Learning Inward Scaled Hypersphere Embedding: Exploring Projections in Higher Dimensions

Abstract

Majority of the current dimensionality reduction or retrieval techniques rely on embedding the learned feature representations onto a computable metric space. Once the learned features are mapped, a distance metric aids the bridging of gaps between similar instances. Since the scaled projection is not exploited in these methods, discriminative embedding onto a hyperspace becomes a challenge. In this paper, we propose to inwardly scale feature representations in proportional to projecting them onto a hypersphere manifold for discriminative analysis. We further propose a novel, yet simpler, convolutional neural network based architecture and extensively evaluate the proposed methodology in the context of classification and retrieval tasks obtaining results comparable to state-of-the-art techniques.

References in corpus (9)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Wide Residual Networks
• Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks
• Random Erasing Data Augmentation
• High-Performance Neural Networks for Visual Object Classification
• Image-Text Multi-Modal Representation Learning by Adversarial Backpropagation
• Git Loss for Deep Face Recognition
• Revisiting Cross Modal Retrieval