Bidirectional Logits Tree: Pursuing Granularity Reconcilement in Fine-Grained Classification
This addresses a specific challenge in fine-grained classification tasks, offering a novel method to reconcile multi-granularity labels, though it appears incremental in nature.
The paper tackles the problem of Granularity Competition in fine-grained classification, where coarse-grained labels hinder learning of fine-grained features, by proposing the Bidirectional Logits Tree (BiLT) framework for Granularity Reconcilement, achieving improved performance as demonstrated in extensive experiments.
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 encoder. However, because coarse-grained levels are inherently easier to learn than finer ones, the base encoder tends to prioritize coarse feature abstractions, which impedes the learning of fine-grained features. To overcome this challenge, we propose a novel framework called the Bidirectional Logits Tree (BiLT) for Granularity Reconcilement. The key idea is to develop classifiers sequentially from the finest to the coarsest granularities, rather than parallelly constructing a set of classifiers based on the same input features. In this setup, the outputs of finer-grained classifiers serve as inputs for coarser-grained ones, facilitating the flow of hierarchical semantic information across different granularities. On top of this, we further introduce an Adaptive Intra-Granularity Difference Learning (AIGDL) approach to uncover subtle semantic differences between classes within the same granularity. Extensive experiments demonstrate the effectiveness of our proposed method.