Semantic Borrowing for Generalized Zero-Shot Learning
Generalized zero-shot learning (GZSL) is one of the most realistic but challenging problems due to the partiality of the classifier to supervised classes, especially under the class-inductive instance-inductive (CIII) training setting, where testing data are not available. Instance-borrowing methods and synthesizing methods solve it to some extent with the help of testing semantics, but therefore neither can be used under CIII. Besides, the latter require the training process of a classifier after generating examples. In contrast, a novel non-transductive regularization under CIII called Semantic Borrowing (SB) for improving GZSL methods with compatibility metric learning is proposed in this paper, which not only can be used for training linear models, but also nonlinear ones such as artificial neural networks. This regularization item in the loss function borrows similar semantics in the training set, so that the classifier can model the relationship between the semantics of zero-shot and supervised classes more accurately during training. In practice, the information of semantics of unknown classes would not be available for training while this approach does NOT need it. Extensive experiments on GZSL benchmark datasets show that SB can reduce the partiality of the classifier to supervised classes and improve the performance of generalized zero-shot classification, surpassing inductive GZSL state of the arts.
Code (0)
등록된 구현이 없습니다.
Tasks
Generalized Zero-Shot LearningMetric Learningzero-shot-classificationZero-Shot LearningSimilar Papers 제목 키워드 기반
Visual and Semantic Prompt Collaboration for Generalized Zero-Shot Learning
Generalized zero-shot learning aims to recognize both seen and unseen classes with the help of semantic information that is shared among different classes. It inevitably requires consistent visual-semantic alignment. Exi…
Generalized Zero-Shot LearningZero-Shot LearningGeneralized Zero-Shot Learning with Deep Calibration Network
A technical challenge of deep learning is recognizing target classes without seen data. Zero-shot learning leverages semantic representations such as attributes or class prototypes to bridge source and target classes. Ex…
Generalized Zero-Shot LearningZero-Shot LearningA Unified approach for Conventional Zero-shot, Generalized Zero-shot and Few-shot Learning
Prevalent techniques in zero-shot learning do not generalize well to other related problem scenarios. Here, we present a unified approach for conventional zero-shot, generalized zero-shot and few-shot learning problems. …
Few-Shot LearningGeneralized Zero-Shot LearningOne-Shot LearningZero-Shot LearningBias-Awareness for Zero-Shot Learning the Seen and Unseen
Generalized zero-shot learning recognizes inputs from both seen and unseen classes. Yet, existing methods tend to be biased towards the classes seen during training. In this paper, we strive to mitigate this bias. We pro…
Generalized Zero-Shot LearningZero-Shot LearningSemantics Disentangling for Generalized Zero-Shot Learning
Generalized zero-shot learning (GZSL) aims to classify samples under the assumption that some classes are not observable during training. To bridge the gap between the seen and unseen classes, most GZSL methods attempt t…
Generalized Zero-Shot LearningRelation NetworkZero-Shot Learning