相关论文: CASC-AI: Consensus-aware Self-corrective Learning …

Cross-modal noise-robust learning is a challenging task since noisy correspondence is hard to recognize and rectify. Due to the cumulative and unavoidable negative impact of unresolved noise, existing methods cannot maintain a stable…

In some medical imaging tasks and other settings where only small parts of the image are informative for the classification task, traditional CNNs can sometimes struggle to generalise. Manually annotated Regions of Interest (ROI) are…

WiFi sensing is an emerging technology that utilizes wireless signals for various sensing applications. However, the reliance on supervised learning, the scarcity of labelled data, and the incomprehensible channel state information (CSI)…

Despite recent success, most contrastive self-supervised learning methods are domain-specific, relying heavily on data augmentation techniques that require knowledge about a particular domain, such as image cropping and rotation. To…

Biomedical image segmentation plays a significant role in computer-aided diagnosis. However, existing CNN based methods rely heavily on massive manual annotations, which are very expensive and require huge human resources. In this work, we…

In real-world datasets, noisy labels are pervasive. The challenge of learning with noisy labels (LNL) is to train a classifier that discerns the actual classes from given instances. For this, the model must identify features indicative of…

Pre-trained vision-language models learn massive data to model unified representations of images and natural languages, which can be widely applied to downstream machine learning tasks. In addition to zero-shot inference, in order to better…

In the context of noisy partial label learning (NPLL), each training sample is associated with a set of candidate labels annotated by multiple noisy annotators. With the emergence of high-performance pre-trained vision-language models…

Semantic segmentation plays a crucial role in enabling comprehensive scene understanding for robotic systems. However, generating annotations is challenging, requiring labels for every pixel in an image. In scenarios like autonomous…

Deep neural networks (DNNs) have achieved great success in a wide variety of medical image analysis tasks. However, these achievements indispensably rely on the accurately-annotated datasets. If with the noisy-labeled images, the training…

Model merging aims to integrate the strengths of multiple fine-tuned models into a unified model while preserving task-specific capabilities. Existing methods, represented by task arithmetic, are typically classified into global- and…

Recent studies on learning with noisy labels have shown remarkable performance by exploiting a small clean dataset. In particular, model agnostic meta-learning-based label correction methods further improve performance by correcting noisy…

The challenge of learning with noisy labels is significant in machine learning, as it can severely degrade the performance of prediction models if not addressed properly. This paper introduces a novel framework that conceptualizes noisy…

Large-scale datasets are important for the development of deep learning models. Such datasets usually require a heavy workload of annotations, which are extremely time-consuming and expensive. To accelerate the annotation procedure,…

In machine learning the best performance on a certain task is achieved by fully supervised methods when perfect ground truth labels are available. However, labels are often noisy, especially in remote sensing where manually curated public…

Whole Slide Images (WSIs) are critical for various clinical applications, including histopathological analysis. However, current deep learning approaches in this field predominantly focus on individual tumor types, limiting model…

Audio-Visual Semantic Segmentation (AVSS) aligns audio and video at the pixel level but requires costly per-frame annotations. We introduce Weakly Supervised Audio-Visual Semantic Segmentation (WSAVSS), which uses only video-level labels to…

Noisy labels are ubiquitous in real-world datasets, especially in the large-scale ones derived from crowdsourcing and web searching. It is challenging to train deep neural networks with noisy datasets since the networks are prone to…

Conformal inference provides a rigorous statistical framework for uncertainty quantification in machine learning, enabling well-calibrated prediction sets with precise coverage guarantees for any classification model. However, its reliance…

Real-world machine learning applications often struggle with two major challenges: distribution shift and label noise. Models tend to overfit by focusing on redundant and uninformative features in the training data, which makes it hard for…