# Language-Guided Open-World Anomaly Segmentation

arXiv: https://arxiv.org/abs/2512.01427 · HTML: https://mlsanity.com/paper/2512.01427/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 35 references that are in the map.
- First posted on arXiv 1 Dec 2025.

## Builds on (most cited first, 30 of 32)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP](https://mlsanity.com/paper/2210.04150/) (2022)
- [Scaling Out-of-Distribution Detection for Real-World Settings](https://mlsanity.com/paper/1911.11132/) (2019)
- [WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation](https://mlsanity.com/paper/2303.14814/) (2023)
- [Recognize Anything: A Strong Image Tagging Model](https://mlsanity.com/paper/2306.03514/) (2023)
- [Side Adapter Network for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2302.12242/) (2023)
- [CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2303.11797/) (2023)
- [SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation](https://mlsanity.com/paper/2104.14812/) (2021)
- [Detecting the Unexpected via Image Resynthesis](https://mlsanity.com/paper/1904.07595/) (2019)
- [AutoTAMP: Autoregressive Task and Motion Planning with LLMs as Translators and Checkers](https://mlsanity.com/paper/2306.06531/) (2023)
- [GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Models](https://mlsanity.com/paper/2210.02025/) (2022)
- [Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene Segmentation](https://mlsanity.com/paper/2107.11264/) (2021)
- [RbA: Segmenting Unknown Regions Rejected by All](https://mlsanity.com/paper/2211.14293/) (2022)
- [Semantic Anomaly Detection with Large Language Models](https://mlsanity.com/paper/2305.11307/) (2023)
- [Deep Metric Learning for Open World Semantic Segmentation](https://mlsanity.com/paper/2108.04562/) (2021)
- [On Advantages of Mask-level Recognition for Outlier-aware Segmentation](https://mlsanity.com/paper/2301.03407/) (2023)
- [Triggering Failures: Out-Of-Distribution detection by learning from local adversarial attacks in Semantic Segmentation](https://mlsanity.com/paper/2108.01634/) (2021)
- [Maskomaly:Zero-Shot Mask Anomaly Segmentation](https://mlsanity.com/paper/2305.16972/) (2023)
- [Outlier detection by ensembling uncertainty with negative objectness](https://mlsanity.com/paper/2402.15374/) (2024)
- [Open-World Semantic Segmentation Including Class Similarity](https://mlsanity.com/paper/2403.07532/) (2024)
- [Mask2Anomaly: Mask Transformer for Universal Open-set Segmentation](https://mlsanity.com/paper/2309.04573/) (2023)
- [Exploring Open-Vocabulary Semantic Segmentation without Human Labels](https://mlsanity.com/paper/2306.00450/) (2023)
- [Hybrid Open-set Segmentation with Synthetic Negative Data](https://mlsanity.com/paper/2301.08555/) (2023)
- [Auto-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2312.04539/) (2023)
- [Vocabulary-free Image Classification and Semantic Segmentation](https://mlsanity.com/paper/2404.10864/) (2024)
- [Segmenting Objectiveness and Task-awareness Unknown Region for Autonomous Driving](https://mlsanity.com/paper/2504.19183/) (2025)

## Abstract (arXiv)

Open-world and anomaly segmentation methods seek to enable autonomous driving systems to detect and segment both known and unknown objects in real-world scenes. However, existing methods do not assign semantically meaningful labels to unknown regions, and distinguishing and learning representations for unknown classes remains difficult. While open-vocabulary segmentation methods show promise in generalizing to novel classes, they require a fixed inference vocabulary and thus cannot be directly applied to anomaly segmentation where unknown classes are unconstrained. We propose Clipomaly, the first CLIP-based open-world and anomaly segmentation method for autonomous driving. Our zero-shot approach requires no anomaly-specific training data and leverages CLIP's shared image-text embedding space to both segment unknown objects and assign human-interpretable names to them. Unlike open-vocabulary methods, our model dynamically extends its vocabulary at inference time without retraining, enabling robust detection and naming of anomalies beyond common class definitions such as those in Cityscapes. Clipomaly achieves state-of-the-art performance on established anomaly segmentation benchmarks while providing interpretability and flexibility essential for practical deployment.