Contrastive Embedding for Generalized Zero-Shot Learning
Generalized zero-shot learning (GZSL) aims to recognize objects from both seen and unseen classes, when only the labeled examples from seen classes are provided. Recent feature generation methods learn a generative model that can synthesize the missing visual features of unseen classes to mitigate the data-imbalance problem in GZSL. However, the original visual feature space is suboptimal for GZSL classification since it lacks discriminative information. To tackle this issue, we propose to integrate the generation model with the embedding model, yielding a hybrid GZSL framework. The hybrid GZSL approach maps both the real and the synthetic samples produced by the generation model into an embedding space, where we perform the final GZSL classification. Specifically, we propose a contrastive embedding (CE) for our hybrid GZSL framework. The proposed contrastive embedding can leverage not only the class-wise supervision but also the instance-wise supervision, where the latter is usually neglected by existing GZSL researches. We evaluate our proposed hybrid GZSL framework with contrastive embedding, named CE-GZSL, on five benchmark datasets. The results show that our CEGZSL method can outperform the state-of-the-arts by a significant margin on three datasets. Our codes are available on https://github.com/Hanzy1996/CE-GZSL.
Code (3)
Tasks
Generalized Zero-Shot LearningZero-Shot LearningSimilar Papers 제목 키워드 기반
Instance Adaptive Prototypical Contrastive Embedding for Generalized Zero Shot Learning
Generalized zero-shot learning(GZSL) aims to classify samples from seen and unseen labels, assuming unseen labels are not accessible during training. Recent advancements in GZSL have been expedited by incorporating contr…
Contrastive LearningGeneralized Zero-Shot LearningZero-Shot LearningAudio-visual Generalized Zero-shot Learning the Easy Way
Audio-visual generalized zero-shot learning is a rapidly advancing domain that seeks to understand the intricate relations between audio and visual cues within videos. The overarching goal is to leverage insights from se…
Generalized Zero-Shot LearningZero-Shot LearningHierarchicalContrast: A Coarse-to-Fine Contrastive Learning Framework for Cross-Domain Zero-Shot Slot Filling
In task-oriented dialogue scenarios, cross-domain zero-shot slot filling plays a vital role in leveraging source domain knowledge to learn a model with high generalization ability in unknown target domain where annotated…
Contrastive Learningslot-fillingSlot FillingTransfer Learning+1Cross-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 LearningEn-Compactness: Self-Distillation Embedding & Contrastive Generation for Generalized Zero-Shot Learning
Generalized zero-shot learning (GZSL) requires a classifier trained on seen classes that can recognize objects from both seen and unseen classes. Due to the absence of unseen training samples, the classifier tends to…
Generalized Zero-Shot LearningZero-Shot Learning