Related papers: S2IL: Structurally Stable Incremental Learning

In the realm of digital pathology, multi-magnification Multiple Instance Learning (multi-mag MIL) has proven effective in leveraging the hierarchical structure of Whole Slide Images (WSIs) to reduce information loss and redundant data.…

Continual learning enables large language models to adapt to evolving tasks without retraining from scratch, yet catastrophic forgetting remains a central obstacle. Among continual learning methods, regularization-based approaches are…

Continual learning (CL) aims to learn new tasks without erasing previous knowledge. However, current CL methods primarily emphasize improving accuracy while often neglecting training efficiency, which consequently restricts their practical…

We demonstrate that in knowledge distillation for diffusion models, the teacher network's highly complex denoising process - stemming from its substantially larger capacity - poses a significant challenge for the student model to faithfully…

One-shot Federated learning (FL) is a powerful technology facilitating collaborative training of machine learning models in a single round of communication. While its superiority lies in communication efficiency and privacy preservation…

Diffusion-based text-to-image generation models trained on extensive text-image pairs have demonstrated the ability to produce photorealistic images aligned with textual descriptions. However, a significant limitation of these models is…

Class incremental learning (CIL) aims to incrementally update a trained model with the new classes of samples (plasticity) while retaining previously learned ability (stability). To address the most challenging issue in this goal, i.e.,…

Data drift is a thorny challenge when deploying person re-identification (ReID) models into real-world devices, where the data distribution is significantly different from that of the training environment and keeps changing. To tackle this…

Vision Foundation Models (VFMs) have achieved remarkable success when applied to various downstream 2D tasks. Despite their effectiveness, they often exhibit a critical lack of 3D awareness. To this end, we introduce Splat and Distill, a…

Recently, images that distort or fabricate facts using generative models have become a social concern. To cope with continuous evolution of generative artificial intelligence (AI) models, model attribution (MA) is necessary beyond just…

Few-shot class incremental learning (FSCIL) is a more realistic and challenging paradigm in continual learning to incrementally learn unseen classes and overcome catastrophic forgetting on base classes with only a few training examples.…

Knowledge distillation (KD) has been widely used to transfer knowledge from large, accurate models (teachers) to smaller, efficient ones (students). Recent methods have explored enforcing consistency by incorporating causal interpretations…

Class-incremental learning (CIL) enables models to learn new classes progressively while preserving knowledge of previously learned ones. Recent advances in this field have shifted towards parameter-efficient fine-tuning techniques, with…

Few-shot class-incremental learning (FSCIL) aims to incrementally recognize new classes using a few samples while maintaining the performance on previously learned classes. One of the effective methods to solve this challenge is to…

Deep Metric Learning (DML) provides a crucial tool for visual similarity and zero-shot applications by learning generalizing embedding spaces, although recent work in DML has shown strong performance saturation across training objectives.…

Federated continual learning (FCL) aims to learn from sequential data stream in the decentralized federated learning setting, while simultaneously mitigating the catastrophic forgetting issue in classical continual learning. Existing FCL…

Adversarial Imitation Learning (AIL) is a dominant framework in imitation learning that infers rewards from expert demonstrations to guide policy optimization. Although providing more expert demonstrations typically leads to improved…

As Web technology continues to develop, it has become increasingly common to use data stored on different clients. At the same time, federated learning has received widespread attention due to its ability to protect data privacy when let…

Traditional federated learning (FL) algorithms operate under the assumption that the data distributions at training (source domains) and testing (target domain) are the same. The fact that domain shifts often occur in practice necessitates…

Class-incremental learning (CIL) in medical image-guided diagnosis requires retaining prior diagnostic knowledge while adapting to newly emerging disease categories, which is critical for scalable clinical deployment. This problem is…