Related papers: Nonlinear Concept Erasure: a Density Matching Appr…
Machine learning models that first learn a representation of a domain in terms of human-understandable concepts, then use it to make predictions, have been proposed to facilitate interpretation and interaction with models trained on…
Concept unlearning aims to erase a target concept from a pretrained text-to-image diffusion model without retraining. Closed-form methods are attractive in this setting because they apply a single deterministic edit to the cross-attention…
Text-to-image generative models can produce photo-realistic images for an extremely broad range of concepts, and their usage has proliferated widely among the general public. On the flip side, these models have numerous drawbacks, including…
Large text-to-image diffusion models have demonstrated remarkable image synthesis capabilities, but their indiscriminate training on Internet-scale data has led to learned concepts that enable harmful, copyrighted, or otherwise undesirable…
With the on-going integration of machine learning systems into the everyday social life of millions the notion of fairness becomes an ever increasing priority in their development. Fairness notions commonly rely on protected attributes to…
Concept erasure helps stop diffusion models (DMs) from generating harmful content; but current methods face robustness retention trade off. Robustness means the model fine-tuned by concept erasure methods resists reactivation of erased…
Neural network models trained on text data have been found to encode undesirable linguistic or sensitive concepts in their representation. Removing such concepts is non-trivial because of a complex relationship between the concept, text…
Creative processes such as painting often involve creating different components of an image one by one. Can we build a computational model to perform this task? Prior works often fail by making global changes to the image, inserting objects…
Interpretability benefits the theoretical understanding of representations. Existing word embeddings are generally dense representations. Hence, the meaning of latent dimensions is difficult to interpret. This makes word embeddings like a…
Embedding is a common technique for analyzing multi-dimensional data. However, the embedding projection cannot always form significant and interpretable visual structures that foreshadow underlying data patterns. We propose an approach that…
With the increasing versatility of text-to-image diffusion models, the ability to selectively erase undesirable concepts (e.g., harmful content) has become indispensable. However, existing concept erasure approaches primarily focus on…
Text-to-image generative models have achieved impressive fidelity and diversity, but can inadvertently produce unsafe or undesirable content due to implicit biases embedded in large-scale training datasets. Existing concept erasure methods,…
The proliferation of text-to-image diffusion models has raised significant privacy and security concerns, particularly regarding the generation of copyrighted or harmful images. In response, concept erasure (defense) methods have been…
Convolutional neural networks (CNNs) are increasingly being used in critical systems, where robustness and alignment are crucial. In this context, the field of explainable artificial intelligence has proposed the generation of high-level…
Concept erasure aims to selectively unlearning undesirable content in diffusion models (DMs) to reduce the risk of sensitive content generation. As a novel paradigm in concept erasure, most existing methods employ adversarial training to…
Despite recent advances in the field of supervised deep learning for text line segmentation, unsupervised deep learning solutions are beginning to gain popularity. In this paper, we present an unsupervised deep learning method that embeds…
Confounding bias is a crucial problem when applying machine learning to practice, especially in clinical practice. We consider the problem of learning representations independent to multiple biases. In literature, this is mostly solved by…
Neural network models are widely used in a variety of domains, often as black-box solutions, since they are not directly interpretable for humans. The field of explainable artificial intelligence aims at developing explanation methods to…
Diffusion models, while powerful, can inadvertently generate harmful or undesirable content, raising significant ethical and safety concerns. Recent machine unlearning approaches offer potential solutions but often lack transparency, making…
We consider the problem of deep fair clustering, which partitions data into clusters via the representations extracted by deep neural networks while hiding sensitive data attributes. To achieve fairness, existing methods present a variety…