国产bbaaaaa片,成年美女黄网站色视频免费,成年黄大片,а天堂中文最新一区二区三区,成人精品视频一区二区三区尤物

首頁(yè)> 外文期刊>IEEE Transactions on Image Processing >Neural Compatibility Modeling With Probabilistic Knowledge Distillation
【24h】

Neural Compatibility Modeling With Probabilistic Knowledge Distillation

機(jī)譯：具有概率知識(shí)蒸餾的神經(jīng)兼容性建模

獲取原文
獲取原文并翻譯 | 示例
  • 摘要
  • 著錄項(xiàng)
  • 相似文獻(xiàn)
  • 相關(guān)主題

摘要

In modern society, clothing matching plays a pivotal role in people's daily life, as suitable outfits can beautify their appearance directly. Nevertheless, how to make a suitable outfit has become a daily headache for many people, especially those who do not have much sense of aesthetics. In the light of this, many research efforts have been dedicated to the task of complementary clothing matching and have achieved great success relying on the advanced data-driven neural networks. However, most existing methods overlook the rich valuable knowledge accumulated by our human beings in the fashion domain, especially the rules regarding clothing matching, like "coats go with dresses" and "silk tops cannot go with chiffon bottoms". Towards this end, in this work, we propose a knowledge-guided neural compatibility modeling scheme, which is able to incorporate the rich fashion domain knowledge to enhance the performance of the compatibility modeling in the context of clothing matching. To better integrate the huge and implicit fashion domain knowledge into the data-driven neural networks, we present a probabilistic knowledge distillation (PKD) method, which is able to encode vast knowledge rules in a probabilistic manner. Extensive experiments on two real-world datasets have verified the guidance of rules from different sources and demonstrated the effectiveness and portability of our model. As a byproduct, we released the codes and involved parameters to benefit the research community.
機(jī)譯：在現(xiàn)代社會(huì)中，服裝匹配在人們?nèi)粘Ｉ钪衅鹬P(guān)鍵作用，因?yàn)楹线m的服裝可以直接美化它們的外觀。盡管如此，如何讓合適的服裝成為許多人的日常頭痛，尤其是那些沒(méi)有太多美學(xué)感的人。鑒于此，許多研究努力致力于互補(bǔ)的服裝匹配的任務(wù)，并取得了巨大的成功，依賴于先進(jìn)的數(shù)據(jù)驅(qū)動(dòng)的神經(jīng)網(wǎng)絡(luò)。然而，大多數(shù)現(xiàn)有方法都忽視了我們?cè)跁r(shí)尚領(lǐng)域中的人類積累的豐富有價(jià)值的知識(shí)，尤其是關(guān)于衣物匹配的規(guī)則，如“外套”和連衣裙“和”絲綢頂部不能與雪紡底部一起使用“。在此目的，在這項(xiàng)工作中，我們提出了一種知識(shí)引導(dǎo)的神經(jīng)兼容性建模方案，能夠納入豐富的時(shí)尚領(lǐng)域知識(shí)，以增強(qiáng)服裝匹配背景下的兼容性建模的性能。為了更好地將巨大和隱式的時(shí)尚域知識(shí)集成到數(shù)據(jù)驅(qū)動(dòng)的神經(jīng)網(wǎng)絡(luò)中，我們提出了一種概率的知識(shí)蒸餾（PKD）方法，其能夠以概率方式編碼巨大的知識(shí)規(guī)則。兩個(gè)現(xiàn)實(shí)世界數(shù)據(jù)集的大量實(shí)驗(yàn)已經(jīng)驗(yàn)證了來(lái)自不同來(lái)源的規(guī)則的指導(dǎo)，并證明了我們模型的有效性和可移植性。作為副產(chǎn)品，我們釋放了代碼并涉及參數(shù)以使研究界受益。

著錄項(xiàng)

相似文獻(xiàn)

  • 外文文獻(xiàn)
  • 中文文獻(xiàn)
  • 專利
獲取原文

客服郵箱：kefu@zhangqiaokeyan.com

京公網(wǎng)安備：11010802029741號(hào) ICP備案號(hào)：京ICP備15016152號(hào)-6 六維聯(lián)合信息科技 (北京) 有限公司?版權(quán)所有

  • 客服微信

  • 服務(wù)號(hào)