相关论文: Refining Context-Entangled Content Segmentation vi…

Self-supervised semantic segmentation methods often suffer from structural errors, including merging distinct objects or fragmenting coherent regions, because they rely primarily on low-level appearance cues such as color and texture. These…

Semantic segmentation is an important task for numerous applications but it is still quite challenging to achieve advanced performance with limited computational costs. In this paper, we present CGRSeg, an efficient yet competitive…

The label scarcity problem is the main challenge that hinders the wide application of deep learning systems in automatic cardiovascular diseases (CVDs) detection using electrocardiography (ECG). Tuning pre-trained models alleviates this…

We propose Curriculum by Masking (CBM), a novel state-of-the-art curriculum learning strategy that effectively creates an easy-to-hard training schedule via patch (token) masking, offering significant accuracy improvements over the…

Aiming at improving performance of visual classification in a cost-effective manner, this paper proposes an incremental semi-supervised learning paradigm called Deep Co-Space (DCS). Unlike many conventional semi-supervised learning methods…

Curriculum Learning (CL) is the idea that learning on a training set sequenced or ordered in a manner where samples range from easy to difficult, results in an increment in performance over otherwise random ordering. The idea parallels…

This paper examines the Code-Switching (CS) phenomenon where two languages intertwine within a single utterance. There exists a noticeable need for research on the CS between English and Korean. We highlight that the current Equivalence…

We present ReCo, a contrastive learning framework designed at a regional level to assist learning in semantic segmentation. ReCo performs semi-supervised or supervised pixel-level contrastive learning on a sparse set of hard negative…

Deep neural networks suffer from the major limitation of catastrophic forgetting old tasks when learning new ones. In this paper we focus on class incremental continual learning in semantic segmentation, where new categories are made…

Contrastive representation learning has proven to be an effective self-supervised learning method for images and videos. Most successful approaches are based on Noise Contrastive Estimation (NCE) and use different views of an instance as…

Corner cases are rare or extreme scenarios that drive real-world failures, but they are difficult to curate at scale: web data are noisy, labels are brittle, and edge deployments preclude large retraining. We present ReCCur (Recursive…

We introduce a two-stage multitask learning framework for analyzing Electroencephalography (EEG) signals that integrates denoising, dynamical modeling, and representation learning. In the first stage, a denoising autoencoder is trained to…

Object detection has advanced significantly in the closed-set setting, but real-world deployment remains limited by two challenges: poor generalization to unseen categories and insufficient robustness under adverse conditions. Prior…

Recent advances in unsupervised deep graph clustering have been significantly promoted by contrastive learning. Despite the strides, most graph contrastive learning models face challenges: 1) graph augmentation is used to improve learning…

Medical image segmentation is an important step in medical image analysis. With the rapid development of convolutional neural network in image processing, deep learning has been used for medical image segmentation, such as optic disc…

Instance segmentation in electron microscopy (EM) volumes is tough due to complex shapes and sparse annotations. Self-supervised learning helps but still struggles with intricate visual patterns in EM. To address this, we propose a…

Modern semantic segmentation methods devote much effect to adjusting image feature representations to improve the segmentation performance in various ways, such as architecture design, attention mechnism, etc. However, almost all those…

Semi-supervised learning is of great significance in medical image segmentation by exploiting unlabeled data. Among its strategies, the co-training framework is prominent. However, previous co-training studies predominantly concentrate on…

WeatherSeg, an advanced semi-supervised segmentation framework, addresses autonomous driving's environmental perception challenges in adverse weather while reducing annotation costs. This framework integrates a Dual Teacher-Student…

Real-world digital environments are highly diverse and dynamic. These characteristics cause agents to frequently encounter unseen environments and distribution shifts, making continual learning in such environments essential for…