# Exploiting Counter-Examples for Active Learning with Partial labels

arXiv: https://arxiv.org/abs/2307.07413 · HTML: https://mlsanity.com/paper/2307.07413/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 67 references that are in the map.
- First posted on arXiv 14 Jul 2023.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds](https://mlsanity.com/paper/1906.03671/) (2019)
- [BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning](https://mlsanity.com/paper/1906.08158/) (2019)
- [The Effectiveness of Data Augmentation in Image Classification using Deep Learning](https://mlsanity.com/paper/1712.04621/) (2017)
- [Learning Loss for Active Learning](https://mlsanity.com/paper/1905.03677/) (2019)
- [Variational Adversarial Active Learning](https://mlsanity.com/paper/1904.00370/) (2019)
- [Progressive Identification of True Labels for Partial-Label Learning](https://mlsanity.com/paper/2002.08053/) (2020)
- [Provably Consistent Partial-Label Learning](https://mlsanity.com/paper/2007.08929/) (2020)
- [Learning from Complementary Labels](https://mlsanity.com/paper/1705.07541/) (2017)
- [Task-Aware Variational Adversarial Active Learning](https://mlsanity.com/paper/2002.04709/) (2020)
- [Leveraged Weighted Loss for Partial Label Learning](https://mlsanity.com/paper/2106.05731/) (2021)
- [Active Learning by Feature Mixing](https://mlsanity.com/paper/2203.07034/) (2022)
- [Scalable Active Learning for Object Detection](https://mlsanity.com/paper/2004.04699/) (2020)
- [Bayesian Generative Active Deep Learning](https://mlsanity.com/paper/1904.11643/) (2019)
- [Partial Label Learning with Self-Guided Retraining](https://mlsanity.com/paper/1902.03045/) (2019)
- [A Regularization Approach for Instance-Based Superset Label Learning](https://mlsanity.com/paper/1904.02832/) (2019)
- [Active Learning from Imperfect Labelers](https://mlsanity.com/paper/1610.09730/) (2016)

## Built on by (most cited first, 1 of 1)

- [G4Seg: Generation for Inexact Segmentation Refinement with Diffusion Models](https://mlsanity.com/paper/2506.01539/) (2025)

## Abstract (arXiv)

This paper studies a new problem, active learning with partial labels (ALPL). In this setting, an oracle annotates the query samples with partial labels, relaxing the oracle from the demanding accurate labeling process. To address ALPL, we first build an intuitive baseline that can be seamlessly incorporated into existing AL frameworks. Though effective, this baseline is still susceptible to the overfitting, and falls short of the representative partial-label-based samples during the query process. Drawing inspiration from human inference in cognitive science, where accurate inferences can be explicitly derived from counter-examples (CEs), our objective is to leverage this human-like learning pattern to tackle the overfitting while enhancing the process of selecting representative samples in ALPL. Specifically, we construct CEs by reversing the partial labels for each instance, and then we propose a simple but effective WorseNet to directly learn from this complementary pattern. By leveraging the distribution gap between WorseNet and the predictor, this adversarial evaluation manner could enhance both the performance of the predictor itself and the sample selection process, allowing the predictor to capture more accurate patterns in the data. Experimental results on five real-world datasets and four benchmark datasets show that our proposed method achieves comprehensive improvements over ten representative AL frameworks, highlighting the superiority of WorseNet. The source code will be available at urlhttps://github.com/Ferenas/APLL.