We aim to provide a computationally cheap yet effective approach for fine-grained image classification (FGIC) in this letter. Unlike previous methods that rely on complex part localization modules, our approach learns fine-grained features by enhancing the semantics of sub-features of a global feature. Specifically, we first achieve the sub-feature semantic by arranging feature channels of a CNN into different groups through channel permutation. Meanwhile, to enhance the discriminability of sub-features, the groups are guided to be activated on object parts with strong discriminability by a weighted combination regularization. Our approach is parameter parsimonious and can be easily integrated into the backbone model as a plug-and-play module for end-to-end training with only image-level supervision. Experiments verified the effectiveness of our approach and validated its comparable performance to the state-of-the-art methods. Code is available at https://github.com/cswluo/SEF.

中文翻译：

---

为细粒度图像分类学习语义增强特征

我们的目标是在这封信中为细粒度图像分类 (FGIC) 提供一种计算上便宜但有效的方法。与以前依赖复杂部分定位模块的方法不同，我们的方法通过增强全局特征的子特征的语义来学习细粒度特征。具体来说，我们首先通过通道排列将 CNN 的特征通道排列成不同的组来实现子特征语义。同时，为了增强子特征的可辨别性，通过加权组合正则化，引导组在可辨别性强的对象部分上被激活。我们的方法参数简洁，可以轻松集成到主干模型中，作为即插即用模块，仅在图像级监督下进行端到端训练。实验验证了我们方法的有效性，并验证了其与最先进方法的可比性能。代码可在 https://github.com/cswluo/SEF 获得。