# Multi-level Semantic Feature Augmentation for One-shot Learning

arXiv: https://arxiv.org/abs/1804.05298 · HTML: https://mlsanity.com/paper/1804.05298/

## Key facts

- Cited by 62 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Apr 2018.

## Built on by (most cited first, 30 of 62)

- [A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities](https://mlsanity.com/paper/2205.06743/) (2022)
- [Registration based Few-Shot Anomaly Detection](https://mlsanity.com/paper/2207.07361/) (2022)
- [Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detection](https://mlsanity.com/paper/2103.01903/) (2021)
- [Generating images of rare concepts using pre-trained diffusion models](https://mlsanity.com/paper/2304.14530/) (2023)
- [Hybrid Relation Guided Set Matching for Few-shot Action Recognition](https://mlsanity.com/paper/2204.13423/) (2022)
- [Norm-guided latent space exploration for text-to-image generation](https://mlsanity.com/paper/2306.08687/) (2023)
- [FHIST: A Benchmark for Few-shot Classification of Histological Images](https://mlsanity.com/paper/2206.00092/) (2022)
- [Few-Shot Learning with a Strong Teacher](https://mlsanity.com/paper/2107.00197/) (2021)
- [Rich Semantics Improve Few-shot Learning](https://mlsanity.com/paper/2104.12709/) (2021)
- [SEGA: Semantic Guided Attention on Visual Prototype for Few-Shot Learning](https://mlsanity.com/paper/2111.04316/) (2021)
- [GenMix: Effective Data Augmentation with Generative Diffusion Model Image Editing](https://mlsanity.com/paper/2412.02366/) (2024)
- [Multimodal Prototype-Enhanced Network for Few-Shot Action Recognition](https://mlsanity.com/paper/2212.04873/) (2022)
- [HyRSM++: Hybrid Relation Guided Temporal Set Matching for Few-shot Action Recognition](https://mlsanity.com/paper/2301.03330/) (2023)
- [Adversarial Feature Augmentation and Normalization for Visual Recognition](https://mlsanity.com/paper/2103.12171/) (2021)
- [Multimodality in Meta-Learning: A Comprehensive Survey](https://mlsanity.com/paper/2109.13576/) (2021)
- [Effectively Leveraging Attributes for Visual Similarity](https://mlsanity.com/paper/2105.01695/) (2021)
- [Adaptive Local-Component-aware Graph Convolutional Network for One-shot Skeleton-based Action Recognition](https://mlsanity.com/paper/2209.10073/) (2022)
- [Dense Vision Transformer Compression with Few Samples](https://mlsanity.com/paper/2403.18708/) (2024)
- [Envisioning Class Entity Reasoning by Large Language Models for Few-shot Learning](https://mlsanity.com/paper/2408.12469/) (2024)
- [Adaptive Prototypical Networks with Label Words and Joint Representation Learning for Few-Shot Relation Classification](https://mlsanity.com/paper/2101.03526/) (2021)
- [Spirit Distillation: A Model Compression Method with Multi-domain Knowledge Transfer](https://mlsanity.com/paper/2104.14696/) (2021)
- [Prototype Completion for Few-Shot Learning](https://mlsanity.com/paper/2108.05010/) (2021)
- [Fine-Grained Few Shot Learning with Foreground Object Transformation](https://mlsanity.com/paper/2109.05719/) (2021)
- [Semantic-aware Video Representation for Few-shot Action Recognition](https://mlsanity.com/paper/2311.06218/) (2023)
- [Tensor feature hallucination for few-shot learning](https://mlsanity.com/paper/2106.05321/) (2021)
- [Information Symmetry Matters: A Modal-Alternating Propagation Network for Few-Shot Learning](https://mlsanity.com/paper/2109.01295/) (2021)
- [HuTuMotion: Human-Tuned Navigation of Latent Motion Diffusion Models with Minimal Feedback](https://mlsanity.com/paper/2312.12227/) (2023)
- [GDC- Generalized Distribution Calibration for Few-Shot Learning](https://mlsanity.com/paper/2204.05230/) (2022)
- [Spirit Distillation: Precise Real-time Semantic Segmentation of Road Scenes with Insufficient Data](https://mlsanity.com/paper/2103.13733/) (2021)
- [Dizygotic Conditional Variational AutoEncoder for Multi-Modal and Partial Modality Absent Few-Shot Learning](https://mlsanity.com/paper/2106.14467/) (2021)

## Abstract (arXiv)

The ability to quickly recognize and learn new visual concepts from limited samples enables humans to swiftly adapt to new environments. This ability is enabled by semantic associations of novel concepts with those that have already been learned and stored in memory. Computers can start to ascertain similar abilities by utilizing a semantic concept space. A concept space is a high-dimensional semantic space in which similar abstract concepts appear close and dissimilar ones far apart. In this paper, we propose a novel approach to one-shot learning that builds on this idea. Our approach learns to map a novel sample instance to a concept, relates that concept to the existing ones in the concept space and generates new instances, by interpolating among the concepts, to help learning. Instead of synthesizing new image instance, we propose to directly synthesize instance features by leveraging semantics using a novel auto-encoder network we call dual TriNet. The encoder part of the TriNet learns to map multi-layer visual features of deep CNNs, that is, multi-level concepts, to a semantic vector. In semantic space, we search for related concepts, which are then projected back into the image feature spaces by the decoder portion of the TriNet. Two strategies in the semantic space are explored. Notably, this seemingly simple strategy results in complex augmented feature distributions in the image feature space, leading to substantially better performance.