Reasoning over Vision and Language: Exploring the Benefits of Supplemental Knowledge
원문 초록
The limits of applicability of vision-and-language models are defined by the coverage of their training data. Tasks like vision question answering (VQA) often require commonsense and factual information beyond what can be learned from task-specific datasets. This paper investigates the injection of knowledge from general-purpose knowledge bases (KBs) into vision-and-language transformers. We use an auxiliary training objective that encourages the learned representations to align with graph embeddings of matching entities in a KB. We empirically study the relevance of various KBs to multiple tasks and benchmarks. The technique brings clear benefits to knowledge-demanding question answering tasks (OK-VQA, FVQA) by capturing semantic and relational knowledge absent from existing models. More surprisingly, the technique also benefits visual reasoning tasks (NLVR2, SNLI-VE). We perform probing experiments and show that the injection of additional knowledge regularizes the space of embeddings, which improves the representation of lexical and semantic similarities. The technique is model-agnostic and can expand the applicability of any vision-and-language transformer with minimal computational overhead.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Describe Anything Model for Visual Question Answering on Text-rich Images
Decoupled Seg Tokens Make Stronger Reasoning Video Segmenter and Grounder
DrishtiKon: Multi-Granular Visual Grounding for Text-Rich Document Images
HRIBench: Benchmarking Vision-Language Models for Real-Time Human Perception in Human-Robot Interaction
Adapting Lightweight Vision Language Models for Radiological Visual Question Answering
SlotPi: Physics-informed Object-centric Reasoning Models
토론
이 논문과 연결된 포럼 글이 아직 없습니다.