Learning local representations is important for face recognition (FR). Recent attention-based networks emphasize few facial parts, while ignoring other potentially discriminative ones. This is more serious when there are large pose variations, occlusions (e.g. face masks), or other image quality changes. To address this, we propose Diverse and Sparse Attentions, called DSA-Face. First, a divergence loss is designed to explicitly encourage the diversity among multiple attention maps by maximizing the Euclidean distance between every pair attention maps. As a result, a Pairwise Self-Contrastive Attention (PSCA) is developed to locate diverse facial parts which provide comprehensive descriptions. Second, an Attention Sparsity Loss (ASL) is proposed to encourage sparse responses in attention maps where only discriminative parts are emphasized while distracted regions (e.g. background or face masks) are discouraged. Built upon the PSCA and ASL, the DSA-Face model is developed to learn diverse and sparse attentions, which can extract diverse discriminative local representations and suppress the focus on noisy regions. Due to the pandemic of the COVID-19, the task of masked face matching is now very important, and our model can handle this much better than previous methods, demonstrating its effectiveness and usefulness. Moreover, our model outperforms the state-of-the-art methods on several other FR benchmarks, showing that it is also general to address various challenges in FR.

中文翻译：

---

DSA-Face：人脸识别的多样化和稀疏关注对姿势变化和遮挡具有鲁棒性


学习局部表征对于人脸识别（FR）非常重要。最近基于注意力的网络强调少数面部部位，而忽略其他潜在的歧视性部位。当存在较大的姿势变化、遮挡（例如面罩）或其他图像质量变化时，这种情况更为严重。为了解决这个问题，我们提出了多样化和稀疏注意力，称为 DSA-Face。首先，散度损失旨在通过最大化每对注意力图之间的欧几里得距离来明确鼓励多个注意力图之间的多样性。因此，开发了成对自我对比注意（PSCA）来定位提供全面描述的不同面部部位。其次，提出了注意力稀疏损失（ASL）来鼓励注意力图中的稀疏响应，其中仅强调有区别的部分，而不鼓励分散注意力的区域（例如背景或面罩）。 DSA-Face 模型建立在 PSCA 和 ASL 的基础上，旨在学习多样化和稀疏的注意力，它可以提取多样化的判别性局部表示并抑制对噪声区域的关注。由于COVID-19的流行，蒙面人脸匹配的任务现在非常重要，我们的模型可以比以前的方法更好地处理这个问题，证明了它的有效性和实用性。此外，我们的模型在其他几个 FR 基准上的表现优于最先进的方法，这表明它对于解决 FR 中的各种挑战也是通用的。