Out-of-Distribution Detection without Class Labels
- URL: http://arxiv.org/abs/2112.07662v1
- Date: Tue, 14 Dec 2021 18:58:32 GMT
- Title: Out-of-Distribution Detection without Class Labels
- Authors: Niv Cohen, Ron Abutbul, Yedid Hoshen
- Abstract summary: Anomaly detection methods identify samples that deviate from the normal behavior of the dataset.
Current methods struggle when faced with training data consisting of multiple classes but no labels.
We first cluster images using self-supervised methods and obtain a cluster label for every image.
We finetune pretrained features on the task of classifying images by their cluster labels.
- Score: 29.606812876314386
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Anomaly detection methods identify samples that deviate from the normal
behavior of the dataset. It is typically tackled either for training sets
containing normal data from multiple labeled classes or a single unlabeled
class. Current methods struggle when faced with training data consisting of
multiple classes but no labels. In this work, we first discover that
classifiers learned by self-supervised image clustering methods provide a
strong baseline for anomaly detection on unlabeled multi-class datasets.
Perhaps surprisingly, we find that initializing clustering methods with
pre-trained features does not improve over their self-supervised counterparts.
This is due to the phenomenon of catastrophic forgetting. Instead, we suggest a
two stage approach. We first cluster images using self-supervised methods and
obtain a cluster label for every image. We use the cluster labels as "pseudo
supervision" for out-of-distribution (OOD) methods. Specifically, we finetune
pretrained features on the task of classifying images by their cluster labels.
We provide extensive analyses of our method and demonstrate the necessity of
our two-stage approach. We evaluate it against the state-of-the-art
self-supervised and pretrained methods and demonstrate superior performance.
Related papers
- Generalized Category Discovery with Clustering Assignment Consistency [56.92546133591019]
Generalized category discovery (GCD) is a recently proposed open-world task.
We propose a co-training-based framework that encourages clustering consistency.
Our method achieves state-of-the-art performance on three generic benchmarks and three fine-grained visual recognition datasets.
arXiv Detail & Related papers (2023-10-30T00:32:47Z) - Self-Training: A Survey [5.772546394254112]
Semi-supervised algorithms aim to learn prediction functions from a small set of labeled observations and a large set of unlabeled observations.
Among the existing techniques, self-training methods have undoubtedly attracted greater attention in recent years.
We present self-training methods for binary and multi-class classification; as well as their variants and two related approaches.
arXiv Detail & Related papers (2022-02-24T11:40:44Z) - AutoNovel: Automatically Discovering and Learning Novel Visual
Categories [138.80332861066287]
We present a new approach called AutoNovel to tackle the problem of discovering novel classes in an image collection given labelled examples of other classes.
We evaluate AutoNovel on standard classification benchmarks and substantially outperform current methods for novel category discovery.
arXiv Detail & Related papers (2021-06-29T11:12:16Z) - A Closer Look at Self-training for Zero-Label Semantic Segmentation [53.4488444382874]
Being able to segment unseen classes not observed during training is an important technical challenge in deep learning.
Prior zero-label semantic segmentation works approach this task by learning visual-semantic embeddings or generative models.
We propose a consistency regularizer to filter out noisy pseudo-labels by taking the intersections of the pseudo-labels generated from different augmentations of the same image.
arXiv Detail & Related papers (2021-04-21T14:34:33Z) - Boosting the Performance of Semi-Supervised Learning with Unsupervised
Clustering [10.033658645311188]
We show that ignoring labels altogether for whole epochs intermittently during training can significantly improve performance in the small sample regime.
We demonstrate our method's efficacy in boosting several state-of-the-art SSL algorithms.
arXiv Detail & Related papers (2020-12-01T14:19:14Z) - SCAN: Learning to Classify Images without Labels [73.69513783788622]
We advocate a two-step approach where feature learning and clustering are decoupled.
A self-supervised task from representation learning is employed to obtain semantically meaningful features.
We obtain promising results on ImageNet, and outperform several semi-supervised learning methods in the low-data regime.
arXiv Detail & Related papers (2020-05-25T18:12:33Z) - Unsupervised Person Re-identification via Multi-label Classification [55.65870468861157]
This paper formulates unsupervised person ReID as a multi-label classification task to progressively seek true labels.
Our method starts by assigning each person image with a single-class label, then evolves to multi-label classification by leveraging the updated ReID model for label prediction.
To boost the ReID model training efficiency in multi-label classification, we propose the memory-based multi-label classification loss (MMCL)
arXiv Detail & Related papers (2020-04-20T12:13:43Z) - Automatically Discovering and Learning New Visual Categories with
Ranking Statistics [145.89790963544314]
We tackle the problem of discovering novel classes in an image collection given labelled examples of other classes.
We learn a general-purpose clustering model and use the latter to identify the new classes in the unlabelled data.
We evaluate our approach on standard classification benchmarks and outperform current methods for novel category discovery by a significant margin.
arXiv Detail & Related papers (2020-02-13T18:53:32Z)
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.