相关论文: Zero-Shot Class Unlearning in CLIP with Synthetic …

We show that the influence of a subset of the training samples can be removed -- or "forgotten" -- from the weights of a network trained on large-scale image classification tasks, and we provide strong computable bounds on the amount of…

Machine unlearning enables models to selectively forget training data, driven by privacy regulations such as GDPR and CCPA. However, its fairness implications remain underexplored: when a model forgets a demographic group, does it…

Machine unlearning is the task of updating machine learning (ML) models after a subset of the training data they were trained on is deleted. Methods for the task are desired to combine effectiveness and efficiency, i.e., they should…

In continual learning, there is a serious problem of catastrophic forgetting, in which previous knowledge is forgotten when a model learns new tasks. Various methods have been proposed to solve this problem. Replay methods which replay data…

``The right to be forgotten'' ensured by laws for user data privacy becomes increasingly important. Machine unlearning aims to efficiently remove the effect of certain data points on the trained model parameters so that it can be…

Recently, pre-trained vision-language models have been increasingly used to tackle the challenging zero-shot segmentation task. Typical solutions follow the paradigm of first generating mask proposals and then adopting CLIP to classify…

With the increasing importance of data privacy and security, federated unlearning has emerged as a novel research field dedicated to ensuring that federated learning models no longer retain or leak relevant information once specific data…

Regulations introduced by General Data Protection Regulation (GDPR) in the EU or California Consumer Privacy Act (CCPA) in the US have included provisions on the \textit{right to be forgotten} that mandates industry applications to remove…

In some of object recognition problems, labeled data may not be available for all categories. Zero-shot learning utilizes auxiliary information (also called signatures) describing each category in order to find a classifier that can…

CLIP delivers strong zero-shot classification but remains highly vulnerable to adversarial attacks. Previous work of adversarial fine-tuning largely focuses on matching the predicted logits between clean and adversarial examples, which…

As generative models become increasingly powerful and pervasive, the ability to unlearn specific data, whether due to privacy concerns, legal requirements, or the correction of harmful content, has become increasingly important. Unlike in…

Lifelong learning algorithms enable models to incrementally acquire new knowledge without forgetting previously learned information. Contrarily, the field of machine unlearning focuses on explicitly forgetting certain previous knowledge…

Prompt learning has emerged as a valuable technique in enhancing vision-language models (VLMs) such as CLIP for downstream tasks in specific domains. Existing work mainly focuses on designing various learning forms of prompts, neglecting…

Recently, zero-shot multi-label classification has garnered considerable attention for its capacity to operate predictions on unseen labels without human annotations. Nevertheless, prevailing approaches often use seen classes as imperfect…

Fine-tuning vision-language models (VLMs) like CLIP to downstream tasks is often necessary to optimize their performance. However, a major obstacle is the limited availability of labeled data. We study the use of pseudolabels, i.e.,…

Semi-supervised learning is attracting blooming attention, due to its success in combining unlabeled data. To mitigate potentially incorrect pseudo labels, recent frameworks mostly set a fixed confidence threshold to discard uncertain…

Contrastive learning (CL), a self-supervised learning approach, can effectively learn visual representations from unlabeled data. Given the CL training data, generative models can be trained to generate synthetic data to supplement the real…

Catastrophic forgetting is a problem caused by neural networks' inability to learn data in sequence. After learning two tasks in sequence, performance on the first one drops significantly. This is a serious disadvantage that prevents many…

Pre-trained vision-language models such as contrastive language-image pre-training (CLIP) have demonstrated a remarkable generalizability, which has enabled a wide range of applications represented by zero-shot classification. However,…

Pre-training image representations from the raw text about images enables zero-shot vision transfer to downstream tasks. Through pre-training on millions of samples collected from the internet, multimodal foundation models, such as CLIP,…