Despite the growing demand for interactive AI systems, there have been few comprehensive studies on human-AI interaction in visual understanding e.g. segmentation. Inspired by the development of prompt-based universal interfaces for LLMs, this paper presents SEEM, a promptable, interactive model for Segmenting Everything Everywhere all at once in an image. SEEM has four desiderata: i) Versatility: by introducing a versatile prompting engine for different types of prompts, including points, boxes, scribbles, masks, texts, and referred regions of another image; ii) Compositionality: by learning a joint visual-semantic space for visual and textual prompts to compose queries on the fly for inference as shown in Fig 1; iii)Interactivity: by incorporating learnable memory prompts to retain dialog history information via mask-guided cross-attention; and iv) Semantic-awareness: by using a text encoder to encode text queries and mask labels for open-vocabulary segmentation.

翻译：尽管对交互式人工智能系统的需求日益增长，但在视觉理解（如分割）中关于人机交互的全面研究仍然较少。受大语言模型（LLM）提示驱动通用接口发展的启发，本文提出SEEM——一种可提示的交互式模型，用于在图像中「同时分段一切」。SEEM满足四项需求：i）通用性：通过引入通用提示引擎，支持包括点、框、涂鸦、掩码、文本及另一图像引用区域在内的不同类型提示；ii）组合性：通过学习视觉与文本提示的联合视觉-语义空间，在推理时按需组合查询（如图1所示）；iii）交互性：通过可学习记忆提示保留对话历史信息，并采用掩码引导的交叉注意力机制；iv）语义感知：利用文本编码器对文本查询和掩码标签进行编码，实现开放词汇分割。