Divide-and-Conquer Approach to Holistic Cognition in High-Similarity Contexts with Limited Data

TL;DR

This paper introduces DHCNet, a divide-and-conquer neural network that enhances ultra-fine-grained visual categorization by effectively modeling holistic cues with limited data, leading to improved recognition of highly similar subcategories.

Contribution

The paper proposes a novel divide-and-conquer strategy and a self-shuffling operation to model holistic cues with less training data in ultra-fine-grained classification.

Findings

DHCNet achieves state-of-the-art results on five Ultra-FGVC datasets.

The method effectively captures holistic cues with limited data.

Performance improvements are significant compared to existing approaches.

Abstract

Ultra-fine-grained visual categorization (Ultra-FGVC) aims to classify highly similar subcategories within fine-grained objects using limited training samples. However, holistic yet discriminative cues, such as leaf contours in extremely similar cultivars, remain under-explored in current studies, thereby limiting recognition performance. Though crucial, modeling holistic cues with complex morphological structures typically requires massive training samples, posing significant challenges in data-limited scenarios. To address this challenge, we propose a novel Divide-and-Conquer Holistic Cognition Network (DHCNet) that implements a divide-and-conquer strategy by decomposing holistic cues into spatially-associated subtle discrepancies and progressively establishing the holistic cognition process, significantly simplifying holistic cognition while reducing dependency on training data. Technically, DHCNet begins by progressively analyzing subtle discrepancies, transitioning from smaller local patches to larger ones using a self-shuffling operation on local regions. Simultaneously, it leverages the unaffected local regions to potentially guide the perception of the original topological structure among the shuffled patches, thereby aiding in the establishment of spatial associations for these discrepancies. Additionally, DHCNet incorporates the online refinement of these holistic cues discovered from local regions into the training process to iteratively improve their quality. As a result, DHCNet uses these holistic cues as supervisory signals to fine-tune the parameters of the recognition model, thus improving its sensitivity to holistic cues across the entire objects. Extensive evaluations demonstrate that DHCNet achieves remarkable performance on five widely-used Ultra-FGVC datasets.