Learning the Compositional Spaces for Generalized Zero-shot Learning

2018-10-17 · ICLR 2019 5 · Hanze Dong, Yanwei Fu, Sung Ju Hwang, Leonid Sigal, xiangyang xue

This paper studies the problem of Generalized Zero-shot Learning (G-ZSL), whose goal is to classify instances belonging to both seen and unseen classes at the test time. We propose a novel space decomposition method to solve G-ZSL. Some previous models with space decomposition operations only calibrate the confident prediction of source classes (W-SVM [46]) or take target-class instances as outliers [49]. In contrast, we propose to directly estimate and fine-tune the decision boundary between the source and the target classes. Specifically, we put forward a framework that enables to learn compositional spaces by splitting the instances into Source, Target, and Uncertain spaces and perform recognition in each space, where the uncertain space contains instances whose labels cannot be confidently predicted. We use two statistical tools, namely, bootstrapping and Kolmogorov-Smirnov (K-S) Test, to learn the compositional spaces for G-ZSL. We validate our method extensively on multiple G-ZSL benchmarks, on which it achieves state-of-the-art performances.

📄 PDF Abstract BibTeX arXiv:1810.07368

Code (0)

등록된 구현이 없습니다.

Tasks

Generalized Zero-Shot LearningOpen Set LearningZero-Shot Learning

3D Compositional Zero-shot Learning with DeCompositional Consensus

2021-11-29 · Muhammad Ferjad Naeem, Evin Pınar Örnek, Yongqin Xian, Luc van Gool 외

Parts represent a basic unit of geometric and semantic similarity across different objects. We argue that part knowledge should be composable beyond the observed object classes. Towards this, we present 3D Compositional …

Benchmarking Compositional Zero-Shot Learning Object Segmentation+6

Syntactically Guided Generative Embeddings for Zero-Shot Skeleton Action Recognition

2021-01-27 · Pranay Gupta, Divyanshu Sharma, Ravi Kiran Sarvadevabhatla

We introduce SynSE, a novel syntactically guided generative approach for Zero-Shot Learning (ZSL). Our end-to-end approach learns progressively refined generative embedding spaces constrained within and across the involv…

Action Recognition Generalized Zero-Shot Learning Generalized Zero Shot skeletal action recognition POS+2

Zero-Shot Compositional Concept Learning

2021-07-12 · ACL (MetaNLP) 2021 8 · Guangyue Xu, Parisa Kordjamshidi, Joyce Y. Chai

In this paper, we study the problem of recognizing compositional attribute-object concepts within the zero-shot learning (ZSL) framework. We propose an episode-based cross-attention (EpiCA) network which combines merits …

Attribute Zero-Shot Learning

Task-Aware Feature Generation for Zero-Shot Compositional Learning

2019-06-11 · Xin Wang, Fisher Yu, Trevor Darrell, Joseph E. Gonzalez

Visual concepts (e.g., red apple, big elephant) are often semantically compositional and each element of the compositions can be reused to construct novel concepts (e.g., red elephant). Compositional feature synthesis, w…

Novel Concepts 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