论文标题
U-NET定向关系是否意识到？
Is the U-Net Directional-Relationship Aware?
论文作者
论文摘要
通常认为CNN能够使用有关其接收领域内的不同对象（例如其定向关系）的上下文信息。但是，这种能力的性质和限制从未得到充分探索。我们使用经过训练的标准U-NET探索特定类型的关系〜-定向〜-，以优化分割的跨透明损失函数。我们按照借口细分任务训练该网络，需要取得成功的方向关系推理，并指出，凭借足够的数据和足够大的接收领域，它成功地学习了所提出的任务。我们进一步探讨了网络通过分析方向关系受到干扰的方案，并表明网络已经学会了使用这些关系进行推理。
CNNs are often assumed to be capable of using contextual information about distinct objects (such as their directional relations) inside their receptive field. However, the nature and limits of this capacity has never been explored in full. We explore a specific type of relationship~-- directional~-- using a standard U-Net trained to optimize a cross-entropy loss function for segmentation. We train this network on a pretext segmentation task requiring directional relation reasoning for success and state that, with enough data and a sufficiently large receptive field, it succeeds to learn the proposed task. We further explore what the network has learned by analysing scenarios where the directional relationships are perturbed, and show that the network has learned to reason using these relationships.
