کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
6938927 1449967 2018 15 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
Curriculum learning of visual attribute clusters for multi-task classification
ترجمه فارسی عنوان
یادگیری برنامه درسی خوشه های بصری برای طبقه بندی چند کاره
کلمات کلیدی
یادگیری برنامه درسی، طبقه بندی چند کاره، ویژگی های ویژوال،
موضوعات مرتبط
مهندسی و علوم پایه مهندسی کامپیوتر چشم انداز کامپیوتر و تشخیص الگو
چکیده انگلیسی
Visual attributes, from simple objects (e.g., backpacks, hats) to soft-biometrics (e.g., gender, height, clothing) have proven to be a powerful representational approach for many applications such as image description and human identification. In this paper, we introduce a novel method to combine the advantages of both multi-task and curriculum learning in a visual attribute classification framework. Individual tasks are grouped after performing hierarchical clustering based on their correlation. The clusters of tasks are learned in a curriculum learning setup by transferring knowledge between clusters. The learning process within each cluster is performed in a multi-task classification setup. By leveraging the acquired knowledge, we speed-up the process and improve performance. We demonstrate the effectiveness of our method via ablation studies and a detailed analysis of the covariates, on a variety of publicly available datasets of humans standing with their full-body visible. Extensive experimentation has proven that the proposed approach boosts the performance by 4%-10%.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Pattern Recognition - Volume 80, August 2018, Pages 94-108
نویسندگان
, , , ,