弯曲与破损的自行车:利用合成数据进行受损物体重识别
Bent & Broken Bicycles: Leveraging synthetic data for damaged object re-identification
AI总结:
本文提出受损物体重识别新任务,利用半自动合成数据构建含39,200张图像的BBBicycles数据集,并提出融合损伤检测与重识别的多任务Transformer基线模型TransReI3D。
摘要:
实例级物体重识别是一项基础计算机视觉任务,其应用范围涵盖图像检索、智能监控和欺诈检测。在本工作中,我们提出了受损物体重识别这一新任务,旨在将因变形或部件缺失导致的视觉外观变化与细微的类内差异区分开来。为探索该任务,我们利用计算机生成图像的能力,以半自动方式创建同一辆自行车在损坏发生前后的高质量合成图像。由此产生的数据集 Bent & Broken Bicycles(BBBicycles)包含 39,200 张图像和 2,800 个独特自行车实例,涵盖 20 种不同的自行车型号。作为该任务的基线,我们提出了 TransReI3D,这是一种多任务、基于 Transformer 的深度网络,将损伤检测(构建为多标签分类任务)与物体重识别统一起来。BBBicycles 数据集可在 https://huggingface.co/datasets/GrainsPolito/BBBicycles 获取。
英文摘要:
Instance-level object re-identification is a fundamental computer vision task, with applications from image retrieval to intelligent monitoring and fraud detection. In this work, we propose the novel task of damaged object re-identification, which aims at distinguishing changes in visual appearance due to deformations or missing parts from subtle intra-class variations. To explore this task, we leverage the power of computer-generated imagery to create, in a semi-automatic fashion, high-quality synthetic images of the same bike before and after a damage occurs. The resulting dataset, Bent & Broken Bicycles (BBBicycles), contains 39,200 images and 2,800 unique bike instances spanning 20 different bike models. As a baseline for this task, we propose TransReI3D, a multi-task, transformer-based deep network unifying damage detection (framed as a multi-label classification task) with object re-identification. The BBBicycles dataset is available at https://huggingface.co/datasets/GrainsPolito/BBBicycles
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。