Learning Entropy Signature for Image Representation and Classification
For image classification tasks, this work provides a novel descriptor that leverages neural network learning dynamics to capture information-relevant image structures, though the improvements over existing methods are not quantified.
The paper introduces Learning Entropy Signatures (LES), a compact image descriptor derived from Spatial Learning Entropy Maps (SLEMs) by selecting the K largest learning entropy locations. Experiments on image classification show that a small number of such locations preserve substantial discriminative information, demonstrating the utility of learning entropy for image representation.
Learning Entropy (LE) has recently been extended to image analysis through Spatial Learning Entropy Maps (SLEMs), which are two-dimensional LE distributions that highlight unusually high learning activity across an image. Unlike conventional image descriptors, SLEMs are generated by incremental, sample-wise learning of a pretrained feedforward MLP network, where local pixel neighborhoods are presented sequentially in a fixed spatial order to predict the corresponding central pixels. Consequently, the learning activity at each image location depends not only on its local structure but also on the knowledge acquired from previously processed locations. This paper introduces Learning Entropy Signatures (LES), an image descriptor derived from SLEM using the K largest LE locations. LES captures the spatial organization of learning-relevant image structures and provides a compact representation of image content based on learning weight behavior. Experimental evaluation on image classification tasks shows that a relatively small number of K largest LE locations preserve substantial discriminative information. The results indicate a close relationship between the learning of neural weights and information relevance, extending the role of Learning Entropy from time series to images and, within images, from structural point extraction to compact image representation and classification.