AI 中文总结
针对细粒度水生物种识别难题，提出FISHER梯度解耦分层多任务学习框架，通过单向信息流和梯度解耦防止负迁移，引入特定分割头及加权方式，实验表明其有效提升未见过特征识别精度和超稀有物种分类准确率。
AI 中文摘要
细粒度水生物种识别具有挑战性，因其形态差异细微且分布长尾，超稀有物种代表性不足。自然的解决方案是在多任务学习（MTL）框架中联合建模分割、形态特征和物种分类。然而，现有MTL方法因低级密集任务和高级分类目标之间的梯度冲突而存在负迁移，降低了细粒度表示。为解决此限制，我们将分层任务间的梯度干扰识别为基本瓶颈，并提出FISHER，一种梯度解耦分层多任务学习框架。FISHER通过强制从分割到特征预测再到物种分类的单向信息流，使优化与水生物种的生物层次对齐，同时明确解耦跨任务边界的梯度。这种设计防止高级目标破坏低级形态表示，有效减轻负迁移，同时保留共享监督的好处。此外，我们引入具有正交正则化的基于原型的分割头，以鼓励解缠的解剖学表示，并采用同方差不确定性加权在训练期间动态平衡任务贡献。我们的分析表明，强大的特征表示是将知识转移到超稀有物种的关键桥梁。在Fish-Vista基准上的广泛实验表明，FISHER实现了97.7%的未见过特征识别平均精度，比强大的基线提高了13.4%的超稀有物种分类准确率，突出了梯度解耦分层学习对长尾生物多样性识别的有效性。
英文摘要
Fine-grained recognition of aquatic species is challenging due to subtle morphological differences and long-tailed distributions, where ultra-rare species are underrepresented. A natural solution is to jointly model segmentation, morphological traits, and species classification within a multi-task learning (MTL) framework. However, existing MTL methods suffer from negative transfer caused by gradient conflicts between low-level dense tasks and high-level classification objectives, degrading fine-grained representations. To address this limitation, we identify gradient interference across hierarchical tasks as a fundamental bottleneck and propose FISHER, a gradient-decoupled hierarchical multi-task learning framework. FISHER aligns optimization with the biological hierarchy of aquatic species by enforcing a unidirectional information flow from segmentation to trait prediction and finally to species classification, while explicitly decoupling gradients across task boundaries. This design prevents high-level objectives from corrupting low-level morphological representations, effectively mitigating negative transfer while preserving the benefits of shared supervision. Furthermore, we introduce a prototypebased segmentation head with orthogonality regularization to encourage disentangled anatomical representations, and employ homoscedastic uncertainty weighting to dynamically balance task contributions during training. Our analysis shows that robust trait representations serve as a critical bridge for transferring knowledge to ultra-rare species. Extensive experiments on the Fish-Vista benchmark demonstrate that FISHER achieves 97.7% mAP for trait identification on unseen species and improves ultra-rare species classification accuracy by 13.4% over strong baselines, highlighting the effectiveness of gradient-decoupled hierarchical learning for long-tailed biodiversity recognition.
CommentsSubmitted for IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (16 pages, 12 Figures, 15 Tables). Project page: https://phucngvinuni.github.io/FISHER/
