Related papers: ALIFE: Adaptive Logit Regularizer and Feature Repl…

The performance of existing audio deepfake detection frameworks degrades when confronted with new deepfake attacks. Rehearsal-based continual learning (CL), which updates models using a limited set of old data samples, helps preserve prior…

Forgetting presents a significant challenge during incremental training, making it particularly demanding for contemporary AI systems to assimilate new knowledge in streaming data environments. To address this issue, most approaches in…

Catastrophic forgetting remains a major challenge for continual learning (CL) in automatic speech recognition (ASR), where models must adapt to new domains without losing performance on previously learned conditions. Several CL methods have…

In this work, we propose an Implicit Regularization Enhancement (IRE) framework to accelerate the discovery of flat solutions in deep learning, thereby improving generalization and convergence. Specifically, IRE decouples the dynamics of…

Incremental learning attempts to develop a classifier which learns continuously from a stream of data segregated into different classes. Deep learning approaches suffer from catastrophic forgetting when learning classes incrementally, while…

In Federated Learning (FL), the data in each client is typically assumed fixed or static. However, data often comes in an incremental manner in real-world applications, where the data domain may increase dynamically. In this work, we study…

We introduce a lifelong imitation learning framework that enables continual policy refinement across sequential tasks under realistic memory and data constraints. Our approach departs from conventional experience replay by operating…

Class-Incremental Learning (CIL) aims to train a reliable model with the streaming data, which emerges unknown classes sequentially. Different from traditional closed set learning, CIL has two main challenges: 1) Novel class detection. The…

Referring image segmentation (RIS) aims to locate the particular region corresponding to the language expression. Existing methods incorporate features from different modalities in a \emph{bottom-up} manner. This design may get some…

Domain incremental learning (DIL) poses a significant challenge in real-world scenarios, as models need to be sequentially trained on diverse domains over time, all the while avoiding catastrophic forgetting. Mitigating representation…

Ill-posed linear inverse problems (ILIP), such as restoration and reconstruction, are a core topic of signal/image processing. A standard approach to deal with ILIP uses a constrained optimization problem, where a regularization function is…

Deep learning architectures have shown remarkable results in scene understanding problems, however they exhibit a critical drop of performances when they are required to learn incrementally new tasks without forgetting old ones. This…

In autonomous driving, environment perception has significantly advanced with the utilization of deep learning techniques for diverse sensors such as cameras, depth sensors, or infrared sensors. The diversity in the sensor stack increases…

It is well-known that a deep neural network has a strong fitting capability and can easily achieve a low training error even with randomly assigned class labels. When the number of training samples is small, or the class labels are noisy,…

Learning feature correspondence is a foundational task in computer vision, holding immense importance for downstream applications such as visual odometry and 3D reconstruction. Despite recent progress in data-driven models, feature…

Continual learning (or class incremental learning) is a realistic learning scenario for computer vision systems, where deep neural networks are trained on episodic data, and the data from previous episodes are generally inaccessible to the…

Referring Image Segmentation (RIS) is an advanced vision-language task that involves identifying and segmenting objects within an image as described by free-form text descriptions. While previous studies focused on aligning visual and…

Numerous noise adaptation techniques have been proposed to fine-tune deep-learning models in speech enhancement (SE) for mismatched noise environments. Nevertheless, adaptation to a new environment may lead to catastrophic forgetting of the…

Few-shot class-incremental learning (FSCIL) aims to incrementally learn models from a small amount of novel data, which requires strong representation and adaptation ability of models learned under few-example supervision to avoid…

This paper addresses the unrealistic aspect of the commonly adopted Continuous Incremental Semantic Segmentation (CISS) scenario, termed overlapped. We point out that overlapped allows the same image to reappear in future tasks with…