سال انتشار:
2020
عنوان انگلیسی مقاله:
Multi-attention deep reinforcement learning and re-ranking for vehicle re-identification
ترجمه فارسی عنوان مقاله:
یادگیری تقویتی عمیق چند منظوره و رتبه بندی مجدد برای شناسایی مجدد خودرو
منبع:
Sciencedirect - Elsevier - Neurocomputing, 414 (2020) 27-35. doi:10.1016/j.neucom.2020.07.020
نویسنده:
Yu Liu a, Jianbing Shen a,⇑, Haibo He b
چکیده انگلیسی:
For solving the vehicle Re-identification (Re-ID) task, we need to focus our attention on the details with
arbitrary size in the image, and it’s tough to locate these details accurately. In this paper, we propose a
Multi-Attention Deep Reinforcement Learning (MADRL) model to focus on multi-attentional subregions
that spreading randomly in the image, and extract the discriminative features for the Re-ID task. First, we
obtain multiple attentions from the representative features, then group the feature channels into
different parts, then train a deep reinforcement learning model to learn more accurate positions of these
fine-grained details with different losses. Unlike existing models with complex strategies to keep the
patch-matching constrains, our MADRL model can automatically locate the matching patches (multiattentional
subregions) in different vehicle images with the same identification (ID). Furthermore, based
on the fine-grained attention and global features we re-calculate the distance between the inter- and
intra- classes, and we get better re-ranking results. Compared with state-of-the-art methods on three
large-scale vehicle Re-ID datasets, our algorithm greatly improves the performance of vehicle Re-ID.
Keywords: Re-identification | Deep reinforcement learning | Multi-attention | Re-ranking
قیمت: رایگان
توضیحات اضافی:
تعداد نظرات : 0