Related papers: Zero-Shot Class Unlearning in CLIP with Synthetic …
Contrastive Language-Image Pre-training (CLIP) has achieved excellent performance over a wide range of tasks. However, the effectiveness of CLIP heavily relies on a substantial corpus of pre-training data, resulting in notable consumption…
Contrastive language-image pre-training (CLIP) models have demonstrated considerable success across various vision-language tasks, such as text-to-image retrieval, where the model is required to effectively process natural language input to…
With its powerful visual-language alignment capability, CLIP performs well in zero-shot and few-shot learning tasks. However, we found in experiments that CLIP's logits suffer from serious inter-class confusion problems in downstream tasks,…
Calibration of deep learning models is crucial to their trustworthiness and safe usage, and as such, has been extensively studied in supervised classification models, with methods crafted to decrease miscalibration. However, there has yet…
CLIP is a widely used foundational vision-language model that is used for zero-shot image recognition and other image-text alignment tasks. We demonstrate that CLIP is vulnerable to change in image quality under compression. This surprising…
While vision-language models like CLIP have advanced zero-shot surgical phase recognition, they struggle with fine-grained surgical activities, especially action triplets. This limitation arises because current CLIP formulations rely on…
Machine unlearning aims to remove targeted knowledge from a trained model without the cost of retraining from scratch. In class unlearning, however, reducing accuracy on forget classes does not necessarily imply true forgetting: forgotten…
Forgetting a subset in machine unlearning is rarely an isolated task. Often, retained samples that are closely related to the forget set can be unintentionally affected, particularly when they share correlated features from pretraining or…
Recently enacted legislation grants individuals certain rights to decide in what fashion their personal data may be used, and in particular a "right to be forgotten". This poses a challenge to machine learning: how to proceed when an…
Machine Unlearning allows participants to remove their data from a trained machine learning model in order to preserve their privacy, and security. However, the machine unlearning literature for generative models is rather limited. The…
Continual learning tackles the setting of learning different tasks sequentially. Despite the lots of previous solutions, most of them still suffer significant forgetting or expensive memory cost. In this work, targeted at these problems, we…
Machine unlearning (MU) seeks to remove knowledge of specific data samples from trained models without the necessity for complete retraining, a task made challenging by the dual objectives of effective erasure of data and maintaining the…
As multimodal models like CLIP become integral to downstream systems, the need to remove sensitive information is critical. However, machine unlearning for contrastively-trained encoders remains underexplored, and existing evaluations fail…
Machine unlearning aims to remove the influence of specific training data from a model without requiring full retraining. This capability is crucial for ensuring privacy, safety, and regulatory compliance. Therefore, verifying whether a…
Recent advances in generative models have demonstrated an exceptional ability to produce highly realistic images. However, previous studies show that generated images often resemble the training data, and this problem becomes more severe as…
Recent work has shown that diffusion models memorize and reproduce training data examples. At the same time, large copyright lawsuits and legislation such as GDPR have highlighted the need for erasing datapoints from diffusion models.…
Existing vision-text contrastive learning like CLIP aims to match the paired image and caption embeddings while pushing others apart, which improves representation transferability and supports zero-shot prediction. However, medical…
Machine unlearning is essential for meeting legal obligations such as the right to be forgotten, which requires the removal of specific data from machine learning models upon request. While several approaches to unlearning have been…
Machine unlearning aims to eliminate the influence of a subset of training samples (i.e., unlearning samples) from a trained model. Effectively and efficiently removing the unlearning samples without negatively impacting the overall model…
This paper introduces Unilogit, a novel self-distillation method for machine unlearning in Large Language Models. Unilogit addresses the challenge of selectively forgetting specific information while maintaining overall model utility, a…