MOS: Towards Scaling Out-of-distribution Detection for Large Semantic
Space
- URL: http://arxiv.org/abs/2105.01879v1
- Date: Wed, 5 May 2021 05:58:29 GMT
- Title: MOS: Towards Scaling Out-of-distribution Detection for Large Semantic
Space
- Authors: Rui Huang and Yixuan Li
- Abstract summary: We propose a group-based OOD detection framework and a novel OOD scoring function termed MOS.
Our key idea is to decompose the large semantic space into smaller groups with similar concepts.
We evaluate models trained on ImageNet against four carefully curated OOD datasets, spanning diverse semantics.
- Score: 18.367982926200714
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Detecting out-of-distribution (OOD) inputs is a central challenge for safely
deploying machine learning models in the real world. Existing solutions are
mainly driven by small datasets, with low resolution and very few class labels
(e.g., CIFAR). As a result, OOD detection for large-scale image classification
tasks remains largely unexplored. In this paper, we bridge this critical gap by
proposing a group-based OOD detection framework, along with a novel OOD scoring
function termed MOS. Our key idea is to decompose the large semantic space into
smaller groups with similar concepts, which allows simplifying the decision
boundaries between in- vs. out-of-distribution data for effective OOD
detection. Our method scales substantially better for high-dimensional class
space than previous approaches. We evaluate models trained on ImageNet against
four carefully curated OOD datasets, spanning diverse semantics. MOS
establishes state-of-the-art performance, reducing the average FPR95 by 14.33%
while achieving 6x speedup in inference compared to the previous best method.
Related papers
- WeiPer: OOD Detection using Weight Perturbations of Class Projections [11.130659240045544]
We introduce perturbations of the class projections in the final fully connected layer which creates a richer representation of the input.
We achieve state-of-the-art OOD detection results across multiple benchmarks of the OpenOOD framework.
arXiv Detail & Related papers (2024-05-27T13:38:28Z) - How to Overcome Curse-of-Dimensionality for Out-of-Distribution
Detection? [29.668859994222238]
We propose a novel framework, Subspace Nearest Neighbor (SNN), for OOD detection.
In training, our method regularizes the model and its feature representation by leveraging the most relevant subset of dimensions.
Compared to the current best distance-based method, SNN reduces the average FPR95 by 15.96% on the CIFAR-100 benchmark.
arXiv Detail & Related papers (2023-12-22T06:04:09Z) - 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) - Innovative Horizons in Aerial Imagery: LSKNet Meets DiffusionDet for
Advanced Object Detection [55.2480439325792]
We present an in-depth evaluation of an object detection model that integrates the LSKNet backbone with the DiffusionDet head.
The proposed model achieves a mean average precision (MAP) of approximately 45.7%, which is a significant improvement.
This advancement underscores the effectiveness of the proposed modifications and sets a new benchmark in aerial image analysis.
arXiv Detail & Related papers (2023-11-21T19:49:13Z) - 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) - Building One-class Detector for Anything: Open-vocabulary Zero-shot OOD
Detection Using Text-image Models [23.302018871162186]
We propose a novel one-class open-set OOD detector that leverages text-image pre-trained models in a zero-shot fashion.
Our approach is designed to detect anything not in-domain and offers the flexibility to detect a wide variety of OOD.
Our method shows superior performance over previous methods on all benchmarks.
arXiv Detail & Related papers (2023-05-26T18:58:56Z) - Metric Learning and Adaptive Boundary for Out-of-Domain Detection [0.9236074230806579]
We have designed an OOD detection algorithm independent of OOD data.
Our algorithm is based on a simple but efficient approach of combining metric learning with adaptive decision boundary.
Compared to other algorithms, we have found that our proposed algorithm has significantly improved OOD performance in a scenario with a lower number of classes.
arXiv Detail & Related papers (2022-04-22T17:54:55Z) - Out-of-distribution Detection with Deep Nearest Neighbors [33.71627349163909]
Out-of-distribution (OOD) detection is a critical task for deploying machine learning models in the open world.
In this paper, we explore the efficacy of non-parametric nearest-neighbor distance for OOD detection.
We demonstrate the effectiveness of nearest-neighbor-based OOD detection on several benchmarks and establish superior performance.
arXiv Detail & Related papers (2022-04-13T16:45:21Z) - Highly Accurate Dichotomous Image Segmentation [139.79513044546]
A new task called dichotomous image segmentation (DIS) aims to segment highly accurate objects from natural images.
We collect the first large-scale dataset, DIS5K, which contains 5,470 high-resolution (e.g., 2K, 4K or larger) images.
We also introduce a simple intermediate supervision baseline (IS-Net) using both feature-level and mask-level guidance for DIS model training.
arXiv Detail & Related papers (2022-03-06T20:09:19Z) - Triggering Failures: Out-Of-Distribution detection by learning from
local adversarial attacks in Semantic Segmentation [76.2621758731288]
We tackle the detection of out-of-distribution (OOD) objects in semantic segmentation.
Our main contribution is a new OOD detection architecture called ObsNet associated with a dedicated training scheme based on Local Adversarial Attacks (LAA)
We show it obtains top performances both in speed and accuracy when compared to ten recent methods of the literature on three different datasets.
arXiv Detail & Related papers (2021-08-03T17:09:56Z) - Enhancing the Generalization for Intent Classification and Out-of-Domain
Detection in SLU [70.44344060176952]
Intent classification is a major task in spoken language understanding (SLU)
Recent works have shown that using extra data and labels can improve the OOD detection performance.
This paper proposes to train a model with only IND data while supporting both IND intent classification and OOD detection.
arXiv Detail & Related papers (2021-06-28T08:27:38Z)
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.