ANTS: Shaping the Adaptive Negative Textual Space by MLLM for OOD Detection

• URL: http://arxiv.org/abs/2509.03951v2
• Date: Thu, 11 Sep 2025 19:44:24 GMT
• Title: ANTS: Shaping the Adaptive Negative Textual Space by MLLM for OOD Detection
• Authors: Wenjie Zhu, Yabin Zhang, Xin Jin, Wenjun Zeng, Lei Zhang,
• Abstract summary: We propose shaping an Adaptive Negative Textual Space (ANTS) using multimodal large language models (MLLMs)<n>Our ANTS significantly reduces the FPR95 by 4.2%, establishing a new state-of-the-art. Furthermore, our method is training-free and zero-shot, enabling high scalability.
• Score: 25.474399776634304
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The introduction of negative labels (NLs) has proven effective in enhancing Out-of-Distribution (OOD) detection. However, existing methods often lack an understanding of OOD images, making it difficult to construct an accurate negative space. In addition, the presence of false negative labels significantly degrades their near-OOD performance. To address these issues, we propose shaping an Adaptive Negative Textual Space (ANTS) by leveraging the understanding and reasoning capabilities of multimodal large language models (MLLMs). Specifically, we identify images likely to be OOD samples as negative images and prompt the MLLM to describe these images, generating expressive negative sentences that precisely characterize the OOD distribution and enhance far-OOD detection. For the near-OOD setting, where OOD samples resemble the in-distribution (ID) subset, we first identify the subset of ID classes that are visually similar to negative images and then leverage the reasoning capability of MLLMs to generate visually similar negative labels tailored to this subset, effectively reducing false negatives and improving near-OOD detection. To balance these two types of negative textual spaces, we design an adaptive weighted score that enables the method to handle different OOD task settings (near-OOD and far-OOD) without relying on task-specific prior knowledge, making it highly adaptable in open environments. On the ImageNet benchmark, our ANTS significantly reduces the FPR95 by 4.2\%, establishing a new state-of-the-art. Furthermore, our method is training-free and zero-shot, enabling high scalability.

Related papers

• Mind the Way You Select Negative Texts: Pursuing the Distance Consistency in OOD Detection with VLMs [80.03370593724422]
  Out-of-distribution (OOD) detection seeks to identify samples from unknown classes.<n>Current methods often incorporate intra-modal distance during OOD detection, such as comparing negative texts with ID labels.<n>We propose InterNeg, a framework that systematically utilizes consistent inter-modal distance enhancement from textual and visual perspectives.
  arXiv  Detail & Related papers  (2026-03-03T05:44:47Z)
• Out-of-Distribution Detection with Positive and Negative Prompt Supervision Using Large Language Models [33.39682202143465]
  Out-of-distribution (OOD) detection is committed to delineating the classification boundaries between in-distribution (ID) and OOD images.<n>Negative prompts are introduced to emphasize the dissimilarity between image features and prompt content.<n>We propose Positive and Negative Prompt Supervision, which encourages negative prompts to capture inter-class features.
  arXiv  Detail & Related papers  (2025-11-14T03:24:09Z)
• GOOD: Training-Free Guided Diffusion Sampling for Out-of-Distribution Detection [61.96025941146103]
  GOOD is a novel framework that guides sampling trajectories towards OOD regions using off-the-shelf in-distribution (ID) classifiers.<n> GOOD incorporates dual-level guidance: Image-level guidance based on the gradient of log partition to reduce input likelihood, drives samples toward low-density regions in pixel space.<n>We introduce a unified OOD score that adaptively combines image and feature discrepancies, enhancing detection robustness.
  arXiv  Detail & Related papers  (2025-10-20T03:58:46Z)
• Adaptive Multi-prompt Contrastive Network for Few-shot Out-of-distribution Detection [4.938957922033169]
  Out-of-distribution (OOD) detection attempts to distinguish outlier samples to prevent models trained on the in-distribution (ID) dataset from producing unavailable outputs.<n>Most OOD detection methods require many IID samples for training, which seriously limits their real-world applications.<n>We propose a novel network: Adaptive Multi-prompt Contrastive Network (AMCN), which adapts the ID-OOD separation boundary by learning inter- and intra-class distribution.
  arXiv  Detail & Related papers  (2025-06-21T08:31:29Z)
• AdaNeg: Adaptive Negative Proxy Guided OOD Detection with Vision-Language Models [15.754054667010468]
  Pre-trained vision-language models are effective at identifying out-of-distribution (OOD) samples by using negative labels as guidance. We introduce textitadaptive negative proxies, which are dynamically generated during testing by exploring actual OOD images. Our approach significantly outperforms existing methods, with a 2.45% increase in AUROC and a 6.48% reduction in FPR95.
  arXiv  Detail & Related papers  (2024-10-26T11:20:02Z)
• Rethinking the Evaluation of Out-of-Distribution Detection: A Sorites Paradox [70.57120710151105]
  Most existing out-of-distribution (OOD) detection benchmarks classify samples with novel labels as the OOD data. Some marginal OOD samples actually have close semantic contents to the in-distribution (ID) sample, which makes determining the OOD sample a Sorites Paradox. We construct a benchmark named Incremental Shift OOD (IS-OOD) to address the issue.
  arXiv  Detail & Related papers  (2024-06-14T09:27:56Z)
• Iterative Deployment Exposure for Unsupervised Out-of-Distribution Detection [5.019613806273252]
  Iterative Deployment Exposure (IDE) is a novel and more realistic setting for out-of-distribution (OOD) detection.<n> CSO uses a new U-OOD scoring function that combines the Mahalanobis distance with a nearest-neighbor approach.<n>We validate our approach on a dedicated benchmark, showing that our method greatly improves upon strong baselines on three medical imaging modalities.
  arXiv  Detail & Related papers  (2024-06-04T13:57:34Z)
• Negative Label Guided OOD Detection with Pretrained Vision-Language Models [96.67087734472912]
  Out-of-distribution (OOD) detection aims at identifying samples from unknown classes. We propose a novel post hoc OOD detection method, called NegLabel, which takes a vast number of negative labels from extensive corpus databases.
  arXiv  Detail & Related papers  (2024-03-29T09:19:52Z)
• Rethinking Out-of-distribution (OOD) Detection: Masked Image Modeling is All You Need [52.88953913542445]
  We find surprisingly that simply using reconstruction-based methods could boost the performance of OOD detection significantly. We take Masked Image Modeling as a pretext task for our OOD detection framework (MOOD)
  arXiv  Detail & Related papers  (2023-02-06T08:24:41Z)
• A Simple Test-Time Method for Out-of-Distribution Detection [45.11199798139358]
  This paper proposes a simple Test-time Linear Training (ETLT) method for OOD detection. We find that the probabilities of input images being out-of-distribution are surprisingly linearly correlated to the features extracted by neural networks. We propose an online variant of the proposed method, which achieves promising performance and is more practical in real-world applications.
  arXiv  Detail & Related papers  (2022-07-17T16:02:58Z)
• Robust Out-of-distribution Detection for Neural Networks [51.19164318924997]
  We show that existing detection mechanisms can be extremely brittle when evaluating on in-distribution and OOD inputs. We propose an effective algorithm called ALOE, which performs robust training by exposing the model to both adversarially crafted inlier and outlier examples.
  arXiv  Detail & Related papers  (2020-03-21T17:46:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.