相关论文: CIFAR-10-Warehouse: Broad and More Realistic Testb…

Spurious correlations in training data significantly hinder the generalization capability of machine learning models when faced with distribution shifts, leading to the proposition of numberous debiasing methods. However, it remains to be…

As generative Artificial Intelligence (AI) advances, the realism of AI generated imagery has reached a threshold capable of deceiving even vigilant human observers. Yet, while current AI-generated Image Detection (AID) approaches perform…

While Wi-Fi sensing offers a compelling, privacy-preserving alternative to cameras, its practical utility has been fundamentally undermined by a lack of robustness across domains. Models trained in one setup fail to generalize to new…

Diffusion models trained on large datasets can synthesize photo-realistic images of remarkable quality and diversity. However, attributing these images back to the training data-that is, identifying specific training examples which caused…

Machine unlearning algorithms, designed for selective removal of training data from models, have emerged as a promising approach to growing privacy concerns. In this work, we expose a critical yet underexplored vulnerability in the…

The image deepfake detection task has been greatly addressed by the scientific community to discriminate real images from those generated by Artificial Intelligence (AI) models: a binary classification task. In this work, the deepfake…

Empirically validating new 3D-printing related algorithms and implementations requires testing data representative of inputs encountered \emph{in the wild}. An ideal benchmarking dataset should not only draw from the same distribution of…

The rapid advancement of generative AI has raised concerns about the authenticity of digital images, as highly realistic fake images can now be generated at low cost, potentially increasing societal risks. In response, several datasets have…

This paper identifies the flaws in existing open-world learning approaches and attempts to provide a complete picture in the form of \textbf{True Open-World Learning}. We accomplish this by proposing a comprehensive generalize-able…

Clinical machine learning models show a significant performance drop when tested in settings not seen during training. Domain generalisation models promise to alleviate this problem, however, there is still scepticism about whether they…

We present Fashion-MNIST, a new dataset comprising of 28x28 grayscale images of 70,000 fashion products from 10 categories, with 7,000 images per category. The training set has 60,000 images and the test set has 10,000 images. Fashion-MNIST…

Labelled image datasets have played a critical role in high-level image understanding. However, the process of manual labelling is both time-consuming and labor intensive. To reduce the cost of manual labelling, there has been increased…

Generative Adversarial Networks (GANs) have made great progress in synthesizing realistic images in recent years. However, they are often trained on image datasets with either too few samples or too many classes belonging to different data…

By redefining the conventional notions of layers, we present an alternative view on finitely wide, fully trainable deep neural networks as stacked linear models in feature spaces, leading to a kernel machine interpretation. Based on this…

Detecting diffusion-generated images has recently grown into an emerging research area. Existing diffusion-based datasets predominantly focus on general image generation. However, facial forgeries, which pose a more severe social risk, have…

Convolutional neural networks (CNNs) remain a central approach in image classification, but their performance depends strongly on architectural and training choices. This paper presents an empirical ablation-based study of CNN optimization…

Deep generative networks trained via maximum likelihood on a natural image dataset like CIFAR10 often assign high likelihoods to images from datasets with different objects (e.g., SVHN). We refine previous investigations of this failure at…

Consistency models (CMs) are a powerful class of diffusion-based generative models optimized for fast sampling. Most existing CMs are trained using discretized timesteps, which introduce additional hyperparameters and are prone to…

In the era of deep learning, data is the critical determining factor in the performance of neural network models. Generating large datasets suffers from various difficulties such as scalability, cost efficiency and photorealism. To avoid…

Test sets are an integral part of evaluating models and gauging progress in object recognition, and more broadly in computer vision and AI. Existing test sets for object recognition, however, suffer from shortcomings such as bias towards…