Emergent Communication in Interactive Sketch Question Answering
Zixing Lei, Yiming Zhang, Yuxin Xiong, Siheng Chen
Abstract
Vision-based emergent communication (EC) aims to learn to communicate through sketches and demystify the evolution of human communication. Ironically, previous works neglect multi-round interaction, which is indispensable in human communication. To fill this gap, we first introduce a novel Interactive Sketch Question Answering (ISQA) task, where two collaborative players are interacting through sketches to answer a question about an image in a multi-round manner. To accomplish this task, we design a new and efficient interactive EC system, which can achieve an effective balance among three evaluation factors, including the question answering accuracy, drawing complexity and human interpretability. Our experimental results including human evaluation demonstrate that multi-round interactive mechanism facilitates targeted and efficient communication between intelligent agents with decent human interpretability.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 5c068bd4-ad94-4281-abef-f01e55e793a7Cited by top-tier papers1
Ask how each one uses itBuilds on13
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- Where2comm: Communication-Efficient Collaborative Perception via Spatial Confidence MapsYue Hu, Shaoheng Fang, Zixing Lei, Yiqi Zhong et al.NeurIPS 2022 · 537 citations
- CLIPasso: semantically-aware object sketchingYael Vinker, Ehsan Pajouheshgar, Jessica Y. Bo, Roman Christian Bachmann et al.SIGGRAPH 2022 · 219 citations
- Learning to Paint With Model-Based Deep Reinforcement LearningZhewei Huang, Shuchang Zhou, Wen HengICCV 2019 · 180 citations
- CLIPascene: Scene Sketching with Different Types and Levels of AbstractionYael Vinker, Yuval Alaluf, Daniel Cohen-Or, Ariel ShamirICCV 2023 · 93 citations
Related papers
- Emergent Graphical Conventions in a Visual Communication GameShuwen Qiu, Sirui Xie, Lifeng Fan, Tao Gao et al.NeurIPS 2022 · 18 citations
- Learning to Interactively Learn and AssistMark Woodward, Chelsea Finn, Karol HausmanAAAI 2020 · 37 citations
- Learning to Draw: Emergent Communication through SketchingDaniela Mihai, Jonathon S. HareNeurIPS 2021 · 34 citations
- Trading off Utility, Informativeness, and Complexity in Emergent CommunicationMycal Tucker, Roger Levy, Julie A. Shah, Noga ZaslavskyNeurIPS 2022 · 34 citations
- Look, Listen, and Answer: Overcoming Biases for Audio-Visual Question AnsweringJie Ma, Min Hu, Pinghui Wang, Wangchun Sun et al.NeurIPS 2024 · 31 citations
