Abstract: Hierarchical Classification (HC) exploits label hierarchies to model multi-granularity semantic dependencies and has important applications in remote-sensing and natural-image analysis. However, real-world degradations, such as noise, occlusion, blur, and low resolution, weaken fine-grained discriminative cues, making a fixed top-down prediction paradigm that always terminates at a leaf node prone to over-refinement, cross-level error propagation, and structural inconsistency. Existing methods primarily emphasize parent–child subsumption consistency, while rarely modeling mutual exclusion among categories at the same level explicitly, thereby limiting the global consistency and robustness of hierarchical predictions. To address the dynamic variation in recognizable granularity under image degradation, the separation between hierarchical-depth selection and category-path prediction, and the inability of local node scores to guarantee globally valid paths, this work further formulates hierarchical classification of degraded images as a granularity-adaptive level–path joint structured inference task. The objective is to avoid forcing every sample to a leaf node, align the predicted depth with the currently recognizable granularity, and simultaneously satisfy parent–child consistency and same-level mutual-exclusion constraints. To this end, we propose VS-HESS, a structurally consistent hierarchical classification framework for degraded scenarios. First, VS-HESS introduces an exclusion-enhanced level–category hybrid prediction paradigm that jointly predicts the deepest level at which a sample can be reliably recognized and its corresponding category path within a unified framework. Second, it incorporates a Hierarchical Exclusion Constraint Graph (HECG) and a state-space matrix to explicitly model same-level category exclusion in addition to parent–child subsumption constraints, and performs consistency-aware inference through structured normalization and marginalization. Third, a hierarchy-semantic-guided visual–semantic cross-attention module uses label-semantic embeddings to guide visual-token aggregation and learns category-specific, cross-granularity discriminative representations. Specifically, a Vision Transformer first performs global visual encoding of a degraded image. Hierarchical label embeddings are then used as queries to aggregate visual tokens in a category-conditioned manner, producing semantic-aware representations and node compatibility scores for categories at different levels. A hierarchical-depth prediction head estimates the deepest semantic level supported by the current visual evidence. On this basis, the HECG jointly represents parent–child subsumption edges and same-level exclusion edges, while the set of structurally valid paths is encoded into a state-space matrix. Consequently, the model no longer makes decisions solely from mutually independent local node scores, but instead performs structured normalization, marginal-probability computation, and final level–path joint selection within the valid path space. The model is optimized end to end using hierarchical-depth supervision, path supervision, and structural-consistency supervision, thereby unifying granularity-adaptive decision making, local category discrimination, and global structured inference in a single training process. On the HRSC-Deg and CUB-Deg degraded hierarchical datasets, VS-HESS achieves the best numerical results across all reported metrics. On HRSC-Deg, the inverse symmetric difference metric, hierarchical precision, hierarchical recall, overall level accuracy, coarse-level accuracy, and fine-level accuracy reach (72.89%), (91.53%), (91.48%), (76.05%), (99.11%), and (90.42%), respectively. On CUB-Deg, the corresponding four overall metrics and the order-, family-, and species-level accuracies reach (65.72%), (90.80%), (92.94%), (73.71%), (98.96%), (92.11%), and (81.12%), respectively. These results demonstrate that visual–semantic evidence encoding, dynamic level selection, and exclusion-enhanced valid-path inference can work synergistically to improve hierarchical path matching and medium- to fine-grained recognition under image degradation. By selecting an appropriate prediction granularity according to the semantic information retained in a degraded image and making structurally consistent decisions within a path space that satisfies both parent–child subsumption and same-level exclusion relations, VS-HESS provides an effective modeling framework for structurally consistent and granularity-adaptive hierarchical image classification across application domains such as remote-sensing ship recognition and natural-image analysis.

摘要： 层次图像分类（Hierarchical Classification，HC）通过利用标签的层级结构刻画多粒度语义依赖，在遥感与自然图像分析中具有重要应用价值。然而，真实场景中的噪声、遮挡、模糊和低分辨率等退化因素会削弱细粒度判别线索，使固定“自顶向下到叶节点”的预测范式易产生过度细化、跨层误差传播及结构不一致问题。现有方法多关注父子从属一致性，却较少显式建模同层类别间的互斥关系，因而难以保证层级预测的全局一致性与鲁棒性。针对退化条件下样本可辨识粒度随图像质量动态变化、层级深度选择与类别路径预测相互割裂，以及局部节点得分难以保证全局路径合法性等问题，本文将退化图像层次分类进一步建模为适粒度的层级–路径（level-path）联合结构化推断任务，目标是在避免强制细化至叶节点的同时，使预测深度与当前可辨识粒度相匹配，并满足父子从属一致和同层类别互斥约束。为此，本文提出一种面向退化场景的结构一致层次分类框架VS-HESS。该方法首先构建互斥增强的层级深度–类别混合预测范式，在统一框架下联合预测样本可被可靠识别的最深层级及其对应类别路径；其次，引入层级互斥图（Hierarchical Exclusion Constraint Graph，HECG）及状态空间矩阵，在父子从属约束之外显式建模同层类别互斥关系，并通过结构化归一化与边缘化实现一致性推断；最后，通过层级语义知识引导的视觉–语义交叉注意力模块，以标签语义嵌入引导视觉token聚合，学习类别特定、跨粒度的判别性表示。具体而言，视觉Transformer首先对退化图像进行全局视觉编码，层级标签语义嵌入随后作为查询，对视觉token进行类别条件化聚合，生成各层级节点的语义感知表示和节点兼容得分；层级深度预测头根据当前视觉证据估计样本能够支持的最深语义层级。在此基础上，HECG统一描述父子从属边与同层互斥边，并将满足结构约束的合法路径集合编码为状态空间矩阵，使模型不再仅依据相互独立的局部节点得分进行决策，而是在合法路径空间内完成结构化归一化、边缘化计算及最终层级–路径联合选择。模型采用层级深度监督、路径监督和结构一致性监督进行端到端联合优化，从而将适粒度决策、局部类别判别和全局结构推断统一到同一训练过程中。在HRSC-Deg和CUB-Deg两个退化层次数据集上，VS-HESS均在全部报告指标上取得最优数值结果。其中，HRSC-Deg上的逆对称差指标、层级精确率、层级召回率、整体层级准确率以及粗、细粒度准确率分别达到72.89%、91.53%、91.48%、76.05%、99.11%和90.42%；CUB-Deg上对应的4项整体指标以及目、科、种层级准确率分别达到65.72%、90.80%、92.94%、73.71%、98.96%、92.11%和81.12%。上述结果表明，视觉–语义证据编码、动态层级选择和互斥增强的合法路径推断能够协同改善退化条件下的层级路径匹配与中细粒度识别。该方法能够依据退化图像保留的语义信息选择适当的预测粒度，并在满足父子从属和同层互斥关系的路径空间中完成结构一致决策，为遥感舰船与自然图像等不同应用域中结构一致且适粒度的层次图像分类提供了一种有效建模方案。