# Unsupervised Active Learning via Natural Feature Progressive Framework

arXiv: https://arxiv.org/abs/2510.04939 · HTML: https://mlsanity.com/paper/2510.04939/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 49 references that are in the map.
- First posted on arXiv 6 Oct 2025.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [Beyond neural scaling laws: beating power law scaling via data pruning](https://mlsanity.com/paper/2206.14486/) (2022)
- [Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt](https://mlsanity.com/paper/2206.07137/) (2022)
- [Cost-Effective Active Learning for Deep Image Classification](https://mlsanity.com/paper/1701.03551/) (2017)
- [Active Learning by Acquiring Contrastive Examples](https://mlsanity.com/paper/2109.03764/) (2021)
- [Coverage-centric Coreset Selection for High Pruning Rates](https://mlsanity.com/paper/2210.15809/) (2022)
- [D2 Pruning: Message Passing for Balancing Diversity and Difficulty in Data Pruning](https://mlsanity.com/paper/2310.07931/) (2023)
- [A Survey on Deep Active Learning: Recent Advances and New Frontiers](https://mlsanity.com/paper/2405.00334/) (2024)
- [Active Learning for Open-set Annotation](https://mlsanity.com/paper/2201.06758/) (2022)
- [Bad Students Make Great Teachers: Active Learning Accelerates Large-Scale Visual Understanding](https://mlsanity.com/paper/2312.05328/) (2023)
- [PT4AL: Using Self-Supervised Pretext Tasks for Active Learning](https://mlsanity.com/paper/2201.07459/) (2022)
- [Making Your First Choice: To Address Cold Start Problem in Vision Active Learning](https://mlsanity.com/paper/2210.02442/) (2022)
- [Prioritizing Samples in Reinforcement Learning with Reducible Loss](https://mlsanity.com/paper/2208.10483/) (2022)
- [LibFewShot: A Comprehensive Library for Few-shot Learning](https://mlsanity.com/paper/2109.04898/) (2021)
- [MCDAL: Maximum Classifier Discrepancy for Active Learning](https://mlsanity.com/paper/2107.11049/) (2021)
- [Uncertainty-Aware Distillation for Semi-Supervised Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2301.09964/) (2023)
- [Deep Active Learning with Noise Stability](https://mlsanity.com/paper/2205.13340/) (2022)
- [Provable Deterministic Leverage Score Sampling](https://mlsanity.com/paper/1404.1530/) (2014)
- [On Deep Unsupervised Active Learning](https://mlsanity.com/paper/2007.13959/) (2020)
- [ELFS: Label-Free Coreset Selection with Proxy Training Dynamics](https://mlsanity.com/paper/2406.04273/) (2024)
- [BAL: Balancing Diversity and Novelty for Active Learning](https://mlsanity.com/paper/2312.15944/) (2023)
- [Bidirectional Uncertainty-Based Active Learning for Open Set Annotation](https://mlsanity.com/paper/2402.15198/) (2024)
- [Active Learning with Multiple Kernels](https://mlsanity.com/paper/2005.03188/) (2020)
- [Deep Unsupervised Active Learning on Learnable Graphs](https://mlsanity.com/paper/2111.04286/) (2021)

## Abstract (arXiv)

The effectiveness of modern deep learning models is predicated on the availability of large-scale, human-annotated datasets, a process that is notoriously expensive and time-consuming. While Active Learning (AL) offers a strategic solution by labeling only the most informative and representative data, its iterative nature still necessitates significant human involvement. Unsupervised Active Learning (UAL) presents an alternative by shifting the annotation burden to a single, post-selection step. Unfortunately, prevailing UAL methods struggle to achieve state-of-the-art performance. These approaches typically rely on local, gradient-based scoring for sample importance estimation, which not only makes them vulnerable to ambiguous and noisy data but also hinders their capacity to select samples that adequately represent the full data distribution. Moreover, their use of shallow, one-shot linear selection falls short of a true UAL paradigm. In this paper, we propose the Natural Feature Progressive Framework (NFPF), a UAL method that revolutionizes how sample importance is measured. At its core, NFPF employs a Specific Feature Learning Machine (SFLM) to effectively quantify each sample's contribution to model performance. We further utilize the SFLM to define a powerful Reconstruction Difference metric for initial sample selection. Our comprehensive experiments show that NFPF significantly outperforms all established UAL methods and achieves performance on par with supervised AL methods on vision datasets. Detailed ablation studies and qualitative visualizations provide compelling evidence for NFPF's superior performance, enhanced robustness, and improved data distribution coverage.