Research map / Detection and segmentation / Open-set and few-shot detection
Generative Object Detection with Co-Training
Yang Liu, Yao Zhang, Feng Hou, Yangzhou Du, Peng Wang, Yang Zhang, zhongchao shi, Jianping Fan, Zhiqiang He
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes co-training for generative object detection with MLLMs to narrow the accuracy gap with discriminative detectors, using only the abstract.
Problem
Generative object detectors built on multimodal LLMs, which name and localize objects from free-form instructions, remain less accurate than discriminative detectors.
Approach
Co-training of generative object detection, as described in the title; the abstract is truncated before the method details, so the specific mechanism is not stated.
Limitations
- Only the abstract is available; the full method and results are unknown.
Closest papers by meaning
- Generative Region-Language Pretraining for Open-Ended Object Detection (CVPR 2024 · similarity 0.93)
- ROD-MLLM: Towards More Reliable Object Detection in Multimodal Large Language Models (CVPR 2025 · similarity 0.91)
- Unified Generative and Discriminative Training for Multi-modal Large Language Models (NeurIPS 2024 · similarity 0.89)
- Cyclic Contrastive Knowledge Transfer for Open-Vocabulary Object Detection (ICLR 2025 · similarity 0.89)
- Roboflow100-VL: A Multi-Domain Object Detection Benchmark for Vision-Language Models (NeurIPS 2025 · similarity 0.89)
- Re-Aligning Language to Visual Objects with an Agentic Workflow (ICLR 2025 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
