TagFog: Textual Anchor Guidance and Fake Outlier Generation for Visual Out-of-Distribution Detection
- URL: http://arxiv.org/abs/2412.05292v1
- Date: Fri, 22 Nov 2024 14:40:25 GMT
- Title: TagFog: Textual Anchor Guidance and Fake Outlier Generation for Visual Out-of-Distribution Detection
- Authors: Jiankang Chen, Tong Zhang, Wei-Shi Zheng, Ruixuan Wang,
- Abstract summary: Out-of-distribution (OOD) detection is crucial in many real-world applications.
We propose a new learning framework which leverage simple Jigsaw-based fake OOD data and rich semantic embeddings (anchors') from the ChatGPT description of ID knowledge to help guide the training of the image encoder.
- Score: 34.31570050254269
- License:
- Abstract: Out-of-distribution (OOD) detection is crucial in many real-world applications. However, intelligent models are often trained solely on in-distribution (ID) data, leading to overconfidence when misclassifying OOD data as ID classes. In this study, we propose a new learning framework which leverage simple Jigsaw-based fake OOD data and rich semantic embeddings (`anchors') from the ChatGPT description of ID knowledge to help guide the training of the image encoder. The learning framework can be flexibly combined with existing post-hoc approaches to OOD detection, and extensive empirical evaluations on multiple OOD detection benchmarks demonstrate that rich textual representation of ID knowledge and fake OOD knowledge can well help train a visual encoder for OOD detection. With the learning framework, new state-of-the-art performance was achieved on all the benchmarks. The code is available at \url{https://github.com/Cverchen/TagFog}.
Related papers
- SimLabel: Consistency-Guided OOD Detection with Pretrained Vision-Language Models [7.90233294809002]
We investigate the ability of image-text comprehension among different semantic-related ID labels in vision-language models (VLMs)
We propose a novel post-hoc strategy called SimLabel to enhance the separability between ID and out-of-distribution (OOD) samples.
Our experiments demonstrate the superior performance of SimLabel on various zero-shot OOD detection benchmarks.
arXiv Detail & Related papers (2025-01-20T13:36:30Z) - FodFoM: Fake Outlier Data by Foundation Models Creates Stronger Visual Out-of-Distribution Detector [25.224930928724326]
Out-of-Distribution (OOD) detection is crucial when deploying machine learning models in open-world applications.
We propose a novel OOD detection framework FodFoM that innovatively combines multiple foundation models to generate two types of challenging fake outlier images.
New state-of-the-art OOD detection performance is achieved on multiple benchmarks.
arXiv Detail & Related papers (2024-11-22T17:29:52Z) - Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detection [71.93411099797308]
Out-of-distribution (OOD) samples are crucial when deploying machine learning models in open-world scenarios.
We propose to tackle this constraint by leveraging the expert knowledge and reasoning capability of large language models (LLM) to potential Outlier Exposure, termed EOE.
EOE can be generalized to different tasks, including far, near, and fine-language OOD detection.
EOE achieves state-of-the-art performance across different OOD tasks and can be effectively scaled to the ImageNet-1K dataset.
arXiv Detail & Related papers (2024-06-02T17:09:48Z) - 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) - EAT: Towards Long-Tailed Out-of-Distribution Detection [55.380390767978554]
This paper addresses the challenging task of long-tailed OOD detection.
The main difficulty lies in distinguishing OOD data from samples belonging to the tail classes.
We propose two simple ideas: (1) Expanding the in-distribution class space by introducing multiple abstention classes, and (2) Augmenting the context-limited tail classes by overlaying images onto the context-rich OOD data.
arXiv Detail & Related papers (2023-12-14T13:47:13Z) - Exploring Large Language Models for Multi-Modal Out-of-Distribution
Detection [67.68030805755679]
Large language models (LLMs) encode a wealth of world knowledge and can be prompted to generate descriptive features for each class.
In this paper, we propose to apply world knowledge to enhance OOD detection performance through selective generation from LLMs.
arXiv Detail & Related papers (2023-10-12T04:14:28Z) - Class Relevance Learning For Out-of-distribution Detection [16.029229052068]
This paper presents an innovative class relevance learning method tailored for OOD detection.
Our method establishes a comprehensive class relevance learning framework, strategically harnessing interclass relationships within the OOD pipeline.
arXiv Detail & Related papers (2023-09-21T08:38:21Z) - From Global to Local: Multi-scale Out-of-distribution Detection [129.37607313927458]
Out-of-distribution (OOD) detection aims to detect "unknown" data whose labels have not been seen during the in-distribution (ID) training process.
Recent progress in representation learning gives rise to distance-based OOD detection.
We propose Multi-scale OOD DEtection (MODE), a first framework leveraging both global visual information and local region details.
arXiv Detail & Related papers (2023-08-20T11:56:25Z) - LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learning [37.36999826208225]
We present a novel vision-language prompt learning approach for few-shot out-of-distribution (OOD) detection.
LoCoOp performs OOD regularization that utilizes the portions of CLIP local features as OOD features during training.
LoCoOp outperforms existing zero-shot and fully supervised detection methods.
arXiv Detail & Related papers (2023-06-02T06:33:08Z) - 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)
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.