# Cost-efficient Active Learning for Referring Image Segmentation and Grounding

arXiv: https://arxiv.org/abs/2608.30621 · HTML: https://mlsanity.com/paper/2608.30621/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 37 of its 54 references that are in the map.
- First posted on arXiv 31 Aug 2026.

## Builds on (most cited first, 30 of 37)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [Modeling Context in Referring Expressions](https://mlsanity.com/paper/1608.00272/) (2016)
- [Generation and Comprehension of Unambiguous Object Descriptions](https://mlsanity.com/paper/1511.02283/) (2015)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [Learning Loss for Active Learning](https://mlsanity.com/paper/1905.03677/) (2019)
- [The Vendi Score: A Diversity Evaluation Metric for Machine Learning](https://mlsanity.com/paper/2210.02410/) (2022)
- [Modeling Context Between Objects for Referring Expression Understanding](https://mlsanity.com/paper/1608.00525/) (2016)
- [ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts](https://mlsanity.com/paper/2312.00784/) (2023)
- [MosMedData: Chest CT Scans With COVID-19 Related Findings Dataset](https://mlsanity.com/paper/2005.06465/) (2020)
- [ViewAL: Active Learning with Viewpoint Entropy for Semantic Segmentation](https://mlsanity.com/paper/1911.11789/) (2019)
- [Deep Active Learning: Unified and Principled Method for Query and Training](https://mlsanity.com/paper/1911.09162/) (2019)
- [Diverse mini-batch Active Learning](https://mlsanity.com/paper/1901.05954/) (2019)
- [Active Learning for Deep Object Detection via Probabilistic Modeling](https://mlsanity.com/paper/2103.16130/) (2021)
- [SEEDS: Superpixels Extracted via Energy-Driven Sampling](https://mlsanity.com/paper/1309.3848/) (2013)
- [Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answering](https://mlsanity.com/paper/2107.02331/) (2021)
- [Zero-shot Referring Image Segmentation with Global-Local Context Features](https://mlsanity.com/paper/2303.17811/) (2023)
- [Bayesian Generative Active Deep Learning](https://mlsanity.com/paper/1904.11643/) (2019)
- [CEREALS - Cost-Effective REgion-based Active Learning for Semantic Segmentation](https://mlsanity.com/paper/1810.09726/) (2018)
- [TransVG++: End-to-End Visual Grounding with Language Conditioned Vision Transformer](https://mlsanity.com/paper/2206.06619/) (2022)
- [Low Budget Active Learning via Wasserstein Distance: An Integer Programming Approach](https://mlsanity.com/paper/2106.02968/) (2021)
- [Pseudo-Q: Generating Pseudo Language Queries for Visual Grounding](https://mlsanity.com/paper/2203.08481/) (2022)
- [OneRef: Unified One-tower Expression Grounding and Segmentation with Mask Referring Modeling](https://mlsanity.com/paper/2410.08021/) (2024)
- [Shatter and Gather: Learning Referring Image Segmentation with Text Supervision](https://mlsanity.com/paper/2308.15512/) (2023)
- [MetaBox+: A new Region Based Active Learning Method for Semantic Segmentation using Priority Maps](https://mlsanity.com/paper/2010.01884/) (2020)
- [Active Learning for Visual Question Answering: An Empirical Study](https://mlsanity.com/paper/1711.01732/) (2017)
- [RESMatch: Referring Expression Segmentation in a Semi-Supervised Manner](https://mlsanity.com/paper/2402.05589/) (2024)
- [On uncertainty estimation in active learning for image segmentation](https://mlsanity.com/paper/2007.06364/) (2020)

## Abstract (arXiv)

Collecting natural-language referring expressions along with region annotations, such as masks or boxes, is a major bottleneck in visual grounding (VG), as annotators must write descriptions that distinguish target regions from visually similar ones. We tackle this by formulating active learning (AL) for VG under the realistic setting where only raw images are available without accompanying text. Since ground-truth text is unavailable, sample selection must estimate which images contain ambiguous regions that would require discriminative referring expressions. To address this, we generate auxiliary region-text pairs using foundation models, and introduce Referred Region Ambiguity, a new acquisition function that measures whether the model's confidence collapses onto a single region or disperses across multiple candidates. It allows our method to prioritize images with strong cross-region competition, which are more informative due to their visual ambiguity. We also design a referring-expression annotation interface that helps annotators quickly focus on writing discriminative language with a few clicks. Experiments on RIS and REC benchmarks show that our AL framework consistently outperforms several AL baselines, while a user study shows up to 1.6X faster description labeling of ours.