← Search

Zhiguang Lu

2 accepted papers

2026

HiGFA: Hierarchical Guidance for Fine-grained Data Augmentation with Diffusion Models

AAAI 2026technical

Generative diffusion models show promise for data augmentation. However, applying them to fine-grained tasks presents a significant challenge: ensuring synthetic images accurately capture the subtle, category-defining features critical for high fidelity. Standard approaches, such as text-based Class

Cited by 0SourcePDFScholar
2025

Bidirectional Logits Tree: Pursuing Granularity Reconcilement in Fine-Grained Classification

AAAI 2025technical

This paper addresses the challenge of Granularity Competition in fine-grained classification tasks, which arises due to the semantic gap between multi-granularity labels. Existing approaches typically develop independent hierarchy-aware models based on shared features extracted from a common base en…