相关论文: Swapping Semantic Contents for Mixing Images

Semi-supervised learning (SSL) for medical image segmentation is a challenging yet highly practical task, which reduces reliance on large-scale labeled dataset by leveraging unlabeled samples. Among SSL techniques, the weak-to-strong…

In the 21st-century information age, with the development of big data technology, effectively extracting valuable information from massive data has become a key issue. Traditional data mining methods are inadequate when faced with…

Despite substantial progress in the field of deep learning, overfitting persists as a critical challenge, and data augmentation has emerged as a particularly promising approach due to its capacity to enhance model generalization in various…

Pseudo-labeling is a crucial technique in semi-supervised learning (SSL), where artificial labels are generated for unlabeled data by a trained model, allowing for the simultaneous training of labeled and unlabeled data in a supervised…

Training deep networks for semantic segmentation requires large amounts of labeled training data, which presents a major challenge in practice, as labeling segmentation masks is a highly labor-intensive process. To address this issue, we…

Semi-supervised learning has emerged as a powerful paradigm for leveraging large amounts of unlabeled data to improve the performance of machine learning models when labeled data are scarce. Among existing approaches, methods derived from…

Semi-supervised learning (SSL) has attracted enormous attention due to its vast potential of mitigating the dependence on large labeled datasets. The latest methods (e.g., FixMatch) use a combination of consistency regularization and…

The success of deep learning methods in medical image segmentation tasks usually requires a large amount of labeled data. However, obtaining reliable annotations is expensive and time-consuming. Semi-supervised learning has attracted much…

Consistency regularization and pseudo-labeling have significantly advanced semi-supervised learning (SSL). Prior works have effectively employed Mixup for consistency regularization in SSL. However, our findings indicate that applying Mixup…

In semantic segmentation, training data down-sampling is commonly performed due to limited resources, the need to adapt image size to the model input, or improve data augmentation. This down-sampling typically employs different strategies…

Self-supervised learning models have been shown to learn rich visual representations without requiring human annotations. However, in many real-world scenarios, labels are partially available, motivating a recent line of work on…

Data augmentation has been pivotal in successfully training deep learning models on classification tasks over the past decade. An important subclass of data augmentation techniques - which includes both label smoothing and Mixup - involves…

Densely annotating LiDAR point clouds is costly, which restrains the scalability of fully-supervised learning methods. In this work, we study the underexplored semi-supervised learning (SSL) in LiDAR segmentation. Our core idea is to…

Semi-supervised semantic segmentation requires the model to effectively propagate the label information from limited annotated images to unlabeled ones. A challenge for such a per-pixel prediction task is the large intra-class variation,…

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…

Existing weakly or semi-supervised semantic segmentation methods utilize image or box-level supervision to generate pseudo-labels for weakly labeled images. However, due to the lack of strong supervision, the generated pseudo-labels are…

Supervised learning techniques are at the center of many tasks in remote sensing. Unfortunately, these methods, especially recent deep learning methods, often require large amounts of labeled data for training. Even though satellites…

In this work, we propose data augmentation methods for embeddings from pre-trained deep learning models that take a weighted combination of a pair of input embeddings, as inspired by Mixup, and combine such augmentation with extra label…

Existing research for image text retrieval mainly relies on sentence-level supervision to distinguish matched and mismatched sentences for a query image. However, semantic mismatch between an image and sentences usually happens in finer…

The diversity of deep learning applications, datasets, and neural network architectures necessitates a careful selection of the architecture and data that match best to a target application. As an attempt to mitigate this dilemma, this…