Learning Inward Scaled Hypersphere Embedding: Exploring Projections in Higher Dimensions
This work addresses a domain-specific problem in dimensionality reduction and retrieval for researchers and practitioners, but it is incremental as it builds on existing techniques.
The paper tackles the challenge of discriminative embedding in hyperspace by proposing inward scaling of feature representations proportional to their projection onto a hypersphere manifold, achieving results comparable to state-of-the-art in classification and retrieval tasks.
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.