Compositional Obverter Communication Learning From Raw Visual Input
원문 초록
One of the distinguishing aspects of human language is its compositionality, which allows us to describe complex environments with limited vocabulary. Previously, it has been shown that neural network agents can learn to communicate in a highly structured, possibly compositional language based on disentangled input (e.g. hand- engineered features). Humans, however, do not learn to communicate based on well-summarized features. In this work, we train neural agents to simultaneously develop visual perception from raw image pixels, and learn to communicate with a sequence of discrete symbols. The agents play an image description game where the image contains factors such as colors and shapes. We train the agents using the obverter technique where an agent introspects to generate messages that maximize its own understanding. Through qualitative analysis, visualization and a zero-shot test, we show that the agents can develop, out of raw image pixels, a language with compositional properties, given a proper pressure from the environment.
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.