Abstract One-class classification (OCC) is a classical problem in computer vision that can be described as the task of classifying outlier class samples (OC samples) from the OCC model trained on inlier class samples (IC samples) when datasets are highly biased toward one class due to the insufficient sample size of the other class. Currently, the adversarial learning OCC (ALOCC) method has been proven to significantly improve OCC performance. However, its drawbacks include instability issues and non-evident reconstruction between the IC and OC samples. Therefore, we propose multihead enhanced self-attention in the ALOCC network, thereby increasing the difference between the IC and OC samples and significantly increasing OCC accuracy compared with ALOCC accuracy. For training, we propose a new loss, called adversarial-balance loss, that effectively solves the training instability problem, further increasing OCC accuracy. The experiments show the effectiveness of the proposed method compared with state-of-art methods.

中文翻译：

---

用于新颖性检测的多头增强自注意力网络

摘要 一类分类 (OCC) 是计算机视觉中的一个经典问题，可以描述为当数据集高度偏向于在内部类样本 (IC 样本) 上训练的 OCC 模型中对异常类样本 (OC 样本) 进行分类的任务。一类是由于另一类的样本量不足。目前，对抗性学习 OCC（ALOCC）方法已被证明可以显着提高 OCC 性能。然而，它的缺点包括不稳定问题和 IC 和 OC 样本之间的非明显重建。因此，我们在 ALOCC 网络中提出多头增强自注意力，从而增加 IC 和 OC 样本之间的差异，并与 ALOCC 精度相比显着提高 OCC 精度。对于训练，我们提出了一种新的损失，称为对抗性平衡损失，有效解决了训练不稳定的问题，进一步提高了OCC的准确率。实验表明，与最先进的方法相比，所提出的方法是有效的。