Annotation Cost-Efficient Active Learning for Deep Metric Learning Driven Remote Sensing Image Retrieval
Deep metric learning (DML) has shown to be very effective for content-based image retrieval (CBIR) in remote sensing (RS). Most of DML methods for CBIR rely on many annotated images to accurately learn model parameters of deep neural networks. However, gathering many image annotations is time consuming and costly. To address this, we propose an annotation cost-efficient active learning (ANNEAL) method specifically designed for DML driven CBIR in RS. ANNEAL aims to create a small but informative training set made up of similar and dissimilar image pairs to be utilized for learning a deep metric space. The informativeness of the image pairs is assessed combining uncertainty and diversity criteria. To assess the uncertainty of image pairs, we introduce two algorithms: 1) metric-guided uncertainty estimation (MGUE); and 2) binary classifier guided uncertainty estimation (BCGUE). MGUE automatically estimates a threshold value that acts as a "boundary" between similar and dissimilar image pairs based on the distances in the metric space. The closer the similarity between image pairs to the estimated threshold value the higher their uncertainty. BCGUE estimates the uncertainty of the image pairs based on the confidence of the classifier in assigning the correct similarity label. The diversity criterion is assessed through a clustering-based strategy. ANNEAL selects the most informative image pairs by combining either MGUE or BCGUE with clustering-based strategy. The selected image pairs are sent to expert annotators to be labeled as similar or dissimilar. This way of annotating images significantly reduces the annotation cost compared to the cost of annotating images with LULC labels. Experimental results carried out on two RS benchmark datasets demonstrate the effectiveness of our method. The code of the proposed method will be publicly available upon the acceptance of the paper.
