Zero Shot learning (ZSL) aims to use the information of seen classes to recognize unseen classes, which is achieved by transferring knowledge of the seen classes from the semantic embeddings. Since the domains of the seen and unseen classes do not overlap, most ZSL algorithms often suffer from domain shift problem. In this paper, we propose a Dual Discriminative Auto-encoder Network (DDANet), in which visual features and semantic attributes are self-encoded by using the high dimensional latent space instead of the feature space or the low dimensional semantic space. In the embedded latent space, the features are projected to both preserve their original semantic meanings and have discriminative characteristics, which are realized by applying dual semantic auto-encoder and discriminative feature embedding strategy. Moreover, the cross modal reconstruction is applied to obtain interactive information. Extensive experiments are conducted on four popular datasets and the results demonstrate the superiority of this method.
AkataZeynep, PerronninFlorent, HarchaouiZaid and SchmidCordelia, Label-embedding for attribute-based classification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 819–826, 2013.
2.
AkataZeynep, ReedScott, WalterDaniel, LeeHonglak and SchieleBernt, Evaluation of output embeddings for finegrained image classification. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2927–2936, 2015.
3.
AnnadaniYashas and BiswasSoma, Preserving semantic relations for zero-shot learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 7603–7612, 2018.
4.
AtzmonYuval and ChechikGal, Probabilistic and-or attribute grouping for zero-shot learning. arXiv preprint arXiv:1806.02664, 2018.
5.
ChaoWei-Lun, ChangpinyoSoravit, GongBoqing and ShaFei, An empirical study and analysis of generalized zero-shot learning for object recognition in the wild. In European Conference on Computer Vision, pages 52–68. Springer, 2016.
6.
DengJia, DongWei, SocherRichard, LiLi-Jia, LiKai and Fei-FeiLi, Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, pages 248–255. Ieee, 2009.
7.
DingZhengming, ShaoMing and FuYun, Generative zeroshot learning via low-rank embedded semantic dictionary, IEEE Transactions on Pattern Analysis and Machine Intelligence41(12) (2018), 2861–2874.
8.
FarhadiAli, EndresIan, HoiemDerek and ForsythDavid, Describing objects by their attributes. In 2009 IEEE Conference on Computer Vision and Pattern Recognition, pages 1778–1785. IEEE, 2009.
9.
FromeAndrea, CorradoGreg S, ShlensJon, BengioSamy, DeanJeff, RanzatoMarc’Aurelio and MikolovTomas, Devise: A deep visual-semantic embedding model. In Advances in Neural Information Processing Systems, pages 2121–2129, 2013.
10.
FuYanwei, HospedalesTimothy M, XiangTao and GongShaogang, Transductive multi-view zero-shot learning, IEEE Transactions on Pattern Analysis and Machine Intelligence37(11) (2015), 2332–2345.
11.
HeKaiming, ZhangXiangyu, RenShaoqing and SunJian, Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 770–778, 2016.
12.
HuangHe, WangChanghu, YuPhilip S and WangChang-Dong, Generative dual adversarial network for generalized zero-shot learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 801–810, 2019.
13.
HuangLifu, JiHeng, ChoKyunghyun and VossClare R, Zero-shot transfer learning for event extraction. arXiv preprint arXiv:1707.01066, 2017.
14.
JiangHuajie, WangRuiping, ShanShiguang and ChenXilin, Learning class prototypes via structure alignment for zero-shot recognition. In Proceedings of the European Conference on Computer Vision (ECCV), pages 118–134, 2018.
15.
KodirovElyor, XiangTao and GongShaogang, Semantic autoencoder for zero-shot learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 3174–3183, 2017.
16.
LampertChristoph H, NickischHannes and HarmelingStefan, Learning to detect unseen object classes by between-class attribute transfer. In 2009 IEEE Conference on Computer Vision and Pattern Recognition, pages 951–958. IEEE, 2009.
17.
LiChuanlong, YeXiufen, YangHaibo, HanYatong, LiXiang and JiaYunpeng, Generalized zero shot learning via synthesis pseudo features, IEEE Access7 (2019), 87827–87836.
18.
LiXinghua, ShenHuanfeng, ZhangLiangpei, ZhangHongyan, YuanQiangqiang and YangGang, Recovering quantitative remote sensing products contaminated by thick clouds and shadows using multitemporal dictionary learning, IEEE Transactions on Geoscience and Remote Sensing52(11) (2014), 7086–7098.
19.
LiuShichen, LongMingsheng, WangJianmin and JordanMichael I, Generalized zero-shot learning with deep calibration network. In Advances in Neural Information Processing Systems, pages 2005–2015, 2018.
20.
LongTeng, XuXing, LiYouyou, ShenFumin, SongJingkuan and ShenHeng Tao, Pseudo transfer with marginalized corrupted attribute for zero-shot learning. In Proceedings of the 26th ACM International Conference on Multimedia, pages 1802–1810, 2018.
21.
van der MaatenLaurens and Hinton.Geoffrey, Visualizing data using t-sne, Journal of Machine Learning Research9(Nov) (2008), 2579–2605.
22.
MikolovTomas, ChenKai, CorradoGreg and DeanJeffrey, Efficient estimation ofword representations in vector space. arXiv preprint arXiv:1301.3781, 2013.
23.
MishraAshish, ReddyShiva Krishna, MittalAnurag and MurthyHema A, A generative model for zero shot learning using conditional variational autoencoders. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pages 2188–2196, 2018.
24.
NorouziMohammad, MikolovTomas, BengioSamy, SingerYoram, ShlensJonathon, FromeAndrea, CorradoGreg S and DeanJeffrey, Zero-shot learning by convex combination of semantic embeddings. arXiv preprint arXiv:1312.5650, 2013.
25.
PattersonGenevieve, XuChen, SuHang and HaysJames, The sun attribute database: Beyond categories for deeper scene understanding, International Journal of Computer Vision108(1–2) (2014), 59–81.
26.
Romera-ParedesBernardino and Torr.Philip, An embarrassingly simple approach to zero-shot learning. In International Conference on Machine Learning, pages 2152–2161, 2015.
27.
SivalingamRavishankar, SomasundaramGuruprasad, MorellasVassilios, PapanikolopoulosNikolaos, LotfallahOsama and ParkYoungchoon, Dictionary learning based object detection and counting in traffic scenes. In Proceedings of the Fourth ACM/IEEE International Conference on Distributed Smart Cameras, pages 42–48, 2010.
28.
VermaVinay Kumar and RaiPiyush, A simple exponential family framework for zero-shot learning. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pages 792–808. Springer, 2017.
29.
WahCatherine, BransonSteve, WelinderPeter, PeronaPietro and BelongieSerge, The caltech-ucsd birds-200-2011 dataset. 2011.
30.
WangKeze, LinLiang, ZuoWangmeng, GuShuhang and ZhangLei, Dictionary pair classifier driven convolutional neural networks for object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 2138–2146, 2016.
31.
WangWenlin, PuYunchen, VermaVinay Kumar, FanKai, ZhangYizhe, ChenChangyou, RaiPiyush and CarinLawrence, Zero-shot learning via class-conditioned deep generative models. arXiv preprint arXiv:1711.05820, 2017.
32.
XianYongqin, AkataZeynep, SharmaGaurav, NguyenQuynh, HeinMatthias and SchieleBernt, Latent embeddings for zeroshot classification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 69–77, 2016.
33.
XianYongqin, LampertChristoph H, SchieleBernt and AkataZeynep, Zero-shot learninga comprehensive evaluation of the good, the bad and the ugly, IEEE Transactions on Pattern Analysis and Machine Intelligence41(9) (2018), 2251–2265.
34.
YuYunlong, JiZhong, PangYanwei, GuoJichang, ZhangZhongfei and WuFei, Bi-adversarial auto-encoder for zero-shot learning. arXiv preprint arXiv:1811.08103, 2018.
35.
ZhangHaofeng, LiuJingren, YaoYazhou and LongYang, Pseudo distribution on unseen classes for generalized zero shot learning, Pattern Recognition Letters135 (2020), 451–458.
36.
ZhangHaofeng, LongYang, GuanYu and ShaoLing, Triple verification network for generalized zero-shot learning, IEEE Transactions on Image Processing28(1) (2018), 506–517.
37.
ZhangHaofeng, LongYang and ShaoLing, Zero-shot leaning and hashing with binary visual similes, Multimedia Tools and Applications78(17) (2019), 24147–24165.
38.
ZhangHaofeng, LongYang, YangWankou and ShaoLing, Dual-verification network for zero-shot learning, Information Sciences470 (2019), 43–57.
39.
ZhangHaofeng, MaoHuaqi, LongYang, YangWankou and ShaoLing, A probabilistic zero-shot learning method via latent nonnegative prototype synthesis of unseen classes, IEEE Transactions on Neural Networks and Learning Systems, 2019.
40.
ZhangHongguang and KoniuszPiotr, Zero-shot kernel learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 7670–7679, 2018.
41.
ZhangZiming and SaligramaVenkatesh, Zero-shot learning via semantic similarity embedding. In Proceedings of the IEEE International Conference on Computer Vision, pages 4166–4174, 2015.
