相关论文: Localizing Memorization in SSL Vision Encoders

Recent advances in self-supervised learning (SSL) have largely closed the gap with supervised ImageNet pretraining. Despite their success these methods have been primarily applied to unlabeled ImageNet images, and show marginal gains when…

Decentralized learning has been advocated and widely deployed to make efficient use of distributed datasets, with an extensive focus on supervised learning (SL) problems. Unfortunately, the majority of real-world data are unlabeled and can…

We present the first comprehensive study of Memorization in Multilingual Large Language Models (MLLMs), analyzing 95 languages using models across diverse model scales, architectures, and memorization definitions. As MLLMs are increasingly…

Learning to solve sequential tasks with recurrent models requires the ability to memorize long sequences and to extract task-relevant features from them. In this paper, we study the memorization subtask from the point of view of the design…

Visual Geo-localization (VG) is a critical research area for identifying geo-locations from visual inputs, particularly in autonomous navigation for robotics and vehicles. Current VG methods often learn feature extractors from geo-labeled…

Masked autoencoders are scalable vision learners, as the title of MAE \cite{he2022masked}, which suggests that self-supervised learning (SSL) in vision might undertake a similar trajectory as in NLP. Specifically, generative pretext tasks…

Semi-Supervised Learning (SSL) has been proved to be an effective way to leverage both labeled and unlabeled data at the same time. Recent semi-supervised approaches focus on deep neural networks and have achieved promising results on…

Recently, discrete tokens derived from self-supervised learning (SSL) models via k-means clustering have been actively studied as pseudo-text in speech language models and as efficient intermediate representations for various tasks.…

Dense Self-Supervised Learning (SSL) methods address the limitations of using image-level feature representations when handling images with multiple objects. Although the dense features extracted by employing segmentation maps and bounding…

Self-supervised learning (SSL) has emerged as a desirable paradigm in computer vision due to the inability of supervised models to learn representations that can generalize in domains with limited labels. The recent popularity of SSL has…

Recent data- and learning-based sound source localization (SSL) methods have shown strong performance in challenging acoustic scenarios. However, little work has been done on adapting such methods to track consistently multiple sources…

Large Language Models have received significant attention due to their abilities to solve a wide range of complex tasks. However these models memorize a significant proportion of their training data, posing a serious threat when disclosed…

Semi-Supervised Learning (SSL) is a framework that utilizes both labeled and unlabeled data to enhance model performance. Conventional SSL methods operate under the assumption that labeled and unlabeled data share the same label space.…

Self-supervised learning (SSL) has grown in interest within the speech processing community, since it produces representations that are useful for many downstream tasks. SSL uses global and contextual methods to produce robust…

Recent advances in image-level self-supervised learning (SSL) have made significant progress, yet learning dense representations for patches remains challenging. Mainstream methods encounter an over-dispersion phenomenon that patches from…

Sound source localization (SSL) is essential for many speech-processing applications. Deep learning models have achieved high performance, but often fail when the training and inference environments differ. Adapting SSL models to dynamic…

Self-supervised learning (SSL) aims to learn intrinsic features without labels. Despite the diverse architectures of SSL methods, the projection head always plays an important role in improving the performance of the downstream task. In…

Code explanation plays a crucial role in the software engineering domain, aiding developers in grasping code functionality efficiently. Recent work shows that the performance of LLMs for code explanation improves in a few-shot setting,…

The performance of machine learning models can significantly degrade under distribution shifts of the data. We propose a new method for classification which can improve robustness to distribution shifts, by combining expert knowledge about…

Self-supervised learning (SSL) can be used to solve complex visual tasks without human labels. Self-supervised representations encode useful semantic information about images, and as a result, they have already been used for tasks such as…