paper-with-me

홈 › Papers

SHOT-VAE: Semi-supervised Deep Generative Models With Label-aware ELBO Approximations

2020-11-21 · Hao-Zhe Feng, Kezhi Kong, Minghao Chen, Tianye Zhang, Minfeng Zhu, Wei Chen

Semi-supervised variational autoencoders (VAEs) have obtained strong results, but have also encountered the challenge that good ELBO values do not always imply accurate inference results. In this paper, we investigate and propose two causes of this problem: (1) The ELBO objective cannot utilize the label information directly. (2) A bottleneck value exists and continuing to optimize ELBO after this value will not improve inference accuracy. On the basis of the experiment results, we propose SHOT-VAE to address these problems without introducing additional prior knowledge. The SHOT-VAE offers two contributions: (1) A new ELBO approximation named smooth-ELBO that integrates the label predictive loss into ELBO. (2) An approximation based on optimal interpolation that breaks the ELBO value bottleneck by reducing the margin between ELBO and the data likelihood. The SHOT-VAE achieves good performance with a 25.30% error rate on CIFAR-100 with 10k labels and reduces the error rate to 6.11% on CIFAR-10 with 4k labels.

📄 PDF Abstract BibTeX arXiv:2011.10684

Code (3)

PaperCodeSubmission/AAAI2021-260 공식 구현 pytorch
FengHZ/AAAI2021-260 pytorch
PaperCodeSubmission/OSPOT-VAE pytorch

Tasks

4kSemi-Supervised Image ClassificationVariational Inference

Methods 이 논문이 사용한 방법론

Mixup Mixup is a data augmentation technique that generates a weighted combination of random image pairs from the training data. Given two images and their ground truth labels:…
Stochastic Gradient Variational Bayes 설명 없음

Similar Papers 제목 키워드 기반

SelfPrompt: Confidence-Aware Semi-Supervised Tuning for Robust Vision-Language Model Adaptation

2025-01-24 · Shuvendu Roy, Ali Etemad

We present SelfPrompt, a novel prompt-tuning approach for vision-language models (VLMs) in a semi-supervised learning setup. Existing methods for tuning VLMs in semi-supervised setups struggle with the negative impact of…

Language ModelingLanguage ModellingPseudo LabelWeakly-supervised Learning

Target Really Matters: Target-aware Contrastive Learning and Consistency Regularization for Few-shot Stance Detection

2022-10-01 · COLING 2022 10 · Rui Liu, Zheng Lin, Huishan Ji, Jiangnan Li 외

Stance detection aims to identify the attitude from an opinion towards a certain target. Despite the significant progress on this task, it is extremely time-consuming and budget-unfriendly to collect sufficient high-qual…

Contrastive LearningFew-Shot Stance DetectionStance Detection

Semi-Supervised Generation with Cluster-aware Generative Models

2017-04-03 · Lars Maaløe, Marco Fraccaro, Ole Winther

Deep generative models trained with large amounts of unlabelled data have proven to be powerful within the domain of unsupervised learning. Many real life data sets contain a small amount of labelled data points, that ar…

ClusteringGeneral Classification

Semi-Supervised Few-Shot Classification with Deep Invertible Hybrid Models

2021-05-22 · Yusuke Ohtsubo, Tetsu Matsukawa, Einoshin Suzuki

In this paper, we propose a deep invertible hybrid model which integrates discriminative and generative learning at a latent space level for semi-supervised few-shot classification. Various tasks for classifying new spec…

ClassificationFew-Shot Learning

Semi-unsupervised Learning of Human Activity using Deep Generative Models

2018-10-29 · Matthew Willetts, Aiden Doherty, Stephen Roberts, Chris Holmes

We introduce 'semi-unsupervised learning', a problem regime related to transfer learning and zero-shot learning where, in the training data, some classes are sparsely labelled and others entirely unlabelled. Models able …

ClassificationGeneral ClassificationTime SeriesTime Series Analysis+2