Pose Adaptive Dual Mixup for Few-Shot Single-View 3D Reconstruction

2021-12-23 · Ta-Ying Cheng, Hsuan-ru Yang, Niki Trigoni, Hwann-Tzong Chen, Tyng-Luh Liu

We present a pose adaptive few-shot learning procedure and a two-stage data interpolation regularization, termed Pose Adaptive Dual Mixup (PADMix), for single-image 3D reconstruction. While augmentations via interpolating feature-label pairs are effective in classification tasks, they fall short in shape predictions potentially due to inconsistencies between interpolated products of two images and volumes when rendering viewpoints are unknown. PADMix targets this issue with two sets of mixup procedures performed sequentially. We first perform an input mixup which, combined with a pose adaptive learning procedure, is helpful in learning 2D feature extraction and pose adaptive latent encoding. The stagewise training allows us to build upon the pose invariant representations to perform a follow-up latent mixup under one-to-one correspondences between features and ground-truth volumes. PADMix significantly outperforms previous literature on few-shot settings over the ShapeNet dataset and sets new benchmarks on the more challenging real-world Pix3D dataset.

📄 PDF Abstract BibTeX arXiv:2112.12484

Code (0)

등록된 구현이 없습니다.

Tasks

3D Reconstruction Few-Shot Learning Single-View 3D Reconstruction

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:…

Self-Evolution Learning for Mixup: Enhance Data Augmentation on Few-Shot Text Classification Tasks

2023-05-22 · Haoqi Zheng, Qihuang Zhong, Liang Ding, Zhiliang Tian 외

Text classification tasks often encounter few shot scenarios with limited labeled data, and addressing data scarcity is crucial. Data augmentation with mixup has shown to be effective on various text classification tasks…

Classification Data Augmentation Few-Shot Text Classification text-classification+1

Dual-level Mixup for Graph Few-shot Learning with Fewer Tasks

2025-02-19 · Yonghao Liu, Mengyu Li, Fausto Giunchiglia, Lan Huang 외

Graph neural networks have been demonstrated as a powerful paradigm for effectively learning graph-structured data on the web and mining content from it.Current leading graph models require a large number of labeled samp…

Few-Shot Learning Graph Learning Meta-Learning

AGMixup: Adaptive Graph Mixup for Semi-supervised Node Classification

2024-12-11 · Weigang Lu, Ziyu Guan, Wei Zhao, Yaming Yang 외

Mixup is a data augmentation technique that enhances model generalization by interpolating between data points using a mixing ratio $\lambda$ in the image domain. Recently, the concept of mixup has been adapted to the gr…

Data Augmentation Node Classification

Charting the Right Manifold: Manifold Mixup for Few-shot Learning

2019-07-28 · Puneet Mangla, Mayank Singh, Abhishek Sinha, Nupur Kumari 외

Few-shot learning algorithms aim to learn model parameters capable of adapting to unseen classes with the help of only a few labeled examples. A recent regularization technique - Manifold Mixup focuses on learning a gene…

Few-Shot Image Classification Few-Shot Learning Representation Learning Self-Supervised Learning

Modeling Generalized Specialist Approach To Train Quality Resilient Snapshot Ensemble

2022-06-12 · Ghalib Ahmed Tahir, Chu Kiong Loo, Zongying Liu

Convolutional neural networks (CNNs) apply well with food image recognition due to the ability to learn discriminative visual features. Nevertheless, recognizing distorted images is challenging for existing CNNs. Hence, …

Data Augmentation Transfer Learning