SizeNet: Object Recognition via Object Real Size-based Convolutional Networks

TL;DR

SizeNet introduces a novel object recognition framework that incorporates real object sizes alongside features, significantly improving accuracy and interpretability over existing deep learning models.

Contribution

The paper presents SizeNet, a new object recognition model that leverages real object sizes to enhance recognition accuracy and distinguish objects with similar features.

Findings

SizeNet outperforms AlexNet, VGG-16, Inception V3, Resnet-18, and DenseNet-121 in accuracy.

SizeNet effectively differentiates objects with similar features but different sizes.

Incorporating real size reduces the category label set for recognition tasks.

Abstract

Inspired by the conclusion that humans choose the visual cortex regions corresponding to the real size of an object to analyze its features when identifying objects in the real world, this paper presents a framework, SizeNet, which is based on both the real sizes and features of objects to solve object recognition problems. SizeNet was used for object recognition experiments on the homemade Rsize dataset, and was compared with the state-of-the-art methods AlexNet, VGG-16, Inception V3, Resnet-18, and DenseNet-121. The results showed that SizeNet provides much higher accuracy rates for object recognition than the other algorithms. SizeNet can solve the two problems of correctly recognizing objects with highly similar features but real sizes that are obviously different from each other, and correctly distinguishing a target object from interference objects whose real sizes are obviously different from the target object. This is because SizeNet recognizes objects based not only on their features, but also on their real size. The real size of an object can help exclude the interference object's categories whose real size ranges do not match the real size of the object, which greatly reduces the object's categories' number in the label set used for the downstream object recognition based on object features. SizeNet is of great significance for studying the interpretable computer vision. Our code and dataset will thus be made public.