The partially occluded image recognition (POIR) problem has been a challenge for artificial intelligence for a long time. A common strategy to handle the POIR problem is using the non-occluded features for classification. Unfortunately, this strategy will lose effectiveness when the image is severely occluded, since the visible parts can only provide limited information. Several studies in neuroscience reveal that feature restoration which fills in the occluded information and is called amodal completion is essential for human brains to recognize partially occluded images. However, feature restoration is commonly ignored by CNNs, which may be the reason why CNNs are ineffective for the POIR problem. Inspired by this, we propose a novel brain-inspired feature restoration network (BIFRNet) to solve the POIR problem. It mimics a ventral visual pathway to extract image features and a dorsal visual pathway to distinguish occluded and visible image regions. In addition, it also uses a knowledge module to store object prior knowledge and uses a completion module to restore occluded features based on visible features and prior knowledge. Thorough experiments on synthetic and real-world occluded image datasets show that BIFRNet outperforms the existing methods in solving the POIR problem. Especially for severely occluded images, BIRFRNet surpasses other methods by a large margin and is close to the human brain performance. Furthermore, the brain-inspired design makes BIFRNet more interpretable.

翻译：部分遮挡图像识别（POIR）问题长期以来一直是人工智能领域面临的挑战。处理该问题的常见策略是利用非遮挡特征进行分类。然而，当图像被严重遮挡时，由于可见部分仅能提供有限信息，该策略将失效。神经科学的多项研究表明，特征恢复（即填补被遮挡信息，称为模态补全）是人类大脑识别部分遮挡图像的关键机制。然而，卷积神经网络普遍忽略特征恢复，这可能是其难以有效解决POIR问题的原因。受此启发，我们提出了一种新颖的脑启发式特征恢复网络（BIFRNet）来解决POIR问题。该网络模拟腹侧视觉通路提取图像特征，并模拟背侧视觉通路区分遮挡与可见图像区域。此外，它利用知识模块存储目标先验知识，并利用补全模块基于可见特征与先验知识恢复遮挡特征。在合成与真实世界遮挡图像数据集上的充分实验表明，BIFRNet在解决POIR问题方面优于现有方法。尤其在严重遮挡图像上，BIFRNet以显著优势超越其他方法，并接近人脑性能。此外，脑启发式设计使BIFRNet具有更强的可解释性。