# From Zero to Hero: Cold-Start Anomaly Detection

arXiv: https://arxiv.org/abs/2405.20341 · HTML: https://mlsanity.com/paper/2405.20341/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 30 references that are in the map.
- First posted on arXiv 30 May 2024.

## Builds on (most cited first, 19 of 19)

- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [Towards General Text Embeddings with Multi-stage Contrastive Learning](https://mlsanity.com/paper/2308.03281/) (2023)
- [Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty](https://mlsanity.com/paper/1906.12340/) (2019)
- [Efficient Intent Detection with Dual Sentence Encoders](https://mlsanity.com/paper/2003.04807/) (2020)
- [An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction](https://mlsanity.com/paper/1909.02027/) (2019)
- [AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection](https://mlsanity.com/paper/2310.18961/) (2023)
- [PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentation](https://mlsanity.com/paper/2010.05903/) (2020)
- [DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detection](https://mlsanity.com/paper/2211.11317/) (2022)
- [Neural Transformation Learning for Deep Anomaly Detection Beyond Images](https://mlsanity.com/paper/2103.16440/) (2021)
- [Mean-Shifted Contrastive Loss for Anomaly Detection](https://mlsanity.com/paper/2106.03844/) (2021)
- [Discovering New Intents with Deep Aligned Clustering](https://mlsanity.com/paper/2012.08987/) (2020)
- [Deep Unknown Intent Detection with Margin Loss](https://mlsanity.com/paper/1906.00434/) (2019)
- [Out-of-domain Detection for Natural Language Understanding in Dialog Systems](https://mlsanity.com/paper/1909.03862/) (2019)
- [Discovering New Intents via Constrained Deep Adaptive Clustering with Cluster Refinement](https://mlsanity.com/paper/1911.08891/) (2019)
- [Deep Open Intent Classification with Adaptive Decision Boundary](https://mlsanity.com/paper/2012.10209/) (2020)
- [MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Images](https://mlsanity.com/paper/2401.16753/) (2024)
- [Modeling Discriminative Representations for Out-of-Domain Detection with Supervised Contrastive Learning](https://mlsanity.com/paper/2105.14289/) (2021)
- [Out-of-Scope Intent Detection with Self-Supervision and Discriminative Training](https://mlsanity.com/paper/2106.08616/) (2021)
- [Are Pretrained Transformers Robust in Intent Classification? A Missing Ingredient in Evaluation of Out-of-Scope Intent Detection](https://mlsanity.com/paper/2106.04564/) (2021)

## Built on by (most cited first, 2 of 2)

- [SciReplicate-Bench: Benchmarking LLMs in Agent-driven Algorithmic Reproduction from Research Papers](https://mlsanity.com/paper/2504.00255/) (2025)
- [Differentially Private Relational Learning with Entity-level Privacy Guarantees](https://mlsanity.com/paper/2506.08347/) (2025)

## Abstract (arXiv)

When first deploying an anomaly detection system, e.g., to detect out-of-scope queries in chatbots, there are no observed data, making data-driven approaches ineffective. Zero-shot anomaly detection methods offer a solution to such "cold-start" cases, but unfortunately they are often not accurate enough. This paper studies the realistic but underexplored cold-start setting where an anomaly detection model is initialized using zero-shot guidance, but subsequently receives a small number of contaminated observations (namely, that may include anomalies). The goal is to make efficient use of both the zero-shot guidance and the observations. We propose ColdFusion, a method that effectively adapts the zero-shot anomaly detector to contaminated observations. To support future development of this new setting, we propose an evaluation suite consisting of evaluation protocols and metrics.