Unsupervised layered image decomposition into object prototypes

T Monnier, E Vincent, J Ponce… - Proceedings of the …, 2021‏ - openaccess.thecvf.com
We present an unsupervised learning framework for decomposing images into layers of
automatically discovered object models. Contrary to recent approaches that model image …

Deep transformation-invariant clustering

T Monnier, T Groueix, M Aubry - Advances in neural …, 2020‏ - proceedings.neurips.cc
Recent advances in image clustering typically focus on learning better deep
representations. In contrast, we present an orthogonal approach that does not rely on …

SpaceJAM: a Lightweight and Regularization-Free Method for Fast Joint Alignment of Images

N Barel, RS Weber, N Mualem, SE Finder… - European Conference on …, 2024‏ - Springer
The unsupervised task of Joint Alignment (JA) of images is beset by challenges such as high
complexity, geometric distortions, and convergence to poor local or even global optima …

An Efficient New Robust PCA Method for Joint Image Alignment and Reconstruction via the L2,1 Norms and Affine Transformation

HT Likassa, Y **a, B Gotu - Scientific Programming, 2022‏ - Wiley Online Library
In this study, an effective robust PCA is developed for joint image alignment and recovery via
L2, 1 norms and affine transformations. To alleviate the potential impacts of outliers, heavy …

Recurrent affine transform encoder for image representation

L Liu, X Jiang, M Saerbeck, J Dauwels - IEEE Access, 2022‏ - ieeexplore.ieee.org
This paper proposes a Recurrent Affine Transform Encoder (RATE) that can be used for
image representation learning. We propose a learning architecture that enables a CNN …

Cryo-EM image alignment: From pair-wise to joint with deep unsupervised difference learning

YX Chen, D Feng, HB Shen - Journal of Structural Biology, 2023‏ - Elsevier
Cryo-electron microscopy (cryo-EM) single-particle analysis is a revolutionary imaging
technique to resolve and visualize biomacromolecules. Image alignment in cryo-EM is an …

Phased groupwise face alignment

G Zhang, H Qin, Y Ke, J Chen, Y Gong - IEEE Access, 2020‏ - ieeexplore.ieee.org
A face does not only have rigid variations but also non-rigid distortions, which has
influenced the performance of groupwise face alignment. A novel method for groupwise face …

[PDF][PDF] Research Article An Efficient New Robust PCA Method for Joint Image Alignment and Reconstruction via the L 2, Norms and Affine Transformation

HT Likassa, Y **a, B Gotu - 2022‏ - academia.edu
In this study, an effective robust PCA is developed for joint image alignment and recovery via
L 2, 1 norms and affine transformations. To alleviate the potential impacts of outliers, heavy …

Joint alignment of image faces

G Zhang, L Pan, J Chen, Y Gong, F Liu - IEEE Access, 2020‏ - ieeexplore.ieee.org
Researches on face alignment have made great progress, which benefits from the use of
prior information and auxiliary models. However, that information lacks in a single face …

MS2BC-a Multi-view Space Structure-Based Clustering Algorithm

SHI **n-rui, Q Yu-hua, L Fei-jiang - Journal of Southwest …, 2020‏ - xbgjxt.swu.edu.cn
Clustering analysis is an important task in the field of machine learning and data mining. In
recent years, a large number of clustering algorithms have been proposed and successfully …