Teaching Machines to Describe Images via Natural Language Feedback
원문 초록
Robots will eventually be part of every household. It is thus critical to enable algorithms to learn from and be guided by non-expert users. In this paper, we bring a human in the loop, and enable a human teacher to give feedback to a learning agent in the form of natural language. We argue that a descriptive sentence can provide a much stronger learning signal than a numeric reward in that it can easily point to where the mistakes are and how to correct them. We focus on the problem of image captioning in which the quality of the output can easily be judged by non-experts. We propose a hierarchical phrase-based captioning model trained with policy gradients, and design a feedback network that provides reward to the learner by conditioning on the human-provided feedback. We show that by exploiting descriptive feedback our model learns to perform better than when given independently written human captions.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Document-Level Text Generation with Minimum Bayes Risk Decoding using Optimal Transport
Show, Tell and Summarize: Dense Video Captioning Using Visual Cue Aided Sentence Summarization
Descriptive Image-Text Matching with Graded Contextual Similarity
Representation Learning through Multimodal Attention and Time-Sync Comments for Affective Video Content Analysis
Global Object Proposals for Improving Multi-Sentence Video Descriptions
Sentinel: Decoding Context Utilization via Attention Probing for Efficient LLM Context Compression
토론
이 논문과 연결된 포럼 글이 아직 없습니다.