[论文解读] Group based deep shared feature learning for fine-grained image classification

Xuelu Li, Vishal Monga|arXiv (Cornell University)|Apr 4, 2020

Advanced Image and Video Retrieval Techniques被引用 10

一句话总结

该论文提出GSFL-Net，一种基于分组的深度共享特征学习框架，通过使用带有特征表达损失的约束自编码器，将特征分解为共享和判别性成分。在推理过程中移除共享特征后，该方法在基准数据集上提升了细粒度分类的准确率，同时增强了模型的可解释性，优于当前最先进方法。

ABSTRACT

Fine-grained image classification has emerged as a significant challenge because objects in such images have small inter-class visual differences but with large variations in pose, lighting, and viewpoints, etc. Most existing work focuses on highly customized feature extraction via deep network architectures which have been shown to deliver state of the art performance. Given that images from distinct classes in fine-grained classification share significant features of interest, we present a new deep network architecture that explicitly models shared features and removes their effect to achieve enhanced classification results. Our modeling of shared features is based on a new group based learning wherein existing classes are divided into groups and multiple shared feature patterns are discovered (learned). We call this framework Group based deep Shared Feature Learning (GSFL) and the resulting learned network as GSFL-Net. Specifically, the proposed GSFL-Net develops a specially designed autoencoder which is constrained by a newly proposed Feature Expression Loss to decompose a set of features into their constituent shared and discriminative components. During inference, only the discriminative feature component is used to accomplish the classification task. A key benefit of our specialized autoencoder is that it is versatile and can be combined with state-of-the-art fine-grained feature extraction models and trained together with them to improve their performance directly. Experiments on benchmark datasets show that GSFL-Net can enhance classification accuracy over the state of the art with a more interpretable architecture.

研究动机与目标

• 解决细粒度图像分类中的挑战，即类间微小视觉差异与类内大范围变化导致的准确识别困难。
• 克服现有方法依赖高度定制化网络结构、未显式建模跨类别共享视觉模式的局限性。
• 开发一种统一的深度学习框架，显式学习并移除共享特征，以增强细粒度分类的判别能力。
• 通过设计可与现有模型联合训练的通用自编码器，实现与当前最先进特征提取器的兼容性，从而提升性能。
• 通过隔离并丢弃共享特征，在推理过程中仅依赖判别性成分，提升模型可解释性。

提出的方法

• 将现有的细粒度类别分组聚类，以识别多个类别之间的共享视觉模式。
• 设计一种专用的自编码器架构，将输入特征分解为共享和判别性成分。
• 引入一种新型特征表达损失，约束自编码器，确保共享与判别性特征的准确分解。
• 与预训练的特征提取器联合端到端训练自编码器，实现联合优化并获得性能提升。
• 在推理阶段，仅使用判别性特征成分进行分类，丢弃共享特征以减少歧义。
• 将该框架应用于多个基准数据集，验证其在多样化细粒度识别任务中的泛化能力与性能提升。

实验结果

研究问题

• RQ1 显式建模并移除共享视觉特征是否能提升细粒度图像识别的分类准确率？
• RQ2 基于分组的类别聚类在识别细粒度类别间有意义的共享特征模式方面有多有效？
• RQ3 带有特征表达损失的约束自编码器在多大程度上能将特征分解为共享与判别性成分？
• RQ4 所提出的GSFL-Net能否无缝集成到现有最先进特征提取器中以提升其性能？
• RQ5 移除共享特征是否能带来更具可解释性与鲁棒性的分类模型？

主要发现

• GSFL-Net在基准细粒度图像分类数据集上的分类准确率高于当前最先进方法。
• 在推理过程中移除共享特征显著降低了视觉相似类别之间的混淆。
• 所提出的特征表达损失能有效引导自编码器以高保真度解耦共享与判别性成分。
• 该框架可与多种深度特征提取器兼容，集成后可直接获得性能提升。
• 模型架构更具可解释性，因为所学习的判别性特征直接决定了分类决策。
• 实验结果证实，基于分组的类别聚类能有效促进有意义共享特征模式的发现，从而提升整体泛化能力。