Related papers: ProtoFlow: Mitigating Forgetting in Class-Incremen…

In class-incremental learning, the objective is to learn a number of classes sequentially without having access to the whole training data. However, due to a problem known as catastrophic forgetting, neural networks suffer substantial…

We introduce ProtoPool, an interpretable image classification model with a pool of prototypes shared by the classes. The training is more straightforward than in the existing methods because it does not require the pruning stage. It is…

This paper studies optical flow estimation, a critical task in motion analysis with applications in autonomous navigation, action recognition, and film production. Traditional optical flow methods require consecutive frames, which are often…

The objective of this work is to improve the accuracy of building demand forecasting. This is a more challenging task than grid level forecasting. For the said purpose, we develop a new technique called recurrent transform learning (RTL).…

We introduce ImitationFlow, a novel Deep generative model that allows learning complex globally stable, stochastic, nonlinear dynamics. Our approach extends the Normalizing Flows framework to learn stable Stochastic Differential Equations.…

Modern deep models are trained on large real-world datasets, where data quality varies and redundancy is common. Data-centric approaches such as dataset pruning have shown promise in improving training efficiency and model performance.…

Evolving data streams induce joint nonstationarity in continual semantic segmentation, where semantic classes, input distributions, and supervision availability change simultaneously over time. This setting reflects practical structured…

Dynamic Time Warping (DTW) is widely used for temporal data processing. However, existing methods can neither learn the discriminative prototypes of different classes nor exploit such prototypes for further analysis. We propose…

Remote sensing change detection is often challenged by spatial misalignment between bi-temporal images, especially when acquisitions are separated by long seasonal or multi-year gaps. While modern convolutional and transformer-based models…

Instance segmentation is a challenging task aiming at classifying and segmenting all object instances of specific classes. While two-stage box-based methods achieve top performances in the image domain, they cannot easily extend their…

Fast flow models accelerate the iterative sampling process by learning to directly predict ODE path integrals, enabling one-step or few-step generation. However, we argue that current fast-flow training paradigms suffer from two fundamental…

Motion forecasting aims to predict the future trajectories of dynamic agents in the scene, enabling autonomous vehicles to effectively reason about scene evolution. Existing approaches operate under the closed-world regime and assume fixed…

Deep learning methods are powerful tools in classifying multivariate time series data. Despite their high performance, these methods are hard to interpret, which diminishes their applications in high-risk domains such as healthcare. In this…

Diffusion models can learn rich representations during data generation, showing potential for Self-Supervised Learning (SSL), but they face a trade-off between generative quality and discriminative performance. Their iterative sampling also…

We introduce ProtoSeg, a novel model for interpretable semantic image segmentation, which constructs its predictions using similar patches from the training set. To achieve accuracy comparable to baseline methods, we adapt the mechanism of…

Keyword Spotting (KWS) systems with small footprint models deployed on edge devices face significant accuracy and robustness challenges due to domain shifts caused by varying noise and recording conditions. To address this, we propose a…

Task-free continual learning (CL) aims to learn a non-stationary data stream without explicit task definitions and not forget previous knowledge. The widely adopted memory replay approach could gradually become less effective for long data…

Instruction tuning has been central to the success of recent vision-language models (VLMs), but it remains expensive-requiring large-scale datasets, high-quality annotations, and large compute budgets. We propose PRioritized cOncept…

Longitudinal brain analysis is essential for understanding healthy aging and identifying pathological deviations. Longitudinal registration of sequential brain MRI underpins such analyses. However, existing methods are limited by reliance…

Spatio-temporal sequence forecasting is one of the fundamental tasks in spatio-temporal data mining. It facilitates many real world applications such as precipitation nowcasting, citywide crowd flow prediction and air pollution forecasting.…