# TAFSSL: Task-Adaptive Feature Sub-Space Learning for few-shot classification

arXiv: https://arxiv.org/abs/2003.06670 · HTML: https://mlsanity.com/paper/2003.06670/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Mar 2020.

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

- [Task-Adaptive Few-shot Node Classification](https://mlsanity.com/paper/2206.11972/) (2022)
- [Transductive Few-shot Learning with Prototype-based Label Propagation by Iterative Graph Refinement](https://mlsanity.com/paper/2304.11598/) (2023)
- [Inductive and Transductive Few-Shot Video Classification via Appearance and Temporal Alignments](https://mlsanity.com/paper/2207.10785/) (2022)
- [FAITH: Few-Shot Graph Classification with Hierarchical Task Graphs](https://mlsanity.com/paper/2205.02435/) (2022)
- [Temporal-Viewpoint Transportation Plan for Skeletal Few-shot Action Recognition](https://mlsanity.com/paper/2210.16820/) (2022)
- [POODLE: Improving Few-shot Learning via Penalizing Out-of-Distribution Samples](https://mlsanity.com/paper/2206.04679/) (2022)
- [Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning](https://mlsanity.com/paper/2110.09446/) (2021)
- [Label Hallucination for Few-Shot Classification](https://mlsanity.com/paper/2112.03340/) (2021)
- [3D Skeleton-based Few-shot Action Recognition with JEANIE is not so Na"ive](https://mlsanity.com/paper/2112.12668/) (2021)
- [Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classification](https://mlsanity.com/paper/2209.08527/) (2022)
- [Open-Set Likelihood Maximization for Few-Shot Learning](https://mlsanity.com/paper/2301.08390/) (2023)
- [Meet JEANIE: a Similarity Measure for 3D Skeleton Sequences via Temporal-Viewpoint Alignment](https://mlsanity.com/paper/2402.04599/) (2024)
- [Towards Practical Few-Shot Query Sets: Transductive Minimum Description Length Inference](https://mlsanity.com/paper/2210.14545/) (2022)
- [Object-aware Long-short-range Spatial Alignment for Few-Shot Fine-Grained Image Classification](https://mlsanity.com/paper/2108.13098/) (2021)
- [Sill-Net: Feature Augmentation with Separated Illumination Representation](https://mlsanity.com/paper/2102.03539/) (2021)
- [Unsupervised Embedding Adaptation via Early-Stage Feature Reconstruction for Few-Shot Classification](https://mlsanity.com/paper/2106.11486/) (2021)
- [Automated Human Cell Classification in Sparse Datasets using Few-Shot Learning](https://mlsanity.com/paper/2107.13093/) (2021)
- [Pseudo-Labeling Based Practical Semi-Supervised Meta-Training for Few-Shot Learning](https://mlsanity.com/paper/2207.06817/) (2022)
- [Transductive Learning for Textual Few-Shot Classification in API-based Embedding Models](https://mlsanity.com/paper/2310.13998/) (2023)
- [Embedding Adaptation is Still Needed for Few-Shot Learning](https://mlsanity.com/paper/2104.07255/) (2021)
- [Model-Agnostic Few-Shot Open-Set Recognition](https://mlsanity.com/paper/2206.09236/) (2022)
- [Multi-Level Contrastive Learning for Few-Shot Problems](https://mlsanity.com/paper/2107.07608/) (2021)
- [Few-shot Learning via Dependency Maximization and Instance Discriminant Analysis](https://mlsanity.com/paper/2109.02820/) (2021)
- [A Strong Baseline for Semi-Supervised Incremental Few-Shot Learning](https://mlsanity.com/paper/2110.11128/) (2021)
- [UNEM: UNrolled Generalized EM for Transductive Few-Shot Learning](https://mlsanity.com/paper/2412.16739/) (2024)
- [Few-shot Learning for Unsupervised Feature Selection](https://mlsanity.com/paper/2107.00816/) (2021)
- [Towards A Conceptually Simple Defensive Approach for Few-shot classifiers Against Adversarial Support Samples](https://mlsanity.com/paper/2110.12357/) (2021)
- [Feature Transformation for Cross-domain Few-shot Remote Sensing Scene Classification](https://mlsanity.com/paper/2203.02270/) (2022)
- [Few-Example Clustering via Contrastive Learning](https://mlsanity.com/paper/2207.04050/) (2022)
- [Robust Transductive Few-shot Learning via Joint Message Passing and Prototype-based Soft-label Propagation](https://mlsanity.com/paper/2311.17096/) (2023)

## Abstract (arXiv)

The field of Few-Shot Learning (FSL), or learning from very few (typically 1 or 5) examples per novel class (unseen during training), has received a lot of attention and significant performance advances in the recent literature. While number of techniques have been proposed for FSL, several factors have emerged as most important for FSL performance, awarding SOTA even to the simplest of techniques. These are: the backbone architecture (bigger is better), type of pre-training on the base classes (meta-training vs regular multi-class, currently regular wins), quantity and diversity of the base classes set (the more the merrier, resulting in richer and better adaptive features), and the use of self-supervised tasks during pre-training (serving as a proxy for increasing the diversity of the base set). In this paper we propose yet another simple technique that is important for the few shot learning performance - a search for a compact feature sub-space that is discriminative for a given few-shot test task. We show that the Task-Adaptive Feature Sub-Space Learning (TAFSSL) can significantly boost the performance in FSL scenarios when some additional unlabeled data accompanies the novel few-shot task, be it either the set of unlabeled queries (transductive FSL) or some additional set of unlabeled data samples (semi-supervised FSL). Specifically, we show that on the challenging miniImageNet and tieredImageNet benchmarks, TAFSSL can improve the current state-of-the-art in both transductive and semi-supervised FSL settings by more than 5%, while increasing the benefit of using unlabeled data in FSL to above 10% performance gain.