请联系主办方进行认证,即可解锁访问限制。
为了不影响召集报名,请您进行认证,即可解锁访问限制。
Pairwise Bilinear Model for Few-shot Fine-grained Image Classification
该主办方未认证,请注意风险防范!
{{list.startDate}} ~ {{list.overDate}}
{{list.overDate}}结束
{{list.startDate}}开始
票种
-
免费 ¥{{toDecimal2(item.price)}} {{item.name}} ¥{{ toDecimal2(item.plusPrice) }} 优惠码减免¥{{item.discountMoney}} 优惠码折扣{{item.discountRate}}%
-
免费 ¥{{toDecimal2(item.price)}} {{item.name}} ¥{{ toDecimal2(item.plusPrice) }} 优惠码减免¥{{item.discountMoney}} 优惠码折扣{{item.discountRate}}%
{{item_time_note}} {{ticketText != ''&&item_time_note!=''?'(':''}} 说明:{{ticketText}} {{ticketText != ''&&item_time_note!=''?')':''}}
数量
领券
-
立减{{coupon.couponDiscountMoney}}元
满{{coupon.couponLimitMoney}}减{{coupon.couponDiscountMoney}}
该主办方未认证,请注意风险防范!
互动吧
{{pub_count}}
活动{{fansCount}}
粉丝{{shopDesc|html}}进店 >
Ta组织活动太忙,还没腾出空写简介进店 >
报告题目:Pairwise Bilinear Model for Few-shot Fine-grained Image Classification
时间:2019年12月19日(周四)上午10:00—11:00
地点:计算所701会议室
报告人:Dr. Jian Zhang, 悉尼科技大学
摘要:
Deep neural networks have demonstrated advanced abilities on various visual classification tasks, which heavily rely on the large-scale training samples with annotated ground-truth. However, it is unrealistic always to require such annotation in real-world applications. Recently, Few-Shot learning (FS), as an attempt to address the shortage of training samples, has made significant progress in generic classification tasks. Nonetheless, it is still challenging for current FS models to distinguish the subtle differences between fine-grained categories given limited training data.
To filling the classification gap, in this paper, we address the Few-Shot Fine-Grained (FSFG) classification problem, which focuses on tackling the fine-grained classification under the challenging few-shot learning setting. A novel low-rank pairwise bilinear pooling operation is proposed to capture the nuanced differences between the support and query images for learning an effective distance metric. Moreover, a feature alignment layer is designed to match the support image features with query ones before the comparison. We name the proposed model Low-Rank Pairwise Alignment Bilinear Network (LRPABN), which is trained in an end-to-end fashion. Comprehensive experimental results on four widely used fine-grained classification datasets demonstrate that our LRPABN model achieves the superior performances compared to state-of-the-art methods.
报告人简介:
Dr. Jian Zhang received the Ph.D. degree in electrical engineering from the University of New South Wales (UNSW), Sydney, Australia, in 1999.From 1997 to 2003, he was with the Visual Information Processing Laboratory, Motorola Labs, Sydney, as a Senior Research Engineer, and later became a Principal Research Engineer and a Foundation Manager with the Visual Communications Research Team. From 2004 to July 2011, he was a Principal Researcher and a Project Leader with National ICT Australia, Sydney. He is currently an Associate Professor with the Global Big Data Technologies Centre, School of Electrical & Data Engineering, Faculty of engineering and Information Technology, University of Technology Sydney, Sydney. Prof Zhang’s research interests include multimedia signal processing, computer vision, pattern recognition, visual information mining, human-computer interaction and intelligent video surveillance systems. Prof Zhang has co-authored more than 130 paper publications, book chapters, patents and technical reports from his research output, he was the co-author of eight granted US and China patents. Dr. Zhang is an IEEE Senior Member. He was Technical Program Chair, 2008 IEEE Multimedia Signal Processing Workshop; Associated Editor, IEEE Transactions on Multimedia; Associated Editor, IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT); Associated Editor, EURASIP Journal on Image and Video Processing. As a General Co-Chair, Jian chaired the International Conference on Multimedia and Expo (IEEE ICME 2012) in Melbourne Australia 2012 and as a Technical Program Co-Chair for IEEE ICME 2020 in London. As a Technical Program Co-Chair, Jian chaired The IEEE Visual Communications and Image Processing (IEEE VCIP 2014) and as a General Co-Chair for organizing the IEEE VICP 2019 in Sydney.
有疑问可咨询:
13643136553或邮件13932327338@163.com
中科图云小助手微信:TuyunAssistant
更多资讯可关注:
服务号:中科图云AICloud
订阅号:中科图云
分享到:
微信扫一扫,分享小程序
扫一扫,分享至朋友圈
温馨提示:
在付费报名之前请仔细甄别主办方的资质及服务能力。部分主办方会私下与报名者沟通承诺参与活动后的权益,并夸大参与后的收益效果等,以此来收取高额的报名费。这类活动通常有基于抖音、淘宝等平台的推广、代理加盟、引流变现等相关内容。
为保障您的权益,避免相关的经济损失,互动吧平台特此说明,平台仅提供相关的技术支持,不承担参与者与主办方在活动过程中的相关纠纷,若出现相关纠纷,平台会积极协助处理。
- 为你推荐
-
{{hot.infoStartTime}}
{{hot.infoStartTime}}
{{hot.infoStartTime.substr(0,16).replace(new Date().getFullYear()+'-','')}}
Live{{hot.plusDiscountPriceRange}}{{hot.priceWithSign}} {{hot.highlight|html}}
加载中
该主办方未认证,请注意风险防范!
{{pub_count}}
活动{{fansCount}}
粉丝{{shopDesc|html}}进店>
Ta组织活动太忙,还没腾出空写简介进店>
一对一为您答疑解惑
-
{{selectlist.title}}
{{selectlist.infoDate}}{{selectlist.priceWithSign}} {{selectlist.plusDiscountPriceRange}} {{selectlist.highlight}}
-
{{list.shortName}}天{{list.desc1}}{{list.desc2}}
成为银牌会员
{{infoText}}
-
高端模板免费用
提升活动人气
-
活动排名加权
提升活动排名
-
去除报名页广告
提升活动报名效果
-
高端邀请海报
全场无限使用
-
活动优先审核
快人一步上架曝光
-
大额提现
限额提升4倍
-
报名渠道监测
掌握各渠道业绩
-
发布多场次活动
发布一次一劳永逸
-
免认证服务
免99元审核服务费
-
更多特权
敬请期待
马上开通
-
{{item.type}}
¥{{item.price}}/{{item.viewType}}
¥{{item.oriPrice}}/{{item.viewType}}
季卡、半年卡、年卡均已包含认证审核服务费,支持开具发票
使用微信或支付宝扫码完成支付
支付金额:¥{{selectGrItem.price}}/{{selectGrItem.viewType}}(已省¥{{selectGrItem.oriPrice - selectGrItem.price}})
购买成功
已购买{{orderName}}
支付金额:¥{{payMoney}}
购买商品:{{orderName}}
扫码支付更轻松
购买成功
已购买{{orderName}}
{{curMemberData.title}}
{{curMemberData.tip}}
-
{{item.name}}
查看更多权益>
{{curMemberData.tags[0].name}}
查看更多权益>
{{item.imgText}}
- {{temp.text}}
购买成功
您已成功购买{{checkMemberData.name}}
扫码