# SwiDeN : Convolutional Neural Networks For Depiction Invariant Object Recognition Source: [SwiDeN : Convolutional Neural Networks For Depiction Invariant Object Recognition]() Collection index: [llms.txt]() Data updated: 2025-12-25T02:16:20.149Z Authors: Ravi Kiran Sarvadevabhatla, Shiv Surya, Srinivas S S Kruthiventi, Venkatesh Babu R Published: 2016-07-29T11:00:08.000Z ## Abstract Current state of the art object recognition architectures achieve impressive performance but are typically specialized for a single depictive style (e.g. photos only, sketches only). In this paper, we present SwiDeN : our Convolutional Neural Network (CNN) architecture which recognizes objects regardless of how they are visually depicted (line drawing, realistic shaded drawing, photograph etc.). In SwiDeN, we utilize a novel \`deep' depictive style-based switching mechanism which appropriately addresses the depiction-specific and depiction-invariant aspects of the problem. We compare SwiDeN with alternative architectures and prior work on a 50-category Photo-Art dataset containing objects depicted in multiple styles. Experimental results show that SwiDeN outperforms other approaches for the depiction-invariant object recognition problem. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Object Classification on Photo-Art-50 (test)](): Object Classification; Photo-Art-50 (test); Overall Accuracy: 94.42. - [Image Classification on Photo-Art-50 (train-test)](): Image Classification; Photo-Art-50 (train-test); Overall Accuracy: 93.02. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()