DEFRAG: Deep Euclidean Feature Representations through Adaptation on the Grassmann Manifold

06/20/2018
by   Breton Minnehan, et al.
0

We propose a novel technique for training deep networks with the objective of obtaining feature representations that exist in a Euclidean space and exhibit strong clustering behavior. Our desired features representations have three traits: they can be compared using a standard Euclidian distance metric, samples from the same class are tightly clustered, and samples from different classes are well separated. However, most deep networks do not enforce such feature representations. The DEFRAG training technique consists of two steps: first good feature clustering behavior is encouraged though an auxiliary loss function based on the Silhouette clustering metric. Then the feature space is retracted onto a Grassmann manifold to ensure that the L_2 Norm forms a similarity metric. The DEFRAG technique achieves state of the art results on standard classification datasets using a relatively small network architecture with significantly fewer parameters than many standard networks.

READ FULL TEXT
research
10/16/2018

Learning Inward Scaled Hypersphere Embedding: Exploring Projections in Higher Dimensions

Majority of the current dimensionality reduction or retrieval techniques...
research
04/04/2022

Con^2DA: Simplifying Semi-supervised Domain Adaptation by Learning Consistent and Contrastive Feature Representations

In this work, we present Con^2DA, a simple framework that extends recent...
research
07/01/2019

Learning to aggregate feature representations

The Algonauts challenge require to construct an multi-subject encoder of...
research
07/08/2020

Fast Training of Deep Neural Networks Robust to Adversarial Perturbations

Deep neural networks are capable of training fast and generalizing well ...
research
03/21/2021

ScanMix: Learning from Severe Label Noise via Semantic Clustering and Semi-Supervised Learning

In this paper, we address the problem of training deep neural networks i...
research
12/14/2021

DeepDiffusion: Unsupervised Learning of Retrieval-adapted Representations via Diffusion-based Ranking on Latent Feature Manifold

Unsupervised learning of feature representations is a challenging yet im...
research
09/11/2015

Learning Sparse Feature Representations using Probabilistic Quadtrees and Deep Belief Nets

Learning sparse feature representations is a useful instrument for solvi...

Please sign up or login with your details

Forgot password? Click here to reset