Marginalized Latent Semantic Encoder for Zero-Shot Learning

2019-06-01 · CVPR 2019 6 · Zhengming Ding, Hongfu Liu

Zero-shot learning has been well explored to precisely identify new unobserved classes through a visual-semantic function obtained from the existing objects. However, there exist two challenging obstacles: one is that the human-annotated semantics are insufficient to fully describe the visual samples; the other is the domain shift across existing and new classes. In this paper, we attempt to exploit the intrinsic relationship in the semantic manifold when given semantics are not enough to describe the visual objects, and enhance the generalization ability of the visual-semantic function with marginalized strategy. Specifically, we design a Marginalized Latent Semantic Encoder (MLSE), which is learned on the augmented seen visual features and the latent semantic representation. Meanwhile, latent semantics are discovered under an adaptive graph reconstruction scheme based on the provided semantics. Consequently, our proposed algorithm could enrich visual characteristics from seen classes, and well generalize to unobserved classes. Experimental results on zero-shot benchmarks demonstrate that the proposed model delivers superior performance over the state-of-the-art zero-shot learning approaches.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Graph ReconstructionZero-Shot Learning

Zero-Shot Learning via Latent Space Encoding

2017-12-26 · Yunlong Yu, Zhong Ji, Jichang Guo, Zhongfei 외

Zero-Shot Learning (ZSL) is typically achieved by resorting to a class semantic embedding space to transfer the knowledge from the seen classes to unseen ones. Capturing the common semantic characteristics between the vi…

Decoder Retrieval Zero-Shot Learning

Generalized Zero-Shot Learning using Multimodal Variational Auto-Encoder with Semantic Concepts

2021-06-26 · Nihar Bendre, Kevin Desai, Peyman Najafirad

With the ever-increasing amount of data, the central challenge in multimodal learning involves limitations of labelled samples. For the task of classification, techniques such as meta-learning, zero-shot learning, and fe…

Decoder Few-Shot Learning Generalized Zero-Shot Learning Meta-Learning+1

Learning Aligned Cross-Modal Representation for Generalized Zero-Shot Classification

2021-12-24 · Zhiyu Fang, Xiaobin Zhu, Chun Yang, Zheng Han 외

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…

Classification zero-shot-classification Zero-Shot Learning

Cross-Linked Variational Autoencoders for Generalized Zero-Shot Learning

2019-03-24 · ICLR Workshop LLD 2019 · Edgar Schönfeld, Sayna Ebrahimi, Samarth Sinha, Trevor Darrell 외

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 Learning Generalized Zero-Shot Learning Zero-Shot Learning

Latte-Mix: Measuring Sentence Semantic Similarity with Latent Categorical Mixtures

2020-10-21 · H. Bai, L. Tan, K. Xiong, M. Li 외

Measuring sentence semantic similarity using pre-trained language models such as BERT generally yields unsatisfactory zero-shot performance, and one main reason is ineffective token aggregation methods such as mean pooli…