Distance Based Image Classification: A Solution To Generative Classification's Conundrum?

Abstract

Most classifiers rely on discriminative boundaries that separate instances of each class from everything else. We argue that discriminative boundaries are counter-intuitive as they define semantics by what-they-are-not; and should be replaced by generative classifiers which define semantics by what-they-are. Unfortunately, generative classifiers are significantly less accurate. This may be caused by the tendency of generative models to focus on easy to model semantic generative factors and ignore non-semantic factors that are important but difficult to model. We propose a new generative model in which semantic factors are accommodated by shell theory's hierarchical generative process and non-semantic factors by an instance specific noise term. We use the model to develop a classification scheme which suppresses the impact of noise while preserving semantic cues. The result is a surprisingly accurate generative classifier, that takes the form of a modified nearest-neighbor algorithm; we

Stats

• citations4
• S2 citations—
• github stars0
• HF likes0
• heat score5.24
• arxiv keylin2022distance

Related papers

• Unsupervised Feature Learning Via Non-parametric Instance-level Discrimination (2018)25.66
• On High-dimensional Modifications Of The Nearest Neighbor Classifier (2024)0.00
• Deep Metric Learning And Image Classification With Nearest Neighbour Gaussian Kernels (2017)9.41
• Improving The Accuracy Of Nearest-neighbor Classification Using Principled Construction And Stochastic Sampling Of Training-set Centroids (2018)0.00
• Binary Generative Adversarial Networks For Image Retrieval (2017)18.34
• Bingan: Learning Compact Binary Descriptors With A Regularized GAN (2018)0.00
• Drop The GAN: In Defense Of Patches Nearest Neighbors As Single Image Generative Models (2021)12.87
• Hierarchy-based Image Embeddings For Semantic Image Retrieval (2018)13.84