TagProp: Discriminative metric learning in nearest neighbor models for image auto-annotation. Image auto-annotation is an important open problem in computer vision. For this task we propose TagProp, a discriminatively trained nearest neighbor model. Tags of test images are predicted using a weighted nearest-neighbor model to exploit labeled training images. Neighbor weights are based on neighbor rank or distance. TagProp allows the integration of metric learning by directly maximizing the log-likelihood of the tag predictions in the training set. In this manner, we can optimally combine a collection of image similarity metrics that cover different aspects of image content, such as local shape descriptors, or global color histograms. We also introduce a word specific sigmoidal modulation of the weighted neighbor tag predictions to boost the recall of rare words. We investigate the performance of different variants of our model and compare to existing work. We present experimental results for three challenging data sets. On all three, TagProp makes a marked improvement as compared to the current state-of-the-art.
Keywords for this software
References in zbMATH (referenced in 11 articles )
Showing results 1 to 11 of 11.
- Liu, Weiwei; Tsang, Ivor W.: Making decision trees feasible in ultrahigh feature and label dimensions (2017)
- Hamid Amiri, S.; Jamzad, Mansour: Efficient multi-modal fusion on supergraph for scalable image annotation (2015)
- Gong, Yunchao; Ke, Qifa; Isard, Michael; Lazebnik, Svetlana: A multi-view embedding space for modeling Internet images, tags, and their semantics (2014) ioport
- Guillaumin, Matthieu; Küttel, Daniel; Ferrari, Vittorio: ImageNet auto-annotation with segmentation propagation (2014) ioport
- Wang, Mei; Xia, Xiaoling; Le, Jiajin; Zhou, Xiangdong: Effective automatic image annotation via integrated discriminative and generative models (2014) ioport
- Li, Zechao; Liu, Jing; Xu, Changsheng; Lu, Hanqing: MLRank: multi-correlation learning to rank for image annotation (2013)
- Mcauley, Julian J.; Ramisa, Arnau; Caetano, Tibério S.: Optimization of robust loss functions for weakly-labeled image taxonomies (2013)
- Guillaumin, Matthieu; Mensink, Thomas; Verbeek, Jakob; Schmid, Cordelia: Face recognition from caption-based supervision (2012)
- Miao, Xu; Rao, Rajesh P. N.: Fast structured prediction using large margin sigmoid belief networks (2012)
- Dimitrovski, Ivica; Kocev, Dragi; Loskovska, Suzana; Džeroski, Sašo: Hierarchical annotation of medical images (2011) ioport
- Weston, Jason; Bengio, Samy; Usunier, Nicolas: Large scale image annotation: learning to rank with joint word-image embeddings (2010) ioport