SIMILARnet: Simultaneous Intelligent Localization and Recognition Network

TL;DR

SIMILARnet introduces a biologically inspired, size-insensitive model that simultaneously localizes and recognizes objects in images without requiring separate training, reducing computational costs.

Contribution

It presents a novel architecture leveraging convolutional filters' position information for simultaneous localization and recognition without differential connections or separate training.

Findings

Achieves promising localization and recognition results.

Not sensitive to input image size.

Reduces computation overhead compared to existing methods.

Abstract

Global Average Pooling (GAP) [4] has been used previously to generate class activation for image classification tasks. The motivation behind SIMILARnet comes from the fact that the convolutional filters possess position information of the essential features and hence, combination of the feature maps could help us locate the class instances in an image. We propose a biologically inspired model that is free of differential connections and doesn't require separate training thereby reducing computation overhead. Our novel architecture generates promising results and unlike existing methods, the model is not sensitive to the input image size, thus promising wider application. Codes for the experiment and illustrations can be found at: https://github.com/brcsomnath/Advanced-GAP .