相关论文: Dataset Ownership Verification in Contrastive Pre-…

Machine unlearning has great significance in guaranteeing model security and protecting user privacy. Additionally, many legal provisions clearly stipulate that users have the right to demand model providers to delete their own data from…

Self-training methods have proven to be effective in exploiting abundant unlabeled data in semi-supervised learning, particularly when labeled data is scarce. While many of these approaches rely on a cross-entropy loss function (CE), recent…

Understanding self-supervised learning is important but challenging. Previous theoretical works study the role of pretraining losses, and view neural networks as general black boxes. However, the recent work of Saunshi et al. argues that…

The unsupervised pretraining of object detectors has recently become a key component of object detector training, as it leads to improved performance and faster convergence during the supervised fine-tuning stage. Existing unsupervised…

In software engineering, deep learning models are increasingly deployed for critical tasks such as bug detection and code review. However, overfitting remains a challenge that affects the quality, reliability, and trustworthiness of…

Practitioners commonly download pretrained machine learning models from open repositories and finetune them to fit specific applications. We show that this practice introduces a new risk of privacy backdoors. By tampering with a pretrained…

Unsupervised contrastive learning has gained increasing attention in the latest research and has proven to be a powerful method for learning representations from unlabeled data. However, little theoretical analysis was known for this…

Annotating medical data for training AI models is often costly and limited due to the shortage of specialists with relevant clinical expertise. This challenge is further compounded by privacy and ethical concerns associated with sensitive…

Convolutional networks have marked their place over the last few years as the best performing model for various visual tasks. They are, however, most suited for supervised learning from large amounts of labeled data. Previous attempts have…

Certified defense using randomized smoothing is a popular technique to provide robustness guarantees for deep neural networks against l2 adversarial attacks. Existing works use this technique to provably secure a pretrained non-robust model…

Object occlusion boundary detection is a fundamental and crucial research problem in computer vision. This is challenging to solve as encountering the extreme boundary/non-boundary class imbalance during training an object occlusion…

To safely deploy deep learning-based computer vision models for computer-aided detection and diagnosis, we must ensure that they are robust and reliable. Towards that goal, algorithmic auditing has received substantial attention. To guide…

A common practice in transfer learning is to initialize the downstream model weights by pre-training on a data-abundant upstream task. In object detection specifically, the feature backbone is typically initialized with Imagenet classifier…

With the rise of powerful foundation models, a pre-training-fine-tuning paradigm becomes increasingly popular these days: A foundation model is pre-trained using a huge amount of data from various sources, and then the downstream users only…

The black box nature of deep learning models complicate their usage in critical applications such as remote sensing. Conformal prediction is a method to ensure trust in such scenarios. Subject to data exchangeability, conformal prediction…

We address the problem of machine unlearning, where the goal is to remove the influence of specific training data from a model upon request, motivated by privacy concerns and regulatory requirements such as the "right to be forgotten."…

Deep learning (DL) based supervised change detection (CD) models require large labeled training data. Due to the difficulty of collecting labeled multi-temporal data, unsupervised methods are preferred in the CD literature. However,…

In order to train robust deep learning models, large amounts of labelled data is required. However, in the absence of such large repositories of labelled data, unlabeled data can be exploited for the same. Semi-Supervised learning aims to…

Facial Kinship Verification is the task of determining the degree of familial relationship between two facial images. It has recently gained a lot of interest in various applications spanning forensic science, social media, and demographic…

Automated scraping stands out as a common method for collecting data in deep learning models without the authorization of data owners. Recent studies have begun to tackle the privacy concerns associated with this data collection method.…