InstructSeq：通过指令条件多模态序列生成统一视觉任务
InstructSeq: Unifying Vision Tasks with Instruction-conditioned Multi-modal Sequence Generation
AI总结：
本文提出指令条件多模态框架 InstructSeq，用自然语言指令统一语义分割、指代表达和图像描述等多种视觉任务，无需任务特定微调即可取得优异性能。
摘要：
使模型能够动态完成由自然语言指令指定的任务，是通往能力更强、更通用的人工智能的一条有前景的路径。本文提出 InstructSeq，一个以指令为条件的多模态建模框架，通过灵活的自然语言控制以及对视觉和文本数据的处理来统一多种视觉任务。InstructSeq 采用多模态 Transformer 架构，涵盖视觉、语言和序列建模。我们使用视觉编码器提取图像特征，并使用文本编码器对指令进行编码。自回归 Transformer 融合这些表示并生成序列化任务输出。通过使用大语言模型（LLM）生成的自然语言指令进行训练，InstructSeq 获得了对自由形式指令的强理解能力，可用于指定视觉任务。这为利用灵活的自然指令引导模型能力提供了直观接口。在没有任何任务特定微调的情况下，InstructSeq 在语义分割、指代表达分割/理解以及图像描述任务上取得了引人注目的性能。灵活的控制和多任务统一使模型在计算机视觉领域具备更接近人类的通用性和泛化能力。代码将很快在 https://github.com/rongyaofang/InstructSeq 发布。
英文摘要：
Empowering models to dynamically accomplish tasks specified through natural language instructions represents a promising path toward more capable and general artificial intelligence. In this work, we introduce InstructSeq, an instruction-conditioned multi-modal modeling framework that unifies diverse vision tasks through flexible natural language control and handling of both visual and textual data. InstructSeq employs a multimodal transformer architecture encompassing visual, language, and sequential modeling. We utilize a visual encoder to extract image features and a text encoder to encode instructions. An autoregressive transformer fuses the representations and generates sequential task outputs. By training with LLM-generated natural language instructions, InstructSeq acquires a strong comprehension of free-form instructions for specifying visual tasks. This provides an intuitive interface for directing capabilities using flexible natural instructions. Without any task-specific tuning, InstructSeq achieves compelling performance on semantic segmentation, referring expression segmentation/comprehension, and image captioning. The flexible control and multi-task unification empower the model with more human-like versatility and generalizability for computer vision. The code will be released soon at https://github.com/rongyaofang/InstructSeq.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
