# Delta-encoder: an effective sample synthesis method for few-shot object recognition

arXiv: https://arxiv.org/abs/1806.04734 · HTML: https://mlsanity.com/paper/1806.04734/

## Key facts

- Cited by 89 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jun 2018.

## Built on by (most cited first, 30 of 89)

- [A Survey of Data Augmentation Approaches for NLP](https://mlsanity.com/paper/2105.03075/) (2021)
- [Free Lunch for Few-shot Learning: Distribution Calibration](https://mlsanity.com/paper/2101.06395/) (2021)
- [A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities](https://mlsanity.com/paper/2205.06743/) (2022)
- [A Survey on Data Augmentation for Text Classification](https://mlsanity.com/paper/2107.03158/) (2021)
- [A Comprehensive Survey of Image Augmentation Techniques for Deep Learning](https://mlsanity.com/paper/2205.01491/) (2022)
- [RSG: A Simple but Effective Module for Learning Imbalanced Datasets](https://mlsanity.com/paper/2106.09859/) (2021)
- [Rectifying the Shortcut Learning of Background for Few-Shot Learning](https://mlsanity.com/paper/2107.07746/) (2021)
- [Hallucination Improves Few-Shot Object Detection](https://mlsanity.com/paper/2105.01294/) (2021)
- [Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classification](https://mlsanity.com/paper/2204.04567/) (2022)
- [Spectral Feature Augmentation for Graph Contrastive Learning and Beyond](https://mlsanity.com/paper/2212.01026/) (2022)
- [Generating Representative Samples for Few-Shot Classification](https://mlsanity.com/paper/2205.02918/) (2022)
- [MoLo: Motion-augmented Long-short Contrastive Learning for Few-shot Action Recognition](https://mlsanity.com/paper/2304.00946/) (2023)
- [M3Net: Multi-view Encoding, Matching, and Fusion for Few-shot Fine-grained Action Recognition](https://mlsanity.com/paper/2308.03063/) (2023)
- [Matching Feature Sets for Few-Shot Image Classification](https://mlsanity.com/paper/2204.00949/) (2022)
- [Self-Supervision Can Be a Good Few-Shot Learner](https://mlsanity.com/paper/2207.09176/) (2022)
- [Towards better understanding and better generalization of few-shot classification in histology images with contrastive learning](https://mlsanity.com/paper/2202.09059/) (2022)
- [Hallucination Improves the Performance of Unsupervised Visual Representation Learning](https://mlsanity.com/paper/2307.12168/) (2023)
- [Contrastive Prototype Learning with Augmented Embeddings for Few-Shot Learning](https://mlsanity.com/paper/2101.09499/) (2021)
- [Enabling hand gesture customization on wrist-worn devices](https://mlsanity.com/paper/2203.15239/) (2022)
- [Adaptive Distribution Calibration for Few-Shot Learning with Hierarchical Optimal Transport](https://mlsanity.com/paper/2210.04144/) (2022)
- [Masked Autoencoders are Robust Data Augmentors](https://mlsanity.com/paper/2206.04846/) (2022)
- [Disentangled Feature Representation for Few-shot Image Classification](https://mlsanity.com/paper/2109.12548/) (2021)
- [Rethinking Few-Shot Class-Incremental Learning with Open-Set Hypothesis in Hyperbolic Geometry](https://mlsanity.com/paper/2207.09963/) (2022)
- [CAD: Co-Adapting Discriminative Features for Improved Few-Shot Classification](https://mlsanity.com/paper/2203.13465/) (2022)
- [AGI for Agriculture](https://mlsanity.com/paper/2304.06136/) (2023)
- [Dense Vision Transformer Compression with Few Samples](https://mlsanity.com/paper/2403.18708/) (2024)
- [ProtoDA: Efficient Transfer Learning for Few-Shot Intent Classification](https://mlsanity.com/paper/2101.11753/) (2021)
- [Few-Shot Learning with Part Discovery and Augmentation from Unlabeled Images](https://mlsanity.com/paper/2105.11874/) (2021)
- [GeNIe: Generative Hard Negative Images Through Diffusion](https://mlsanity.com/paper/2312.02548/) (2023)
- [Fine-Grained Few Shot Learning with Foreground Object Transformation](https://mlsanity.com/paper/2109.05719/) (2021)

## Abstract (arXiv)

Learning to classify new categories based on just one or a few examples is a long-standing challenge in modern computer vision. In this work, we proposes a simple yet effective method for few-shot (and one-shot) object recognition. Our approach is based on a modified auto-encoder, denoted Delta-encoder, that learns to synthesize new samples for an unseen category just by seeing few examples from it. The synthesized samples are then used to train a classifier. The proposed approach learns to both extract transferable intra-class deformations, or "deltas", between same-class pairs of training examples, and to apply those deltas to the few provided examples of a novel class (unseen during training) in order to efficiently synthesize samples from that new class. The proposed method improves over the state-of-the-art in one-shot object-recognition and compares favorably in the few-shot case. Upon acceptance code will be made available.