基于语义匹配的歧义相似条件识别
Identifying Ambiguous Similarity Conditions via Semantic Matching
摘要：
图像内部丰富的语义导致了图像与其他图像之间的模糊关系，即，两个图像在一种情况下可能相似，但在另一种情况下可能不同。假设“aircraft”与“bird”的相似度大于“训练”，弱监督条件相似性学习（WS-CSL）学习多个嵌入来匹配语义条件，而不需要“can fly”等显式条件标签。然而，三元组中的相似性关系是不确定的，除非提供一个条件。例如，一旦条件标签变为“is vehicle”，先前的比较就变得无效。为此，我们引入了一种新的评估标准，通过将学习到的嵌入分配到其最佳条件后预测比较的正确性，该标准衡量了WS-CSL作为监督模型可以覆盖多少潜在语义。此外，我们提出了距离诱导的语义条件验证网络（DiscoverNet），它的特点是在一个“分解和融合”的方式的实例-实例和三元组-条件关系。为了使学习的嵌入覆盖所有语义，DiscoverNet在三元组和条件之间的对应关系上使用了一个集合模块或额外的正则化器。DiscoverNet在UT-Zappos-50 k和Celeb-A w.r.t.等基准测试中达到了最先进的性能。不同的标准
英文摘要：
Rich semantics inside an image result in its ambiguous relationship with others, i.e., two images could be similar in one condition but dissimilar in another. Given triplets like "aircraft" is similar to "bird" than "train", Weakly Supervised Conditional Similarity Learning (WS-CSL) learns multiple embeddings to match semantic conditions without explicit condition labels such as "can fly". However, similarity relationships in a triplet are uncertain except providing a condition. For example, the previous comparison becomes invalid once the conditional label changes to "is vehicle". To this end, we introduce a novel evaluation criterion by predicting the comparison's correctness after assigning the learned embeddings to their optimal conditions, which measures how much WS-CSL could cover latent semantics as the supervised model. Furthermore, we propose the Distance Induced Semantic COndition VERification Network (DiscoverNet), which characterizes the instance-instance and triplets-condition relations in a "decompose-and-fuse" manner. To make the learned embeddings cover all semantics, DiscoverNet utilizes a set module or an additional regularizer over the correspondence between a triplet and a condition. DiscoverNet achieves state-of-the-art performance on benchmarks like UT-Zappos-50k and Celeb-A w.r.t. different criteria.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
