DeepAI AI Chat
Log In Sign Up

Fashion Image Retrieval with Capsule Networks

by   Furkan Kınlı, et al.

In this study, we investigate in-shop clothing retrieval performance of densely-connected Capsule Networks with dynamic routing. To achieve this, we propose Triplet-based design of Capsule Network architecture with two different feature extraction methods. In our design, Stacked-convolutional (SC) and Residual-connected (RC) blocks are used to form the input of capsule layers. Experimental results show that both of our designs outperform all variants of the baseline study, namely FashionNet, without relying on the landmark information. Moreover, when compared to the SOTA architectures on clothing retrieval, our proposed Triplet Capsule Networks achieve comparable recall rates only with half of parameters used in the SOTA architectures.


Investigating Capsule Networks with Dynamic Routing for Text Classification

In this study, we explore capsule networks with dynamic routing for text...

Multi-Kernel Capsule Network for Schizophrenia Identification

Objective: Schizophrenia seriously affects the quality of life. To date,...

WCE Polyp Detection with Triplet based Embeddings

Wireless capsule endoscopy is a medical procedure used to visualize the ...

A Context-aware Capsule Network for Multi-label Classification

Recently proposed Capsule Network is a brain inspired architecture that ...

Wasserstein Routed Capsule Networks

Capsule networks offer interesting properties and provide an alternative...

Momentum Capsule Networks

Capsule networks are a class of neural networks that achieved promising ...

ASPCNet: A Deep Adaptive Spatial Pattern Capsule Network for Hyperspectral Image Classification

Previous studies have shown the great potential of capsule networks for ...