Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classification
Keywords:Scene Analysis & Understanding, Applications, Image and Video Retrieval, Object Detection & Categorization
AbstractDeep convolutional neural networks (CNNs) have shown a strong ability in mining discriminative object pose and parts information for image recognition. For fine-grained recognition, context-aware rich feature representation of object/scene plays a key role since it exhibits a significant variance in the same subcategory and subtle variance among different subcategories. Finding the subtle variance that fully characterizes the object/scene is not straightforward. To address this, we propose a novel context-aware attentional pooling (CAP) that effectively captures subtle changes via sub-pixel gradients, and learns to attend informative integral regions and their importance in discriminating different subcategories without requiring the bounding-box and/or distinguishable part annotations. We also introduce a novel feature encoding by considering the intrinsic consistency between the informativeness of the integral regions and their spatial structures to capture the semantic correlation among them. Our approach is simple yet extremely effective and can be easily applied on top of a standard classification backbone network. We evaluate our approach using six state-of-the-art (SotA) backbone networks and eight benchmark datasets. Our method significantly outperforms the SotA approaches on six datasets and is very competitive with the remaining two.
How to Cite
Behera, A., Wharton, Z., Hewage, P. R. P. G., & Bera, A. (2021). Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classification. Proceedings of the AAAI Conference on Artificial Intelligence, 35(2), 929-937. https://doi.org/10.1609/aaai.v35i2.16176
AAAI Technical Track on Computer Vision I