Enhancing Anomaly Detection Generalization through Knowledge Exposure: The Dual Effects of Augmentation
- URL: http://arxiv.org/abs/2406.10617v1
- Date: Sat, 15 Jun 2024 12:37:36 GMT
- Title: Enhancing Anomaly Detection Generalization through Knowledge Exposure: The Dual Effects of Augmentation
- Authors: Mohammad Akhavan Anvari, Rojina Kashefi, Vahid Reza Khazaie, Mohammad Khalooei, Mohammad Sabokrou,
- Abstract summary: Anomaly detection involves identifying instances within a dataset that deviates from the norm and occur infrequently.
Current benchmarks tend to favor methods biased towards low diversity in normal data, which does not align with real-world scenarios.
We propose new testing protocols and a novel method called Knowledge Exposure (KE), which integrates external knowledge to comprehend concept dynamics.
- Score: 9.740752855568202
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Anomaly detection involves identifying instances within a dataset that deviate from the norm and occur infrequently. Current benchmarks tend to favor methods biased towards low diversity in normal data, which does not align with real-world scenarios. Despite advancements in these benchmarks, contemporary anomaly detection methods often struggle with out-of-distribution generalization, particularly in classifying samples with subtle transformations during testing. These methods typically assume that normal samples during test time have distributions very similar to those in the training set, while anomalies are distributed much further away. However, real-world test samples often exhibit various levels of distribution shift while maintaining semantic consistency. Therefore, effectively generalizing to samples that have undergone semantic-preserving transformations, while accurately detecting normal samples whose semantic meaning has changed after transformation as anomalies, is crucial for the trustworthiness and reliability of a model. For example, although it is clear that rotation shifts the meaning for a car in the context of anomaly detection but preserves the meaning for a bird, current methods are likely to detect both as abnormal. This complexity underscores the necessity for dynamic learning procedures rooted in the intrinsic concept of outliers. To address this issue, we propose new testing protocols and a novel method called Knowledge Exposure (KE), which integrates external knowledge to comprehend concept dynamics and differentiate transformations that induce semantic shifts. This approach enhances generalization by utilizing insights from a pre-trained CLIP model to evaluate the significance of anomalies for each concept. Evaluation on CIFAR-10, CIFAR-100, and SVHN with the new protocols demonstrates superior performance compared to previous methods.
Related papers
- MeLIAD: Interpretable Few-Shot Anomaly Detection with Metric Learning and Entropy-based Scoring [2.394081903745099]
We propose MeLIAD, a novel methodology for interpretable anomaly detection.
MeLIAD is based on metric learning and achieves interpretability by design without relying on any prior distribution assumptions of true anomalies.
Experiments on five public benchmark datasets, including quantitative and qualitative evaluation of interpretability, demonstrate that MeLIAD achieves improved anomaly detection and localization performance.
arXiv Detail & Related papers (2024-09-20T16:01:43Z) - Enhancing Anomaly Detection via Generating Diversified and Hard-to-distinguish Synthetic Anomalies [7.021105583098609]
Recent approaches have focused on leveraging domain-specific transformations or perturbations to generate synthetic anomalies from normal samples.
We introduce a novel domain-agnostic method that employs a set of conditional perturbators and a discriminator.
We demonstrate the superiority of our method over state-of-the-art benchmarks.
arXiv Detail & Related papers (2024-09-16T08:15:23Z) - GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detection [60.78684630040313]
Diffusion models tend to reconstruct normal counterparts of test images with certain noises added.
From the global perspective, the difficulty of reconstructing images with different anomalies is uneven.
We propose a global and local adaptive diffusion model (abbreviated to GLAD) for unsupervised anomaly detection.
arXiv Detail & Related papers (2024-06-11T17:27:23Z) - Anomaly Detection by Context Contrasting [57.695202846009714]
Anomaly detection focuses on identifying samples that deviate from the norm.
Recent advances in self-supervised learning have shown great promise in this regard.
We propose Con$$, which learns through context augmentations.
arXiv Detail & Related papers (2024-05-29T07:59:06Z) - Video Anomaly Detection via Spatio-Temporal Pseudo-Anomaly Generation : A Unified Approach [49.995833831087175]
This work proposes a novel method for generating generic Video-temporal PAs by inpainting a masked out region of an image.
In addition, we present a simple unified framework to detect real-world anomalies under the OCC setting.
Our method performs on par with other existing state-of-the-art PAs generation and reconstruction based methods under the OCC setting.
arXiv Detail & Related papers (2023-11-27T13:14:06Z) - GIT: Detecting Uncertainty, Out-Of-Distribution and Adversarial Samples
using Gradients and Invariance Transformations [77.34726150561087]
We propose a holistic approach for the detection of generalization errors in deep neural networks.
GIT combines the usage of gradient information and invariance transformations.
Our experiments demonstrate the superior performance of GIT compared to the state-of-the-art on a variety of network architectures.
arXiv Detail & Related papers (2023-07-05T22:04:38Z) - SaliencyCut: Augmenting Plausible Anomalies for Anomaly Detection [24.43321988051129]
We propose a novel saliency-guided data augmentation method, SaliencyCut, to produce pseudo but more common anomalies.
We then design a novel patch-wise residual module in the anomaly learning head to extract and assess the fine-grained anomaly features from each sample.
arXiv Detail & Related papers (2023-06-14T08:55:36Z) - Augment to Detect Anomalies with Continuous Labelling [10.646747658653785]
Anomaly detection is to recognize samples that differ in some respect from the training observations.
Recent state-of-the-art deep learning-based anomaly detection methods suffer from high computational cost, complexity, unstable training procedures, and non-trivial implementation.
We leverage a simple learning procedure that trains a lightweight convolutional neural network, reaching state-of-the-art performance in anomaly detection.
arXiv Detail & Related papers (2022-07-03T20:11:51Z) - Self-Supervised Training with Autoencoders for Visual Anomaly Detection [61.62861063776813]
We focus on a specific use case in anomaly detection where the distribution of normal samples is supported by a lower-dimensional manifold.
We adapt a self-supervised learning regime that exploits discriminative information during training but focuses on the submanifold of normal examples.
We achieve a new state-of-the-art result on the MVTec AD dataset -- a challenging benchmark for visual anomaly detection in the manufacturing domain.
arXiv Detail & Related papers (2022-06-23T14:16:30Z) - Explainable Deep Few-shot Anomaly Detection with Deviation Networks [123.46611927225963]
We introduce a novel weakly-supervised anomaly detection framework to train detection models.
The proposed approach learns discriminative normality by leveraging the labeled anomalies and a prior probability.
Our model is substantially more sample-efficient and robust, and performs significantly better than state-of-the-art competing methods in both closed-set and open-set settings.
arXiv Detail & Related papers (2021-08-01T14:33:17Z)
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.