Related papers: Gated Adaptation for Continual Learning in Human A…

Multimodal continual instruction tuning enables multimodal large language models to sequentially adapt to new tasks while building upon previously acquired knowledge. However, this continual learning paradigm faces the significant challenge…

We show that gating mechanisms in recurrent neural networks (RNNs) induce lag-dependent and direction-dependent effective learning rates, even when training uses a fixed, global step size. This behavior arises from a coupling between…

Gait recognition is an important biometric for human identification at a distance, particularly under low-resolution or unconstrained environments. Current works typically focus on either 2D representations (e.g., silhouettes and skeletons)…

Traditional continual learning methods prioritize knowledge retention and focus primarily on mitigating catastrophic forgetting, implicitly assuming that the data distribution of previously learned tasks remains static. This overlooks the…

Deep learning models generally display catastrophic forgetting when learning new data continuously. Many incremental learning approaches address this problem by reusing data from previous tasks while learning new tasks. However, the direct…

Recent works have shown that large models pretrained on common visual learning tasks can provide useful representations for a wide range of specialized perception problems, as well as a variety of robotic manipulation tasks. While prior…

Catastrophic forgetting remains a central challenge in continual learning (CL) with pre-trained models. While existing approaches typically freeze the backbone and fine-tune a small number of parameters to mitigate forgetting, they still…

Deploying pretrained visual models in real-world environments often suffers from significant performance degradation due to the diversity of testing scenarios. Continuous adaptation of learning models on edge devices via unlabeled data…

Multimodal learning seeks to utilize data from multiple sources to improve the overall performance of downstream tasks. It is desirable for redundancies in the data to make multimodal systems robust to missing or corrupted observations in…

Continual learning requires models to adapt to new data while preserving previously acquired knowledge. At its core, this challenge can be viewed as principled one-step adaptation: incorporating new information with minimal interference to…

Transformers face quadratic complexity and memory issues with long sequences, prompting the adoption of linear attention mechanisms using fixed-size hidden states. However, linear models often suffer from limited recall performance, leading…

Data-driven modeling in mechanics is evolving rapidly based on recent machine learning advances, especially on artificial neural networks. As the field matures, new data and models created by different groups become available, opening…

Imaging in clinical routine is subject to changing scanner protocols, hardware, or policies in a typically heterogeneous set of acquisition hardware. Accuracy and reliability of deep learning models suffer from those changes as data and…

This study introduces a pioneering methodology for human action recognition by harnessing deep neural network techniques and adaptive fusion strategies across multiple modalities, including RGB, optical flows, audio, and depth information.…

Application of intelligent systems especially in smart homes and health-related topics has been drawing more attention in the last decades. Training Human Activity Recognition (HAR) models -- as a major module -- requires a fair amount of…

Effective network state classification is a primary task for ensuring network security and optimizing performance. Existing deep learning models have shown considerable progress in this area. Some methods excel at analyzing the complex…

In this paper, we introduce Attention Prompt Tuning (APT) - a computationally efficient variant of prompt tuning for video-based applications such as action recognition. Prompt tuning approaches involve injecting a set of learnable prompts…

Wearable HAR has improved steadily, but most progress still relies on closed-set classification, which limits real-world use. In practice, human activity is open-ended, unscripted, personalized, and often compositional, unfolding as…

The problem of a deep learning model losing performance on a previously learned task when fine-tuned to a new one is a phenomenon known as Catastrophic forgetting. There are two major ways to mitigate this problem: either preserving…

Multi-domain task-incremental learning requires a model to sequentially acquire knowledge across visually diverse domains without forgetting prior tasks, and without access to task identity at inference. Parameter-efficient methods built on…