Related papers: Diffusion-based Data Augmentation and Knowledge Di…

This paper tackles a novel yet challenging problem: how to transfer knowledge from the emerging Segment Anything Model (SAM) -- which reveals impressive zero-shot instance segmentation capacity -- to learn a compact panoramic semantic…

Variable selection for high-dimensional, highly correlated data has long been a challenging problem, often yielding unstable and unreliable models. We propose a resample-aggregate framework that exploits diffusion models' ability to…

Recent studies emphasize the crucial role of data augmentation in enhancing the performance of object detection models. However,existing methodologies often struggle to effectively harmonize dataset diversity with semantic coordination.To…

We introduce Diffusion Active Learning, a novel approach that combines generative diffusion modeling with data-driven sequential experimental design to adaptively acquire data for inverse problems. Although broadly applicable, we focus on…

Accurately predicting the upgrade of ductal carcinoma in situ (DCIS) to invasive ductal carcinoma (IDC) is crucial for surgical planning. However, traditional deep learning methods face challenges due to limited ultrasound data and poor…

Label smoothing is an effective regularization tool for deep neural networks (DNNs), which generates soft labels by applying a weighted average between the uniform distribution and the hard label. It is often used to reduce the overfitting…

Knowledge distillation is a strategy of training a student network with guide of the soft output from a teacher network. It has been a successful method of model compression and knowledge transfer. However, currently knowledge distillation…

Deep learning-based segmentation techniques have shown remarkable performance in brain segmentation, yet their success hinges on the availability of extensive labeled training data. Acquiring such vast datasets, however, poses a significant…

In this paper, we present a novel approach that combines deep metric learning and synthetic data generation using diffusion models for out-of-distribution (OOD) detection. One popular approach for OOD detection is outlier exposure, where…

Surgical scene understanding is a key prerequisite for contextaware decision support in the operating room. While deep learning-based approaches have already reached or even surpassed human performance in various fields, the task of…

Adapting a pretrained diffusion model to new objectives at inference time remains an open problem in generative modeling. Existing steering methods suffer from inaccurate value estimation, especially at high noise levels, which biases…

Many creative multimedia systems are built upon visual primitives such as strokes or textures, which are difficult to collect at scale and fundamentally different from natural image data. This data scarcity makes it challenging for modern…

Small-scale data is a critical problem in time-series forecasting tasks. Data augmentation is an effective strategy for this task, but it has a limitation in generating meaningful data. To address this limitation, we propose DAD4TS, a…

Weakly-supervised semantic segmentation (WSSS), which aims to train segmentation models solely using image-level labels, has achieved significant attention. Existing methods primarily focus on generating high-quality pseudo labels using…

Change detection, which aims to detect spatial changes from a pair of multi-temporal images due to natural or man-made causes, has been widely applied in remote sensing, disaster management, urban management, etc. Most existing change…

A dramatic influx of diffusion-generated images has marked recent years, posing unique challenges to current detection technologies. While the task of identifying these images falls under binary classification, a seemingly straightforward…

Semi-supervised medical image segmentation aims to leverage limited annotated data and rich unlabeled data to perform accurate segmentation. However, existing semi-supervised methods are highly dependent on the quality of self-generated…

Generative diffusion models have achieved remarkable success in producing high-quality images. However, these models typically operate in continuous intensity spaces, diffusing independently across pixels and color channels. As a result,…

Unsupervised representation learning, particularly sequential disentanglement, aims to separate static and dynamic factors of variation in data without relying on labels. This remains a challenging problem, as existing approaches based on…

The collaborative classification of dual-frequency PolSAR images is a meaningful but also challenging research. The effect of regional consistency on classification information learning and the rational use of dual-frequency data are two…