Fine-Grained Image Classification with Coarse and Fine Labels on One-Shot Learning

Jiao, Qihan; Li, Zhi; Li, Gongyang; Ye, Linwei; Wang, Yang

doi:10.1109/icmew46912.2020.9105959

Cited by 2 publications

(1 citation statement)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Supervised classification has achieved great success in the research, but in this kind of classification, each class needs enough labeling training, and the learned classifier cannot deal with unseen classes [1]. To solve the above problems, the methods of few/oneshot learning [2][3][4], open set recogniton [5], cumulative learning [6], class-incremental [7] and open world [8] have been put forward. However, in the above methods, if unseen classes with no available tag instance appear in the test stage, the classifier still cannot determine their class tag.…”

Section: Introductionmentioning

confidence: 99%

Zero-Shot Learning with Joint Generative Adversarial Networks

et al. 2023

View full text Add to dashboard Cite

Zero-shot learning (ZSL) is implemented by transferring knowledge from seen classes to unseen classes through embedding space or feature generation. However, the embedding-based method has a hubness problem, and the generation-based method may contain considerable bias. To solve these problems, a joint model with multiple generative adversarial networks (JG-ZSL) is proposed in this paper. Firstly, we combined the generation-based model and the embedding-based model to build a hybrid ZSL framework by mapping the real samples and the synthetic samples into the embedding space for classification, which alleviates the problem of data imbalance effectively. Secondly, based on the original generation-method model, a coupled GAN is introduced to generate semantic embeddings, which can generate semantic vectors for unseen classes in embedded space to alleviate the bias of mapping results. Finally, semantic-relevant self-adaptive margin center loss was used, which can explicitly encourage intra-class compactness and inter-class separability, and it can also guide coupled GAN to generate discriminative and representative semantic features. All the experiments on the four standard datasets (CUB, AWA1, AWA2, SUN) show that the proposed method is effective.

show abstract