Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders
Many approaches in generalized zero-shot learning rely on cross-modal mapping between the image feature space and the class embedding space. As labeled images are expensive, one direction is to augment the dataset by generating either images or image features. However, the former misses fine-grained details and the latter requires learning a mapping associated with class embeddings. In this work, we take feature generation one step further and propose a model where a shared latent space of image features and class embeddings is learned by modality-specific aligned variational autoencoders. This leaves us with the required discriminative information about the image and classes in the latent features, on which we train a softmax classifier. The key to our approach is that we align the distributions learned from images and from side-information to construct latent features that contain the essential multi-modal information associated with unseen classes. We evaluate our learned latent features on several benchmark datasets, i.e. CUB, SUN, AWA1 and AWA2, and establish a new state of the art on generalized zero-shot as well as on few-shot learning. Moreover, our results on ImageNet with various zero-shot splits show that our latent features generalize well in large-scale settings.
Code (1)
Tasks
Few-Shot LearningGeneralized Few-Shot LearningGeneralized Zero-Shot LearningGeneralized Zero-Shot Learning - UnseenLong-tail learning with class descriptorsZero-Shot LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Cross-Linked Variational Autoencoders for Generalized Zero-Shot Learning
Most approaches in generalized zero-shot learning rely on cross-modal mapping between an image feature space and a class embedding space or on generating artificial image features. However, learning a shared cross-modal …
Few-Shot LearningGeneralized Zero-Shot LearningZero-Shot LearningGeneralized Zero- and Few-Shot Learning via Aligned Variational Autoencoders
Many approaches in generalized zero-shot learning rely on cross-modal mapping between the image feature space and the class embedding space. As labeled images are expensive, one direction is to augment the dataset by gen…
Few-Shot LearningGeneralized Few-Shot LearningGeneralized Zero-Shot LearningZero-Shot Learning+1Learning shared manifold representation of images and attributes for generalized zero-shot learning
Many of the zero-shot learning methods have realized predicting labels of unseen images by learning the relations between images and pre-defined class-attributes. However, recent studies show that, under the more realist…
Generalized Zero-Shot LearningZero-Shot LearningGeneralized Zero-Shot Domain Adaptation via Coupled Conditional Variational Autoencoders
Domain adaptation approaches aim to exploit useful information from the source domain where supervised learning examples are easier to obtain to address a learning problem in the target domain where there is no or limite…
Domain AdaptationGeneralized Zero-Shot LearningZero-Shot LearningLearning Aligned Cross-Modal Representation for Generalized Zero-Shot Classification
Learning a common latent embedding by aligning the latent spaces of cross-modal autoencoders is an effective strategy for Generalized Zero-Shot Classification (GZSC). However, due to the lack of fine-grained instance-wis…
Classificationzero-shot-classificationZero-Shot Learning