Page 189 - 《软件学报》2021年第9期

杨博 等:一种协同过滤式零次学习方法 2813

从图中可以看出:右侧这些图像不能很明显地体现所属类别的判别性特征,与该类别的常规图像特征以及
类别属性描述都差异较大,即使是从人类的认知角度,这些样本也确实很难被正确分类.
5 总 结

本文面向零次图像分类任务提出了一种协同过滤式零次学习方法,通过借鉴推荐领域中的协同过滤思想,
将零次学习过程建模为一个矩阵填充问题,建立了零次学习领域与推荐领域的桥梁.根据已知类别标签矩阵提
供的丰富信息推断图像及类别的隐特征表示,从而使用视觉特征矩阵和语义特征矩阵重构标签矩阵,实现对新
类别样本的分类.此外,通过构建类别语义图来建立类别间的语义关联,将已知类别知识迁移至新类别,并应用
图卷积神经网络更新节点,为每个节点学得更好的特征表示.本文方法是端到端的轻量级模型,迭代 300 次~500
次即可达到近似最优的测试准确率.实验结果表明:在传统零次学习任务以及广义零次学习任务上,本文提出的
CF-ZSL 方法在 AWA2,CUB 和 SUN 这 3 个零次学习数据集上均能达到稳定且优秀的实验结果.通过设计不同
的损失函数或采用不同的协同过滤模型,可能会更好地发挥协同过滤算法的优势.我们相信:在融合推荐领域和
零次学习领域的方向上,仍存在很多潜力有待挖掘.

致谢 感谢赖永老师在论文修改过程中提出的建设性意见,感谢夏日婷、于东然、刘丁菠以及李俊达同学对本
文工作提出的宝贵建议.

References:
[1] Krizhevsky A, Sutskever I, Hinton G. Imagenet classification with deep convolutional neural networks. Advances in Neural
Information Processing Systems, 2012,25:1097−1105.
[2] He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proc. of the IEEE Conf. on Computer Vision and
Pattern Recognition. 2016. 770−778.
[3] Hinton G, Deng L, Yu D, Dahl GE, Mohamed A, Jaitly N, Senior A, Vanhoucke V, Nguyen P, Sainath TN, Kingsbury B. Deep
neural networks for acoustic modeling in speech recognition: The shared views of four research groups. IEEE Signal processing
Magazine, 2012,29(6):82−97.
[4] Graves A, Mohamed A, Hinton G. Speech recognition with deep recurrent neural networks. In: Proc. of the IEEE Int’l Conf. on
Acoustics, Speech and Signal Processing. 2013. 6645−6649.
[5] Fagnant D, Kockelman K. Preparing a nation for autonomous vehicles: Opportunities, barriers and policy recommendations.
Transportation Research Part A: Policy and Practice, 2015,77:167−181.
[6] Yao Q, Tian Y. A model predictive controller with longitudinal speed compensation for autonomous vehicle path tracking. Applied
Sciences, 2019,9(22):4739.
[7] Xian Y, Schiele B, Akata Z. Zero-shot learning-the good, the bad and theugly. In: Proc. of the IEEE Conf. on Computer Vision and
Pattern Recognition. 2017. 4582−4591.
[8] Wang X, Ye Y, Gupta A. Zero-shot recognition via semantic embeddings and knowledge graphs. In: Proc. of the IEEE Conf. on
Computer Vision and Pattern Recognition. 2018. 6857−6866.
[9] Su X, Khoshgoftaar T. A survey of collaborative filtering techniques. In: Proc. of the Advances in Artificial Intelligence. 2009.
[10] Koren Y, Bell R. Advances in Collaborative Filtering. Recommender Systems Handbook. 2015. 77−118.
[11] Annadani Y, Biswas S. Preserving semantic relations for zero-shot learning. In: Proc. of the IEEE Conf. on Computer Vision and
Pattern Recognition. 2018. 7603−7612.
[12] Changpinyo S, Chao WL, Gong B, Sha F. Synthesized classifiers for zero-shot learning. In: Proc. of the IEEE Conf. on Computer
Vision and Pattern Recognition. 2016. 5327−5336.
[13] Kodirov E, Xiang T, Gong S. Semantic autoencoder for zero-shot learning. In: Proc. of the IEEE Conf. on Computer Vision and
Pattern Recognition. 2017. 3174−3183.
[14] Fu Y, Hospedales T, Xiang T, Gong S. Transductive multi-view zero-shot learning. IEEE Trans. on Pattern Analysis and Machine
Intelligence, 2015,37(11):2332−2345.
[15] Fu Z, Xiang T, Kodirov E, Gong S. Zero-shot learning on semantic class prototype graph. IEEE Trans. on Pattern Analysis and
Machine Intelligence, 2017,40(8):2009−2022.