Cognitive Visual Commonsense Reasoning Using Dynamic Working Memory
This addresses a lack of generalizability and prior knowledge in VCR, which has applications in areas like visual question answering and automated systems, but the approach appears incremental as it builds on existing memory-based methods.
The paper tackles the Visual Commonsense Reasoning (VCR) task by proposing a dynamic working memory network to incorporate prior knowledge, achieving significant improvements over existing methods on the benchmark dataset.
Visual Commonsense Reasoning (VCR) predicts an answer with corresponding rationale, given a question-image input. VCR is a recently introduced visual scene understanding task with a wide range of applications, including visual question answering, automated vehicle systems, and clinical decision support. Previous approaches to solving the VCR task generally rely on pre-training or exploiting memory with long dependency relationship encoded models. However, these approaches suffer from a lack of generalizability and prior knowledge. In this paper we propose a dynamic working memory based cognitive VCR network, which stores accumulated commonsense between sentences to provide prior knowledge for inference. Extensive experiments show that the proposed model yields significant improvements over existing methods on the benchmark VCR dataset. Moreover, the proposed model provides intuitive interpretation into visual commonsense reasoning. A Python implementation of our mechanism is publicly available at https://github.com/tanjatang/DMVCR