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

Incorporating every annotator's perspective is crucial for unbiased data modeling. Annotator fatigue and changing opinions over time can distort dataset annotations. To combat this, we propose to learn a more accurate representation of…

Acquiring annotations for whole slide images (WSIs)-based deep learning tasks, such as creating tissue segmentation masks or detecting mitotic figures, is a laborious process due to the extensive image size and the significant manual work…

Given the similarity between facial expression categories, the presence of compound facial expressions, and the subjectivity of annotators, facial expression recognition (FER) datasets often suffer from ambiguity and noisy labels. Ambiguous…

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…

For the Facial Action Unit (AU) detection task, accurately capturing the subtle facial differences between distinct AUs is essential for reliable detection. Additionally, AU detection faces challenges from class imbalance and the presence…

Label noise is ubiquitous in real-world scenarios, posing a practical challenge to supervised models due to its effect in hurting the generalization performance of deep neural networks. Existing methods primarily employ the sample selection…

Recent years have seen increasing use of supervised learning methods for segmentation tasks. However, the predictive performance of these algorithms depends on the quality of labels. This problem is particularly pertinent in the medical…

The existing SSCL of RSI is built based on constructing positive and negative sample pairs. However, due to the richness of RSI ground objects and the complexity of the RSI contextual semantics, the same RSI patches have the coexistence and…

Federated learning (FL) has emerged as a prominent method for collaboratively training machine learning models using local data from edge devices, all while keeping data decentralized. However, accounting for the quality of data contributed…

Point cloud segmentation is a fundamental task in 3D. Despite recent progress on point cloud segmentation with the power of deep networks, current learning methods based on the clean label assumptions may fail with noisy labels. Yet, class…

Deep learning models usually require a large amount of labeled data to achieve satisfactory performance. In multimedia analysis, domain adaptation studies the problem of cross-domain knowledge transfer from a label rich source domain to a…

Image segmentation and classification are the two main fundamental steps in pattern recognition. To perform medical image segmentation or classification with deep learning models, it requires training on large image dataset with annotation.…

Deep neural networks are prone to overfitting noisy labels, resulting in poor generalization performance. To overcome this problem, we present a simple and effective method self-ensemble label correction (SELC) to progressively correct…

Scene-aware Adaptive Compressive Sensing (ACS) has attracted significant interest due to its promising capability for efficient and high-fidelity acquisition of scene images. ACS typically prescribes adaptive sampling allocation (ASA) based…

Deep neural networks (DNNs) fail to learn effectively under label noise and have been shown to memorize random labels which affect their generalization performance. We consider learning in isolation, using one-hot encoded labels as the sole…

Deep learning methods have achieved promising performance in many areas, but they are still struggling with noisy-labeled images during the training process. Considering that the annotation quality indispensably relies on great expertise,…

In this paper, we propose a novel framework for speech-image retrieval. We utilize speech-image contrastive (SIC) learning tasks to align speech and image representations at a coarse level and speech-image matching (SIM) learning tasks to…

Most existing text-to-image person retrieval methods usually assume that the training image-text pairs are perfectly aligned; however, the noisy correspondence(NC) issue (i.e., incorrect or unreliable alignment) exists due to poor image…

Label noise and ambiguities between similar classes are challenging problems in developing new models and annotating new data for semantic segmentation. In this paper, we propose Compensation Learning in Semantic Segmentation, a framework…

Manually annotating nuclei from the gigapixel Hematoxylin and Eosin (H&E)-stained Whole Slide Images (WSIs) is a laborious and costly task, meaning automated algorithms for cell nuclei instance segmentation and classification could…