Related papers: A Two-Stream Mutual Attention Network for Semi-sup…

Weakly supervised semantic segmentation (WSSS) based on image-level labels is challenging since it is hard to obtain complete semantic regions. To address this issue, we propose a self-training method that utilizes fused multi-scale…

Retinal vessel segmentation from retinal images is an essential task for developing the computer-aided diagnosis system for retinal diseases. Efforts have been made on high-performance deep learning-based approaches to segment the retinal…

Semi-supervised learning has attracted much attention due to its less dependence on acquiring abundant annotations from experts compared to fully supervised methods, which is especially important for medical image segmentation which…

Audio-Visual Source Localization (AVSL) aims to locate sounding objects within video frames given the paired audio clips. Existing methods predominantly rely on self-supervised contrastive learning of audio-visual correspondence. Without…

In machine learning, one must acquire labels to help supervise a model that will be able to generalize to unseen data. However, the labeling process can be tedious, long, costly, and error-prone. It is often the case that most of our data…

Semi-supervised learning, which leverages both annotated and unannotated data, is an efficient approach for medical image segmentation, where obtaining annotations for the whole dataset is time-consuming and costly. Traditional…

The capability of the traditional semi-supervised learning (SSL) methods is far from real-world application due to severely biased pseudo-labels caused by (1) class imbalance and (2) class distribution mismatch between labeled and unlabeled…

Supervised learning algorithms based on Convolutional Neural Networks have become the benchmark for medical image segmentation tasks, but their effectiveness heavily relies on a large amount of labeled data. However, annotating medical…

The task of continual learning requires careful design of algorithms that can tackle catastrophic forgetting. However, the noisy label, which is inevitable in a real-world scenario, seems to exacerbate the situation. While very few studies…

Sentence-level classification and sequential labeling are two fundamental tasks in language understanding. While these two tasks are usually modeled separately, in reality, they are often correlated, for example in intent classification and…

Weakly Supervised Semantic Segmentation (WSSS) is a challenging problem that has been extensively studied in recent years. Traditional approaches often rely on external modules like Class Activation Maps to highlight regions of interest and…

Learning with noisy labels aims to ensure model generalization given a label-corrupted training set. The sample selection strategy achieves promising performance by selecting a label-reliable subset for model training. In this paper, we…

Manually segmenting the hepatic vessels from Computer Tomography (CT) is far more expertise-demanding and laborious than other structures due to the low-contrast and complex morphology of vessels, resulting in the extreme lack of…

Deep neural networks have achieved remarkable success in a wide variety of natural image and medical image computing tasks. However, these achievements indispensably rely on accurately annotated training data. If encountering some…

Previous graph neural networks (GNNs) usually assume that the graph data is with clean labels for representation learning, but it is not true in real applications. In this paper, we propose a new multi-teacher distillation method based on…

In weakly-supervised semantic segmentation (WSSS) using only image-level class labels, a problem with CNN-based Class Activation Maps (CAM) is that they tend to activate the most discriminative local regions of objects. On the other hand,…

Whole-slide images (WSIs) are critical for cancer diagnosis due to their ultra-high resolution and rich semantic content. However, their massive size and the limited availability of fine-grained annotations pose substantial challenges for…

Noisy labels severely hinder the accuracy and generalization of machine learning models, especially when ambiguous instance features make reliable annotation difficult. Existing approaches, including transition-matrix-based label…

Multi-label classification poses challenges due to imbalanced and noisy labels in training data. We propose a unified data augmentation method, named BalanceMix, to address these challenges. Our approach includes two samplers for imbalanced…

Multi-label classification is a widely encountered problem in daily life, where an instance can be associated with multiple classes. In theory, this is a supervised learning method that requires a large amount of labeling. However,…