active learning and video summarization, though it is incremental as it builds on existing subspace-based selection techniques.
The paper tackles the problem of selecting representative data samples that preserve structural information by proposing the Iterative Projection and Matching (IPM) algorithm, which achieves linear complexity and outperforms conventional methods in computational efficiency and selection accuracy across multiple computer vision tasks.
The goal of data selection is to capture the most structural information from a set of data. This paper presents a fast and accurate data selection method, in which the selected samples are optimized to span the subspace of all data. We propose a new selection algorithm, referred to as iterative projection and matching (IPM), with linear complexity w.r.t. the number of data, and without any parameter to be tuned. In our algorithm, at each iteration, the maximum information from the structure of the data is captured by one selected sample, and the captured information is neglected in the next iterations by projection on the null-space of previously selected samples. The computational efficiency and the selection accuracy of our proposed algorithm outperform those of the conventional methods. Furthermore, the superiority of the proposed algorithm is shown on active learning for video action recognition dataset on UCF-101; learning using representatives on ImageNet; training a generative adversarial network (GAN) to generate multi-view images from a single-view input on CMU Multi-PIE dataset; and video summarization on UTE Egocentric dataset.