On the use of human reference data for evaluating automatic image descriptions
원문 초록
Automatic image description systems are commonly trained and evaluated using crowdsourced, human-generated image descriptions. The best-performing system is then determined using some measure of similarity to the reference data (BLEU, Meteor, CIDER, etc). Thus, both the quality of the systems as well as the quality of the evaluation depends on the quality of the descriptions. As Section 2 will show, the quality of current image description datasets is insufficient. I argue that there is a need for more detailed guidelines that take into account the needs of visually impaired users, but also the feasibility of generating suitable descriptions. With high-quality data, evaluation of image description systems could use reference descriptions, but we should also look for alternatives.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Text-Visual Semantic Constrained AI-Generated Image Quality Assessment
Mitigating Hallucinations in Vision-Language Models through Image-Guided Head Suppression
Patho-R1: A Multimodal Reinforcement Learning-Based Pathology Expert Reasoner
VisBias: Measuring Explicit and Implicit Social Biases in Vision Language Models
SPIDER: A Comprehensive Multi-Organ Supervised Pathology Dataset and Baseline Models
IDEA: Image Description Enhanced CLIP-Adapter
토론
이 논문과 연결된 포럼 글이 아직 없습니다.