论文标题
通过神经视觉关注模拟人类的凝视
Simulating Human Gaze with Neural Visual Attention
论文作者
论文摘要
现有的人类视觉关注模型通常无法纳入直接的任务指导，因此在探索场景时无法建模意图或目标。为了将任何下游视觉任务的引导纳入注意力建模，我们提出了神经视觉注意（NEVA）算法。为此，我们强加了神经网络，即视觉的生物学约束，并训练注意机制，以产生视觉探索，以最大程度地提高下游任务的性能。我们观察到，生物学上受约束的神经网络会产生类似人类的扫描路径，而不会接受该目标的训练。在三个常见基准数据集上进行的广泛实验表明，我们的方法在产生类似人类的扫描过程中优于最先进的人类注意力模型。
Existing models of human visual attention are generally unable to incorporate direct task guidance and therefore cannot model an intent or goal when exploring a scene. To integrate guidance of any downstream visual task into attention modeling, we propose the Neural Visual Attention (NeVA) algorithm. To this end, we impose to neural networks the biological constraint of foveated vision and train an attention mechanism to generate visual explorations that maximize the performance with respect to the downstream task. We observe that biologically constrained neural networks generate human-like scanpaths without being trained for this objective. Extensive experiments on three common benchmark datasets show that our method outperforms state-of-the-art unsupervised human attention models in generating human-like scanpaths.
