paper-with-me

홈 › Papers

InstructSeq: Unifying Vision Tasks with Instruction-conditioned Multi-modal Sequence Generation

2023-11-30 · Rongyao Fang, Shilin Yan, Zhaoyang Huang, Jingqiu Zhou, Hao Tian, Jifeng Dai, Hongsheng Li

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.

📄 PDF Abstract BibTeX arXiv:2311.18835

Code (0)

등록된 구현이 없습니다.

Tasks

Image CaptioningReferring ExpressionReferring Expression SegmentationSemantic Segmentation

Similar Papers 제목 키워드 기반

SPARGen: Unifying Spatial Perception and Reasoning through Native Multimodal Generation

2026-08-14 · Jinsheng Quan, Jianhua Li, Siyi Xie, Xuanke Shi 외 arxiv

Spatial perception and reasoning from visual observations require recovering geometric structure, establishing correspondences, and understanding spatial relations. Existing approaches typically address these capabilitie…

multimodal generationSpatial Reasoning3D Reconstruction

InstructDiffusion: A Generalist Modeling Interface for Vision Tasks

2023-09-07 · CVPR 2024 1 · Zigang Geng, Binxin Yang, Tiankai Hang, Chen Li 외

We present InstructDiffusion, a unifying and generic framework for aligning computer vision tasks with human instructions. Unlike existing approaches that integrate prior knowledge and pre-define the output space (e.g., …

Keypoint Detection

VisIT-Bench: A Benchmark for Vision-Language Instruction Following Inspired by Real-World Use

2023-08-12 · Yonatan Bitton, Hritik Bansal, Jack Hessel, Rulin Shao 외

We introduce VisIT-Bench (Visual InsTruction Benchmark), a benchmark for evaluation of instruction-following vision-language models for real-world use. Our starting point is curating 70 'instruction families' that we env…

Instruction Following

VisIT-Bench: A Dynamic Benchmark for Evaluating Instruction-Following Vision-and-Language Models

2023-09-26 · NeurIPS 2023 11

We introduce VisIT-Bench (Visual InsTruction Benchmark), a benchmark for evaluating instruction-following vision-language models for real-world use. Our starting point is curating 70 "instruction families" that we envisi…

Rethinking Mutual Information for Language Conditioned Skill Discovery on Imitation Learning

2024-02-27 · Zhaoxun Ju, Chao Yang, Hongbo Wang, Yu Qiao 외

Language-conditioned robot behavior plays a vital role in executing complex tasks by associating human commands or instructions with perception and actions. The ability to compose long-horizon tasks based on unconstraine…

Imitation LearningQuantization