paper-with-me

Papers

f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning

2019-03-25 · CVPR 2019 6 · Yongqin Xian, Saurabh Sharma, Bernt Schiele, Zeynep Akata

When labeled training data is scarce, a promising data augmentation approach is to generate visual features of unknown classes using their attributes. To learn the class conditional distribution of CNN features, these models rely on pairs of image features and class attributes. Hence, they can not make use of the abundance of unlabeled data samples. In this paper, we tackle any-shot learning problems i.e. zero-shot and few-shot, in a unified feature generating framework that operates in both inductive and transductive learning settings. We develop a conditional generative model that combines the strength of VAE and GANs and in addition, via an unconditional discriminator, learns the marginal feature distribution of unlabeled images. We empirically show that our model learns highly discriminative CNN features for five datasets, i.e. CUB, SUN, AWA and ImageNet, and establish a new state-of-the-art in any-shot learning, i.e. inductive and transductive (generalized) zero- and few-shot learning settings. We also demonstrate that our learned features are interpretable: we visualize them by inverting them back to the pixel space and we explain them by generating textual arguments of why they are associated with a certain label.

📄 PDF Abstract BibTeX arXiv:1903.10132

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationFew-Shot LearningGeneralized Zero-Shot LearningTransductive LearningZero-Shot Learning

Methods 이 논문이 사용한 방법론

USD Coin Customer Service Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

Improved Feature Generating Framework for Transductive Zero-shot Learning

2024-12-24 · Zihan Ye, Xinyuan Ru, Shiming Chen, Yaochu Jin 외

Feature Generative Adversarial Networks have emerged as powerful generative models in producing high-quality representations of unseen classes within the scope of Zero-shot Learning (ZSL). This paper delves into the pivo…

regressionZero-Shot Learning

Bi-directional Distribution Alignment for Transductive Zero-Shot Learning

2023-03-15 · CVPR 2023 1 · Zhicai Wang, Yanbin Hao, Tingting Mu, Ouxiang Li 외

It is well-known that zero-shot learning (ZSL) can suffer severely from the problem of domain shift, where the true and learned data distributions for the unseen classes do not match. Although transductive ZSL (TZSL) att…

Zero-Shot Learning

Data Augmentation and Classification of Sea-Land Clutter for Over-the-Horizon Radar Using AC-VAEGAN

2023-01-03 · Xiaoxuan Zhang, Zengfu Wang, Kun Lu, Quan Pan

In the sea-land clutter classification of sky-wave over-the-horizon-radar (OTHR), the imbalanced and scarce data leads to a poor performance of the deep learning-based classification model. To solve this problem, this pa…

ClassificationData AugmentationGenerative Adversarial Network

Latent Embedding Feedback and Discriminative Features for Zero-Shot Classification

2020-03-17 · ECCV 2020 8 · Sanath Narayan, Akshita Gupta, Fahad Shahbaz Khan, Cees G. M. Snoek 외

Zero-shot learning strives to classify unseen categories for which no data is available during training. In the generalized variant, the test samples can further belong to seen or unseen categories. The state-of-the-art …

Action ClassificationClassificationDecoderGeneral Classification+3

Learning latent representations across multiple data domains using Lifelong VAEGAN

2020-07-20 · ECCV 2020 8 · Fei Ye, Adrian G. Bors

The problem of catastrophic forgetting occurs in deep learning models trained on multiple databases in a sequential manner. Recently, generative replay mechanisms (GRM), have been proposed to reproduce previously learned…

Lifelong learningRepresentation Learning