Related papers: SMMix: Self-Motivated Image Mixing for Vision Tran…

Masked Image Modeling (MIM) is a technique in self-supervised learning that focuses on acquiring detailed visual representations from unlabeled images by estimating the missing pixels in randomly masked sections. It has proven to be a…

Self-supervised Multi-modal Contrastive Learning (SMCL) remarkably advances modern Vision-Language Pre-training (VLP) models by aligning visual and linguistic modalities. Due to noises in web-harvested text-image pairs, however, scaling up…

In semantic segmentation, the creation of pixel-level labels for training data incurs significant costs. To address this problem, semi-supervised learning, which utilizes a small number of labeled images alongside unlabeled images to…

The purpose of federated learning is to enable multiple clients to jointly train a machine learning model without sharing data. However, the existing methods for training an image segmentation model have been based on an unrealistic…

Techniques combining multiple images as input/output have proven to be effective data augmentations for training convolutional neural networks. In this paper, we present StackMix: Each input is presented as a concatenation of two images,…

This paper presents a supervised mixing augmentation method termed SuperMix, which exploits the salient regions within input images to construct mixed training samples. SuperMix is designed to obtain mixed images rich in visual features and…

Semi-supervised semantic segmentation has witnessed remarkable advancements in recent years. However, existing algorithms are based on convolutional neural networks and directly applying them to Vision Transformers poses certain limitations…

Convolutional neural networks (CNN) are capable of learning robust representation with different regularization methods and activations as convolutional layers are spatially correlated. Based on this property, a large variety of regional…

While deep neural networks have achieved remarkable performance, data augmentation has emerged as a crucial strategy to mitigate overfitting and enhance network performance. These techniques hold particular significance in industrial…

We investigate whether the training protocol can induce spatial locality in the early layers of a Vision Transformer (ViT) trained from scratch, without large-scale pretraining. Keeping the architecture and optimization procedure fixed, we…

In this study, we propose a novel data augmentation method that introduces the concept of CutMix into the generation process of diffusion models, thereby exploiting both the ability of diffusion models to generate natural and…

Data augmentation improves the generalization power of deep learning models by synthesizing more training samples. Sample-mixing is a popular data augmentation approach that creates additional data by combining existing samples. Recent…

Recent advances in tuning-free personalized image generation based on diffusion models are impressive. However, to improve subject fidelity, existing methods either retrain the diffusion model or infuse it with dense visual embeddings, both…

Data mixing strategies (e.g., CutMix) have shown the ability to greatly improve the performance of convolutional neural networks (CNNs). They mix two images as inputs for training and assign them with a mixed label with the same ratio.…

We introduce MIM (Masked Image Modeling)-Refiner, a contrastive learning boost for pre-trained MIM models. MIM-Refiner is motivated by the insight that strong representations within MIM models generally reside in intermediate layers.…

Image quality assessment (IQA) has long been a fundamental challenge in image understanding. In recent years, deep learning-based IQA methods have shown promising performance. However, the lack of large amounts of labeled data in the IQA…

Semi-supervised learning (SSL) has demonstrated high performance in image classification tasks by effectively utilizing both labeled and unlabeled data. However, existing SSL methods often suffer from poor calibration, with models yielding…

Patch-level data augmentation techniques such as Cutout and CutMix have demonstrated significant efficacy in enhancing the performance of vision tasks. However, a comprehensive theoretical understanding of these methods remains elusive. In…

In this paper, we introduce a novel semi-supervised learning framework tailored for medical image segmentation. Central to our approach is the innovative Multi-scale Text-aware ViT-CNN Fusion scheme. This scheme adeptly combines the…

Mixup is a well-known data-dependent augmentation technique for DNNs, consisting of two sub-tasks: mixup generation and classification. However, the recent dominant online training method confines mixup to supervised learning (SL), and the…