Improving Facial Attribute Prediction using Semantic Segmentation, in arxiv 2017.04

笔者最近在关注fine-grained方面的paper,发现有以下的方面去做:

1 part-based

2 weakly-supervised的,如second-orderless pooling(Compact Bilinear Pooling)等

3 还是weakly-supervised的,但用上了proposals/grids/regions(如selective search)等,在网络中同时做classification和detection。

该论文Improving Facial Attribute Prediction using Semantic Segmentation, In arXiv, 2017.04.同样是怎么利用image-level的labels,如人脸属性来做人脸属性分类的。

本博文除了该论文,还会涉及到另外一篇论文Weakly Supervised Deep Detection Networks. In CVPR, 2016.


废话少说,当然细节的东西还是各自看论文去。


由于这次的重点不是说论文里面的face parsing。至于怎么做face parsing的,还是看论文去。上面的图1的一个前提条件是,已经训练好face parsing net的了,而且由这个net来提供face的parsing maps。在做face attr分类时,parsing maps直接resize到对应conv feature maps的大小。

图1的b)和c)挺有意思的,但是从论文上看SSG的作用不大。不管怎样,SSG和SSP的目的是,利用parsing的结果来refine分类模型学到的feature map,使得模型能够充分利用spatial information(一般的做法是在最后一层做global pooling,这显然是spatial orderless的):即每个feature map只响应一个对应part region(这里用parsing来表示)。


笔者比较感兴趣的是SSP,所以在这里就说下Weakly Supervised Deep Detection Networks. In CVPR, 2016.


这里需要弄清楚的一个概念是,detection branch,其实和classification branch是没有太大区别,区别在于如何做softmax的:

classification的目的是,判断该region会是哪个类别,而detection的目的是,判断某个类别会在哪些region出现,非常make sense。

这个就是网络的架构图,具体的细节看论文去。

整体上,这样做都是为了学到更好的特征,而且是在weakly-supervised的约束下。
至于有没有效果,就看你怎么用了。

=====
如果这篇博文对你有帮助,可否赏笔者喝杯奶茶?


  • 0
    点赞
  • 1
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
Compared with homogeneous network-based methods, het- erogeneous network-based treatment is closer to reality, due to the different kinds of entities with various kinds of relations [22– 24]. In recent years, knowledge graph (KG) has been utilized for data integration and federation [11, 17]. It allows the knowledge graph embedding (KGE) model to excel in the link prediction tasks [18, 19]. For example, Dai et al. provided a method using Wasser- stein adversarial autoencoder-based KGE, which can solve the problem of vanishing gradient on the discrete representation and exploit autoencoder to generate high-quality negative samples [20]. The SumGNN model proposed by Yu et al. succeeds in inte- grating external information of KG by combining high-quality fea- tures and multi-channel knowledge of the sub-graph [21]. Lin et al. proposed KGNN to predict DDI only based on triple facts of KG [66]. Although these methods have used KG information, only focusing on the triple facts or simple data fusion can limit performance and inductive capability [69]. Su et al. successively proposed two DDIs prediction methods [55, 56]. The first one is an end-to-end model called KG2ECapsule based on the biomedical knowledge graph (BKG), which can generate high-quality negative samples and make predictions through feature recursively propagating. Another one learns both drug attributes and triple facts based on attention to extract global representation and obtains good performance. However, these methods also have limited ability or ignore the merging of information from multiple perspectives. Apart from the above, the single perspective has many limitations, such as the need to ensure the integrity of related descriptions, just as network-based methods cannot process new nodes [65]. So, the methods only based on network are not inductive, causing limited generalization [69]. However, it can be alleviated by fully using the intrinsic property of the drug seen as local information, such as chemical structure (CS) [40]. And a handful of existing frameworks can effectively integrate multi-information without losing induction [69]. Thus, there is a necessity for us to propose an effective model to fully learn and fuse the local and global infor- mation for improving performance of DDI identification through multiple information complementing.是什么意思
06-11

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值