Sampling Strategies for Active Learning in Personal Photo Retrieval

Abstract

With the advent and proliferation of digital cameras and computers, the number of digital photos created and stored by consumers has grown extremely large. This created increasing demand for image retrieval systems to ease interaction between consumers and personal media content. Active learning is a widely used user interaction model for retrieval systems, which learns the query concept by asking users to label a number of images at each iteration. In this paper, we study sampling strategies for active learning in personal photo retrieval. In order to reduce human annotation efforts in a content-based image retrieval setting, we propose using multiple sampling criteria for active learning: informativeness, diversity and representativeness. Our experimental results show that by combining multiple sampling criteria in active learning, the performance of personal photo retrieval system can be significantly improved.

Image collection structuring based on evidential active learner

“…Considering the Corel database, we find in our experiments that only 7% of the images generates errors for all strategies. Indeed, theoretically it should be possible to decrease considerably the error rate, maybe by alternating or combining strategies like in [16], or by defining other strategies.…”

Multi-Concept Multi-Modality Active Learning for Interactive Video Annotation

“…Cohn et al have demonstrated its usefulness in theory [8]. Wu et al define a representativeness measure for each sample according to its distance to nearby samples, and take it as a criterion of sample selection [18]. Zhang et al estimate data distribution p(x) by Kernel Density Estimation (KDE), and then take it into account in sample selection [13,20].…”

Interactive Video Annotation by Multi-Concept Multi-Modality Active Learning

“…Thus, in practice most active learning methods empirically adopt closest-to-boundary criterion to choose the most uncertain samples [23,24]. Zhang et al and Wu et al further proposed to incorporate the density distribution of samples into the sample selection process [29,32]. Brinker et al [4] pointed out that the selected samples should be diverse, especially when the active learning method works in a batch mode, i.e., in each round a batch of samples rather than an individual sample is selected.…”

“…(1) we can also see the impact of p(x). Wu et al define a representativeness measure for each sample according to its distance to nearby samples, and take it as a criterion of sample selection [29]. Zhang et al estimate data distribution p(x) by Kernel Density Estimation (KDE), and then use it in sample selection [17,32].…”