Pattern Recognition Letters ( IF 5.1 ) Pub Date : 2021-10-06 , DOI: 10.1016/j.patrec.2021.10.004 Briti Gangopadhyay 1 , Somnath Hazra 1 , Pallab Dasgupta 1
Human vision is able to compensate imperfections in sensory inputs from the real world by reasoning based on prior knowledge about the world. Deep learning has had a significant impact on computer vision due to its inherent ability in handling imprecision, but the absence of a reasoning framework based on domain knowledge limits its ability to interpret complex scenarios. We propose semi-lexical languages as a formal basis for reasoning with imperfect tokens provided by the real world. The power of deep learning is used to map the imperfect tokens into the alphabet of the language, and symbolic reasoning is used to determine the membership of input in the language. Semi-lexical languages have bindings that prevent the variations in which a semi-lexical token is interpreted in different parts of the input, thereby leaning on deduction to enhance the quality of recognition of individual tokens. We present case studies that demonstrate the advantage of using such a framework over pure deep learning and pure symbolic methods.
中文翻译:
半词汇语言:使用领域知识解决基于深度学习的计算机视觉中的歧义的正式基础
人类视觉能够通过基于对世界的先验知识的推理来补偿来自现实世界的感官输入的缺陷。由于其固有的处理不精确性的能力,深度学习对计算机视觉产生了重大影响,但缺乏基于领域知识的推理框架限制了其解释复杂场景的能力。我们提出半词汇语言作为推理的正式基础,用现实世界提供的不完美标记进行推理。深度学习的力量用于将不完美的标记映射到语言的字母表中,并使用符号推理来确定语言中输入的成员资格。半词法语言具有绑定,可以防止在输入的不同部分解释半词法标记的变化,从而依靠演绎来提高个体令牌的识别质量。我们提供的案例研究证明了使用这种框架相对于纯深度学习和纯符号方法的优势。