Latent Space Energy-based Model for Fine-grained Open Set Recognition

TL;DR

This paper introduces a latent space energy-based model for fine-grained open-set recognition, combining generative and discriminative approaches to improve recognition of subtle class differences and unknown detection.

Contribution

It proposes a novel latent space EBM with attribute-aware information bottleneck, residual attribute feature aggregation, and virtual outlier synthesis modules for enhanced fine-grained recognition.

Findings

Effective in recognizing fine-grained classes

Generates high-resolution photo-realistic images

Improves unknown class detection

Abstract

Fine-grained open-set recognition (FineOSR) aims to recognize images belonging to classes with subtle appearance differences while rejecting images of unknown classes. A recent trend in OSR shows the benefit of generative models to discriminative unknown detection. As a type of generative model, energy-based models (EBM) are the potential for hybrid modeling of generative and discriminative tasks. However, most existing EBMs suffer from density estimation in high-dimensional space, which is critical to recognizing images from fine-grained classes. In this paper, we explore the low-dimensional latent space with energy-based prior distribution for OSR in a fine-grained visual world. Specifically, based on the latent space EBM, we propose an attribute-aware information bottleneck (AIB), a residual attribute feature aggregation (RAFA) module, and an uncertainty-based virtual outlier synthesis (UVOS) module to improve the expressivity, granularity, and density of the samples in fine-grained classes, respectively. Our method is flexible to take advantage of recent vision transformers for powerful visual classification and generation. The method is validated on both fine-grained and general visual classification datasets while preserving the capability of generating photo-realistic fake images with high resolution.