Related papers: DISYRE: Diffusion-Inspired SYnthetic REstoration f…
Video anomaly detection (VAD) is an important computer vision problem. Thanks to the mode coverage capabilities of generative models, the likelihood-based paradigm is catching growing interest, as it can model normal distribution and detect…
Anomaly detection is a critical task in industrial manufacturing, aiming to identify defective parts of products. Most industrial anomaly detection methods assume the availability of sufficient normal data for training. This assumption may…
How diffusion models generalize beyond their training set is not known, and is somewhat mysterious given two facts: the optimum of the denoising score matching (DSM) objective usually used to train diffusion models is the score function of…
Combining neuroimaging datasets from multiple sites and scanners can help increase statistical power and thus provide greater insight into subtle neuroanatomical effects. However, site-specific effects pose a challenge by potentially…
Use of an autoencoder (AE) as a normal model is a state-of-the-art technique for unsupervised-anomaly detection in sounds (ADS). The AE is trained to minimize the sample mean of the anomaly score of normal sounds in a mini-batch. One…
As advancements in the field of breast cancer treatment continue to progress, the assessment of post-surgical cosmetic outcomes has gained increasing significance due to its substantial impact on patients' quality of life. However,…
Diffusion models have achieved remarkable success in generative modeling. However, this study confirms the existence of overfitting in diffusion model training, particularly in data-limited regimes. To address this challenge, we propose…
Unsupervised Contrastive learning has gained prominence in fields such as vision, and biology, leveraging predefined positive/negative samples for representation learning. Data augmentation, categorized into hand-designed and model-based…
Deploying video anomaly detection in practice is hampered by the scarcity and collection cost of real abnormal footage. We address this by training without any real abnormal videos while evaluating under the standard weakly supervised…
In this paper, we propose the Adversarial Denoising Diffusion Model (ADDM). The ADDM is based on the Denoising Diffusion Probabilistic Model (DDPM) but complementarily trained by adversarial learning. The proposed adversarial learning is…
The detection and localization of anomalies is one important medical image analysis task. Most commonly, Computer Vision anomaly detection approaches rely on manual annotations that are both time consuming and expensive to obtain.…
Anomaly detection (AD) is the machine learning task of identifying highly discrepant abnormal samples by solely relying on the consistency of the normal training samples. Under the constraints of a distribution shift, the assumption that…
Unsupervised anomaly detection (UAD) alleviates large labeling efforts by training exclusively on unlabeled in-distribution data and detecting outliers as anomalies. Generally, the assumption prevails that large training datasets allow the…
Learning generative models directly from corrupted observations is a long standing challenge across natural and scientific domains. We introduce Restoration Score Distillation (RSD), a unified framework for learning high fidelity, one step…
Understanding causal dependencies in observational data is critical for informing decision-making. These relationships are often modeled as Bayesian Networks (BNs) and Directed Acyclic Graphs (DAGs). Existing methods, such as NOTEARS and…
The machine learning community is increasingly recognizing the importance of fostering trust and safety in modern generative AI (GenAI) models. We posit machine unlearning (MU) as a crucial foundation for developing safe, secure, and…
Unsupervised anomaly detection (UAD) aims to find anomalous images by optimising a detector using a training set that contains only normal images. UAD approaches can be based on reconstruction methods, self-supervised approaches, and…
Diffusion-based super-resolution (SR) models have recently garnered significant attention due to their potent restoration capabilities. But conventional diffusion models perform noise sampling from a single distribution, constraining their…
Diffusion-based methods represented as stochastic differential equations on a continuous-time domain have recently proven successful as a non-adversarial generative model. Training such models relies on denoising score matching, which can…
Recommendation systems often rely on implicit feedback, where only positive user-item interactions can be observed. Negative sampling is therefore crucial to provide proper negative training signals. However, existing methods tend to…