# Feature Space Transfer for Data Augmentation

arXiv: https://arxiv.org/abs/1801.04356 · HTML: https://mlsanity.com/paper/1801.04356/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jan 2018.

## Built on by (most cited first, 21 of 21)

- [A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities](https://mlsanity.com/paper/2205.06743/) (2022)
- [Evaluation of post-hoc interpretability methods in time-series classification](https://mlsanity.com/paper/2202.05656/) (2022)
- [A Survey on Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2304.08130/) (2023)
- [GistNet: a Geometric Structure Transfer Network for Long-Tailed Recognition](https://mlsanity.com/paper/2105.00131/) (2021)
- [Data-Centric Learning from Unlabeled Graphs with Diffusion Model](https://mlsanity.com/paper/2303.10108/) (2023)
- [Breadcrumbs: Adversarial Class-Balanced Sampling for Long-tailed Recognition](https://mlsanity.com/paper/2105.00127/) (2021)
- [MetaCloth: Learning Unseen Tasks of Dense Fashion Landmark Detection from a Few Samples](https://mlsanity.com/paper/2112.02763/) (2021)
- [Learning to Focus: Cascaded Feature Matching Network for Few-shot Image Recognition](https://mlsanity.com/paper/2101.05018/) (2021)
- [Metric Based Few-Shot Graph Classification](https://mlsanity.com/paper/2206.03695/) (2022)
- [Cross-Domain Few-Shot Classification via Inter-Source Stylization](https://mlsanity.com/paper/2208.08015/) (2022)
- [UpCycling: Semi-supervised 3D Object Detection without Sharing Raw-level Unlabeled Scenes](https://mlsanity.com/paper/2211.11950/) (2022)
- [Augmenting Safety-Critical Driving Scenarios while Preserving Similarity to Expert Trajectories](https://mlsanity.com/paper/2404.13347/) (2024)
- [Data augmentation by morphological mixup for solving Raven's Progressive Matrices](https://mlsanity.com/paper/2103.05222/) (2021)
- [Extending Temporal Data Augmentation for Video Action Recognition](https://mlsanity.com/paper/2211.04888/) (2022)
- [Reprint: a randomized extrapolation based on principal components for data augmentation](https://mlsanity.com/paper/2204.12024/) (2022)
- [TablEye: Seeing small Tables through the Lens of Images](https://mlsanity.com/paper/2307.02491/) (2023)
- [CALA: A Class-Aware Logit Adapter for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2412.12654/) (2024)
- [Micro-Expression Recognition Based on Attribute Information Embedding and Cross-modal Contrastive Learning](https://mlsanity.com/paper/2205.14643/) (2022)
- [AI Competitions and Benchmarks: Dataset Development](https://mlsanity.com/paper/2404.09703/) (2024)
- [Semantics-Aware Generative Latent Data Augmentation for Learning in Low-Resource Domains](https://mlsanity.com/paper/2602.02841/) (2026)
- [A Transfer Learning Evaluation of Deep Neural Networks for Image Classification](https://mlsanity.com/paper/2605.11989/) (2026)

## Abstract (arXiv)

The problem of data augmentation in feature space is considered. A new architecture, denoted the FeATure TransfEr Network (FATTEN), is proposed for the modeling of feature trajectories induced by variations of object pose. This architecture exploits a parametrization of the pose manifold in terms of pose and appearance. This leads to a deep encoder/decoder network architecture, where the encoder factors into an appearance and a pose predictor. Unlike previous attempts at trajectory transfer, FATTEN can be efficiently trained end-to-end, with no need to train separate feature transfer functions. This is realized by supplying the decoder with information about a target pose and the use of a multi-task loss that penalizes category- and pose-mismatches. In result, FATTEN discourages discontinuous or non-smooth trajectories that fail to capture the structure of the pose manifold, and generalizes well on object recognition tasks involving large pose variation. Experimental results on the artificial ModelNet database show that it can successfully learn to map source features to target features of a desired pose, while preserving class identity. Most notably, by using feature space transfer for data augmentation (w.r.t. pose and depth) on SUN-RGBD objects, we demonstrate considerable performance improvements on one/few-shot object recognition in a transfer learning setup, compared to current state-of-the-art methods.