Timezone: »

 
Poster
Emergent Graphical Conventions in a Visual Communication Game
Shuwen Qiu · Sirui Xie · Lifeng Fan · Tao Gao · Jungseock Joo · Song-Chun Zhu · Yixin Zhu

Thu Dec 01 09:00 AM -- 11:00 AM (PST) @ Hall J #914
in Poster Session 5 »

Humans communicate with graphical sketches apart from symbolic languages. Primarily focusing on the latter, recent studies of emergent communication overlook the sketches; they do not account for the evolution process through which symbolic sign systems emerge in the trade-off between iconicity and symbolicity. In this work, we take the very first step to model and simulate this process via two neural agents playing a visual communication game; the sender communicates with the receiver by sketching on a canvas. We devise a novel reinforcement learning method such that agents are evolved jointly towards successful communication and abstract graphical conventions. To inspect the emerged conventions, we define three key properties -- iconicity, symbolicity, and semanticity -- and design evaluation methods accordingly. Our experimental results under different controls are consistent with the observation in studies of human graphical conventions. Of note, we find that evolved sketches can preserve the continuum of semantics under proper environmental pressures. More interestingly, co-evolved agents can switch between conventionalized and iconic communication based on their familiarity with referents. We hope the present research can pave the path for studying emergent communication with the modality of sketches.

Keywords: Representation Learning · Visual communication · Emergent languages
[ Paper]  [ Poster]  [ OpenReview] 

Author Information

Shuwen Qiu (University of California, Los Angeles)
Sirui Xie (University of California, Los Angeles)
Lifeng Fan (University of California, Los Angeles)
Tao Gao (UCLA)
Jungseock Joo (NVIDIA)
Song-Chun Zhu (UCLA)
Yixin Zhu (Peking University)

More from the Same Authors