计算机科学
推论
目标检测
人工智能
集合(抽象数据类型)
对象(语法)
训练集
探测器
计算机视觉
软件部署
简单(哲学)
机器学习
延迟(音频)
模式识别(心理学)
数据挖掘
编码(集合论)
图像(数学)
数据建模
钥匙(锁)
视觉对象识别的认知神经科学
数据集
上下文模型
图像处理
对象模型
噪音(视频)
稳健性(进化)
特征提取
语义学(计算机科学)
作者
Leilei Wang,Longfei Liu,Xi Shen,Xuanlong Yu,Yong He,Fei Richard Yu,Yingyi Chen
摘要
Real-time open-vocabulary object detection (OVOD) is essential for practical deployment in dynamic environments, where models must recognize a large and evolving set of categories under strict latency constraints. Current real-time OVOD methods are predominantly built upon YOLO-style models. In contrast, real-time DETR-based methods still lag behind in terms of inference latency, model lightweightness, and overall performance. In this work, we present OV-DEIM, an end-to-end DETR-style open-vocabulary detector built upon the recent DEIMv2 framework with integrated vision-language modeling for efficient open-vocabulary inference. We further introduce a simple query supplement strategy that improves Fixed AP without compromising inference speed. Beyond architectural improvements, we introduce GridSynthetic, a simple yet effective data augmentation strategy that composes multiple training samples into structured image grids. By exposing the model to richer object co-occurrence patterns and spatial layouts within a single forward pass, GridSynthetic mitigates the negative impact of noisy localization signals on the classification loss and improves semantic discrimination, particularly for rare categories. Extensive experiments demonstrate that OV-DEIM achieves state-of-the-art performance on open-vocabulary detection benchmarks, delivering superior efficiency and notable improvements on challenging rare categories. Code and pretrained models are available at https://github.com/wleilei/OV-DEIM.
科研通智能强力驱动
Strongly Powered by AbleSci AI