经常性反馈改进了对部分封闭物体的确认 (Recurrent Feedback Improves Recognition of Partially Occluded Objects)

from arxiv, 6 pages, 2 figures, 28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2020). arXiv admin note: substantial text overlap with arXiv:1909.06175

Recurrent connectivity in the visual cortex is believed to aid object recognition for challenging conditions such as occlusion. Here we investigate if and how artificial neural networks also benefit from recurrence. We compare architectures composed of bottom-up, lateral and top-down connections and evaluate their performance using two novel stereoscopic occluded object datasets. We find that classification accuracy is significantly higher for recurrent models when compared to feedforward models of matched parametric complexity. Additionally we show that for challenging stimuli, the recurrent feedback is able to correctly revise the initial feedforward guess.

翻译：视觉皮层的经常性连接被认为有助于识别具有挑战性的条件, 如隐蔽等。我们在这里调查人工神经网络是否以及如何从重现中受益。我们比较由自下而上、横向和自下而下连接组成的结构, 并使用两个新型的立体隐形天体数据集来评估它们的性能。我们发现, 相对于相匹配的参数复杂性的进化模型, 经常模型的分类准确性要高得多。此外, 我们显示, 具有挑战性的 Stimuli, 重复的反馈能够正确修改初始的进化前猜想。