A Deep Positive-Negative Prototype Approach to Integrated Prototypical Discriminative Learning

TL;DR

This paper introduces a Deep Positive-Negative Prototype (DPNP) model that unifies prototype-based and discriminative learning to enhance class separation and interpretability in deep neural networks, achieving competitive accuracy with smaller models.

Contribution

The paper proposes a novel DPNP model that unifies class prototypes with weight vectors, creating a structured latent space for improved classification and interpretability.

Findings

DPNP outperforms state-of-the-art models on several datasets.

DPNP achieves high accuracy with smaller networks.

Prototypes are organized in nearly regular positions in feature space.

Abstract

This paper proposes a novel Deep Positive-Negative Prototype (DPNP) model that combines prototype-based learning (PbL) with discriminative methods to improve class compactness and separability in deep neural networks. While PbL traditionally emphasizes interpretability by classifying samples based on their similarity to representative prototypes, it struggles with creating optimal decision boundaries in complex scenarios. Conversely, discriminative methods effectively separate classes but often lack intuitive interpretability. Toward exploiting advantages of these two approaches, the suggested DPNP model bridges between them by unifying class prototypes with weight vectors, thereby establishing a structured latent space that enables accurate classification using interpretable prototypes alongside a properly learned feature representation. Based on this central idea of unified prototype-weight representation, Deep Positive Prototype (DPP) is formed in the latent space as a representative for each class using off-the-shelf deep networks as feature extractors. Then, rival neighboring class DPPs are treated as implicit negative prototypes with repulsive force in DPNP, which push away DPPs from each other. This helps to enhance inter-class separation without the need for any extra parameters. Hence, through a novel loss function that integrates cross-entropy, prototype alignment, and separation terms, DPNP achieves well-organized feature space geometry, maximizing intra-class compactness and inter-class margins. We show that DPNP can organize prototypes in nearly regular positions within feature space, such that it is possible to achieve competitive classification accuracy even in much lower-dimensional feature spaces. Experimental results on several datasets demonstrate that DPNP outperforms state-of-the-art models, while using smaller networks.