Conventional object detection models require large amounts of training data.
In comparison, humans can recognize previously unseen objects by merely knowing
their semantic description. To mimic similar behaviour, zero-shot object
detection aims to recognize and localize 'unseen' object instances by using
only their semantic information. The model is first trained to learn the
relationships between visual and semantic domains for seen objects, later
transferring the acquired knowledge to totally unseen objects. This setting
gives rise to the need for correct alignment between visual and semantic
concepts, so that the unseen objects can be identified using only their
semantic attributes. In this paper, we propose a novel loss function called
'Polarity loss', that promotes correct visual-semantic alignment for an
improved zero-shot object detection. On one hand, it refines the noisy semantic
embeddings via metric learning on a 'Semantic vocabulary' of related concepts
to establish a better synergy between visual and semantic domains. On the other
hand, it explicitly maximizes the gap between positive and negative predictions
to achieve better discrimination between seen, unseen and background objects.
Our approach is inspired by embodiment theories in cognitive science, that
claim human semantic understanding to be grounded in past experiences (seen
objects), related linguistic concepts (word vocabulary) and visual perception
(seen/unseen object images). We conduct extensive evaluations on MS-COCO and
Pascal VOC datasets, showing significant improvements over state of the art.

本文提出了一种名为 “Polarity loss” 的新型 Loss 函数，通过度量学习来优化 “语义词汇表” 上的噪声语义嵌入，从而改进了零样本目标检测中的视觉 - 语义对齐，同时通过显式地最大化正负预测之间的差距，达到更好的差别化效果。