# Local Deep-Feature Alignment for Unsupervised Dimension Reduction

arXiv: https://arxiv.org/abs/1904.09747 · HTML: https://mlsanity.com/paper/1904.09747/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Apr 2019.

## Built on by (most cited first, 12 of 12)

- [Are we ready for a new paradigm shift? A Survey on Visual Deep MLP](https://mlsanity.com/paper/2111.04060/) (2021)
- [PseudoBound: Limiting the anomaly reconstruction capability of one-class classifiers using pseudo anomalies](https://mlsanity.com/paper/2303.10704/) (2023)
- [ESGN: Efficient Stereo Geometry Network for Fast 3D Object Detection](https://mlsanity.com/paper/2111.14055/) (2021)
- [Heterogeneous Tri-stream Clustering Network](https://mlsanity.com/paper/2301.04451/) (2023)
- [A Universal Model for Cross Modality Mapping by Relational Reasoning](https://mlsanity.com/paper/2102.13360/) (2021)
- [Contextual Attention Mechanism, SRGAN Based Inpainting System for Eliminating Interruptions from Images](https://mlsanity.com/paper/2204.02591/) (2022)
- [A Local Similarity-Preserving Framework for Nonlinear Dimensionality Reduction with Neural Networks](https://mlsanity.com/paper/2103.06383/) (2021)
- [Balancing Accuracy and Latency in Multipath Neural Networks](https://mlsanity.com/paper/2104.12040/) (2021)
- [A Class-wise Non-salient Region Generalized Framework for Video Semantic Segmentation](https://mlsanity.com/paper/2212.14154/) (2022)
- [Regenerating Arbitrary Video Sequences with Distillation Path-Finding](https://mlsanity.com/paper/2311.07170/) (2023)
- [Remote sensing framework for geological mapping via stacked autoencoders and clustering](https://mlsanity.com/paper/2404.02180/) (2024)
- [Arbitrary Ratio Feature Compression via Next Token Prediction](https://mlsanity.com/paper/2602.11494/) (2026)

## Abstract (arXiv)

This paper presents an unsupervised deep-learning framework named Local Deep-Feature Alignment (LDFA) for dimension reduction. We construct neighbourhood for each data sample and learn a local Stacked Contractive Auto-encoder (SCAE) from the neighbourhood to extract the local deep features. Next, we exploit an affine transformation to align the local deep features of each neighbourhood with the global features. Moreover, we derive an approach from LDFA to map explicitly a new data sample into the learned low-dimensional subspace. The advantage of the LDFA method is that it learns both local and global characteristics of the data sample set: the local SCAEs capture local characteristics contained in the data set, while the global alignment procedures encode the interdependencies between neighbourhoods into the final low-dimensional feature representations. Experimental results on data visualization, clustering and classification show that the LDFA method is competitive with several well-known dimension reduction techniques, and exploiting locality in deep learning is a research topic worth further exploring.