Related papers: LLM-Guided Probabilistic Fusion for Label-Efficien…

Large language models (LLMs) have enabled the creation of multi-modal LLMs that exhibit strong comprehension of visual data such as images and videos. However, these models usually rely on extensive visual tokens from visual encoders,…

The recent research in semi-supervised learning (SSL) is mostly dominated by consistency regularization based methods which achieve strong performance. However, they heavily rely on domain-specific data augmentations, which are not easy to…

Competitive point cloud semantic segmentation results usually rely on a large amount of labeled data. However, data annotation is a time-consuming and labor-intensive task, particularly for three-dimensional point cloud data. Thus,…

Current 3D semi-supervised segmentation methods face significant challenges such as limited consideration of contextual information and the inability to generate reliable pseudo-labels for effective unsupervised data use. To address these…

Semi-supervised semantic segmentation relieves the reliance on large-scale labeled data by leveraging unlabeled data. Recent semi-supervised semantic segmentation approaches mainly resort to pseudo-labeling methods to exploit unlabeled…

We present a comprehensive experimental study on pretrained feature extractors for visual out-of-distribution (OOD) detection, focusing on adapting contrastive language-image pretrained (CLIP) models. Without fine-tuning on the training…

Pre-training techniques have been verified successfully in a variety of NLP tasks in recent years. Despite the widespread use of pre-training models for NLP applications, they almost exclusively focus on text-level manipulation, while…

Semi-supervised learning frameworks usually adopt mutual learning approaches with multiple submodels to learn from different perspectives. To avoid transferring erroneous pseudo labels between these submodels, a high threshold is usually…

Link Prediction (LP) is a critical task in graph machine learning. While Graph Neural Networks (GNNs) have significantly advanced LP performance recently, existing methods face key challenges including limited supervision from sparse…

The success of semi-supervised learning crucially relies on the scalability to a huge amount of unlabelled data that are needed to capture the underlying manifold structure for better classification. Since computing the pairwise similarity…

Vision-language models (VLMs) can learn high-quality representations from a large-scale training dataset of image-text pairs. Prompt learning is a popular approach to fine-tuning VLM to adapt them to downstream tasks. Despite the satisfying…

Semi-supervised learning techniques are gaining popularity due to their capability of building models that are effective, even when scarce amounts of labeled data are available. In this paper, we present a framework and specific tasks for…

Federated learning aims to tackle the ``isolated data island" problem, where it trains a collective model from physically isolated clients while safeguarding the privacy of users' data. However, supervised federated learning necessitates…

Training deep models with limited annotations poses a significant challenge when applied to diverse practical domains. Employing semi-supervised learning alongside the self-supervised model offers the potential to enhance label efficiency.…

Semi-supervised learning (SSL) has achieved great success in leveraging a large amount of unlabeled data to learn a promising classifier. A popular approach is pseudo-labeling that generates pseudo labels only for those unlabeled data with…

Automatic speech recognition (ASR) models rely on high-quality transcribed data for effective training. Generating pseudo-labels for large unlabeled audio datasets often relies on complex pipelines that combine multiple ASR outputs through…

Identity-document fraud detection is not a stationary binary classification problem. Adaptive attackers modify templates and fabrication pipelines, making historical fraud labels stale, and successful forgeries recur at scale as coherent…

Self-supervised pre-training techniques have achieved remarkable progress in Document AI. Most multimodal pre-trained models use a masked language modeling objective to learn bidirectional representations on the text modality, but they…

Learning from large amounts of unsupervised data and a small amount of supervision is an important open problem in computer vision. We propose a new semi-supervised learning method, Semantic Positives via Pseudo-Labels (SemPPL), that…

Neural network potentials (NNPs) are crucial for accelerating computational materials science by surrogating density functional theory (DFT) calculations. Improving their accuracy is possible through pre-training and fine-tuning, where an…