相关论文: Feature Unlearning for Pre-trained GANs and VAEs

The dynamics of gradient-based training in neural networks often exhibit nontrivial structures; hence, understanding them remains a central challenge in theoretical machine learning. In particular, a concept of feature unlearning, in which…

Masked autoencoders (MAEs) have established themselves as a powerful method for unsupervised pre-training for computer vision tasks. While vanilla MAEs put equal emphasis on reconstructing the individual parts of the image, we propose to…

How can we effectively unlearn selected concepts from pre-trained generative foundation models without resorting to extensive retraining? This research introduces `continual unlearning', a novel paradigm that enables the targeted removal of…

With recent progress in graphics, it has become more tractable to train models on synthetic images, potentially avoiding the need for expensive annotations. However, learning from synthetic images may not achieve the desired performance due…

Machine Unlearning aims to remove undesired information from trained models without requiring full retraining from scratch. Despite recent advancements, their underlying loss landscapes and optimization dynamics received less attention. In…

We propose a new strategy to improve the accuracy and robustness of image classification. First, we train a baseline CNN model. Then, we identify challenging regions in the feature space by identifying all misclassified samples, and…

Unsupervised representation learning holds the promise of exploiting large amounts of unlabeled data to learn general representations. A promising technique for unsupervised learning is the framework of Variational Auto-encoders (VAEs).…

Over the years, computer vision researchers have spent an immense amount of effort on designing image features for the visual object recognition task. We propose to incorporate this valuable experience to guide the task of training deep…

Deep neural networks often rely on spurious correlations in training data, leading to biased or unfair predictions in safety-critical domains such as medicine and autonomous driving. While conventional bias mitigation typically requires…

Machine unlearning (MUL) refers to the problem of making a pre-trained model selectively forget some training instances or class(es) while retaining performance on the remaining dataset. Existing MUL research involves fine-tuning using a…

GAN is a deep-learning based generative approach to generate contents such as images, languages and speeches. Recently, studies have shown that GAN can also be applied to generative adversarial attack examples to fool the machine-learning…

By pretraining to synthesize coherent images from perturbed inputs, generative models inherently learn to understand object boundaries and scene compositions. How can we repurpose these generative representations for general-purpose…

Fairness in visual recognition is becoming a prominent and critical topic of discussion as recognition systems are deployed at scale in the real world. Models trained from data in which target labels are correlated with protected attributes…

Object Transfiguration replaces an object in an image with another object from a second image. For example it can perform tasks like "putting exactly those eyeglasses from image A on the nose of the person in image B". Usage of exemplar…

As deep learning models are becoming larger and data-hungrier, there are growing ethical, legal and technical concerns over use of data: in practice, agreements on data use may change over time, rendering previously-used training data…

This paper presents a novel approach for text/speech-driven animation of a photo-realistic head model based on blend-shape geometry, dynamic textures, and neural rendering. Training a VAE for geometry and texture yields a parametric model…

We address the problem of segmenting 3D multi-modal medical images in scenarios where very few labeled examples are available for training. Leveraging the recent success of adversarial learning for semi-supervised segmentation, we propose a…

Machine learning models may inadvertently memorize sensitive, unauthorized, or malicious data, posing risks of privacy breaches, security vulnerabilities, and performance degradation. To address these issues, machine unlearning has emerged…

Deep classifiers are known to rely on spurious features $\unicode{x2013}$ patterns which are correlated with the target on the training data but not inherently relevant to the learning problem, such as the image backgrounds when classifying…

Neural networks are prone to learning shortcuts -- they often model simple correlations, ignoring more complex ones that potentially generalize better. Prior works on image classification show that instead of learning a connection to object…