Related papers: Forget Less, Count Better: A Domain-Incremental Se…
Foundations models are presented as generalists that often perform well over a myriad of tasks. Fine-tuning these models, even on limited data, provides an additional boost in task-specific performance but often at the cost of their wider…
In Continual Learning (CL), a model is required to learn a stream of tasks sequentially without significant performance degradation on previously learned tasks. Current approaches fail for a long sequence of tasks from diverse domains and…
Most standard learning approaches lead to fragile models which are prone to drift when sequentially trained on samples of a different nature - the well-known "catastrophic forgetting" issue. In particular, when a model consecutively learns…
Accurate indoor crowd counting (ICC) is a key enabler to many smart home/office applications. In this paper, we propose a Domain-Agnostic and Sample-Efficient wireless indoor crowd Counting (DASECount) framework that suffices to attain…
Catastrophic forgetting and capacity saturation are the central challenges of any parametric lifelong learning system. In this work, we study these challenges in the context of sequential supervised learning with an emphasis on recurrent…
Continual learning, involving sequential training on diverse tasks, often faces catastrophic forgetting. While knowledge distillation-based approaches exhibit notable success in preventing forgetting, we pinpoint a limitation in their…
Datasets for training crowd counting deep networks are typically heavy-tailed in count distribution and exhibit discontinuities across the count range. As a result, the de facto statistical measures (MSE, MAE) exhibit large variance and…
Knowledge distillation is an attractive approach for learning compact deep neural networks, which learns a lightweight student model by distilling knowledge from a complex teacher model. Attention-based knowledge distillation is a specific…
Due to its promising results, density map regression has been widely employed for image-based crowd counting. The approach, however, often suffers from severe performance degradation when tested on data from unseen scenarios, the so-called…
Federated Continual Learning (FCL) has recently emerged as a crucial research area, as data from distributed clients typically arrives as a stream, requiring sequential learning. This paper explores a more practical and challenging FCL…
Diffusion models have shown strong performance in generating high-quality tabular data, but they carry privacy risks by reproducing exact training samples. While prior work focuses on dataset-level augmentation to reduce memorization,…
Teacher-student knowledge distillation is a popular technique for compressing today's prevailing large language models into manageable sizes that fit low-latency downstream applications. Both the teacher and the choice of transfer set used…
While diffusion-based models have shown remarkable generative capabilities in static settings, their extension to continual learning (CL) scenarios remains fundamentally constrained by Generative Catastrophic Forgetting (GCF). We observe…
The recent surge of pervasive devices that generate dynamic data streams has underscored the necessity for learning systems to adapt continually to data distributional shifts. To tackle this challenge, the research community has put forth a…
Successful continual learning of new knowledge would enable intelligent systems to recognize more and more classes of objects. However, current intelligent systems often fail to correctly recognize previously learned classes of objects when…
Replay-based continual learning (CL) methods assume that models trained on a small subset can also effectively minimize the empirical risk of the complete dataset. These methods maintain a memory buffer that stores a sampled subset of data…
The task of Long-tailed Class Incremental Learning (LT-CIL) addresses the sequential learning of new classes from datasets with imbalanced class distributions. This scenario intensifies the fundamental problem of catastrophic forgetting,…
Modern machine learning algorithms need large datasets to be trained. Crowdsourcing has become a popular approach to label large datasets in a shorter time as well as at a lower cost comparing to that needed for a limited number of experts.…
Few-shot class-incremental learning (FSCIL) receives significant attention from the public to perform classification continuously with a few training samples, which suffers from the key catastrophic forgetting problem. Existing methods…
Crowd understanding has aroused the widespread interest in vision domain due to its important practical significance. Unfortunately, there is no effort to explore crowd understanding in multi-modal domain that bridges natural language and…