Related papers: From Isolation to Integration: Building an Adaptiv…

A new random forest based model for solving the Multiple Instance Learning (MIL) problem under small tabular data, called Soft Tree Ensemble MIL (STE-MIL), is proposed. A new type of soft decision trees is considered, which is similar to…

With the memory-resource-limited constraints, class-incremental learning (CIL) usually suffers from the "catastrophic forgetting" problem when updating the joint classification model on the arrival of newly added classes. To cope with the…

This paper studies class incremental learning (CIL) of continual learning (CL). Many approaches have been proposed to deal with catastrophic forgetting (CF) in CIL. Most methods incrementally construct a single classifier for all classes of…

Imitation learning has been a trend recently, yet training a generalist agent across multiple tasks still requires large-scale expert demonstrations, which are costly and labor-intensive to collect. To address the challenge of limited…

The ability to learn new concepts while preserve the learned knowledge is desirable for learning systems in Class-Incremental Learning (CIL). Recently, feature expansion of the model become a prevalent solution for CIL, where the old…

Class Incremental Learning (CIL) is challenging due to catastrophic forgetting. On top of that, Exemplar-free Class Incremental Learning is even more challenging due to forbidden access to previous task data. Recent exemplar-free CIL…

Autonomous driving involves complex tasks such as data fusion, object and lane detection, behavior prediction, and path planning. As opposed to the modular approach which dedicates individual subsystems to tackle each of those tasks, the…

Class-Incremental Learning (CIL) aims to enable AI models to continuously learn from sequentially arriving data of different classes over time while retaining previously acquired knowledge. Recently, Parameter-Efficient Fine-Tuning (PEFT)…

Primary and secondary education is a crucial stage to build a strong foundation before diving deep into specialised subjects in colleges and universities. To excel in the current education system, students are required to have a deep…

Real-world robot manipulation in dynamic unstructured environments requires lifelong adaptability to evolving objects, scenes and tasks. Traditional imitation learning relies on static training paradigms, which are ill-suited for lifelong…

Current adversarial examples (AEs) are typically designed for static models. However, with the wide application of Class-Incremental Learning (CIL), models are no longer static and need to be updated with new data distributed and labeled…

Class Incremental Learning (CIL) requires models to continuously learn new classes without forgetting previously learned ones, while maintaining stable performance across all possible class sequences. In real-world settings, the order in…

Exemplar-free Class Incremental Learning (EFCIL) aims to sequentially learn tasks with access only to data from the current one. EFCIL is of interest because it mitigates concerns about privacy and long-term storage of data, while at the…

Today's autonomous agents, largely driven by foundation models (FMs), can understand natural language instructions and solve long-horizon tasks with human-like reasoning. However, current human-robot interaction largely follows a one-way…

Text clustering, as one of the most fundamental challenges in unsupervised learning, aims at grouping semantically similar text segments without relying on human annotations. With the rapid development of deep learning, deep clustering has…

Class-Incremental Learning (CIL) requires a model to continually learn new classes without forgetting old ones. A common and efficient solution freezes a pre-trained model and employs lightweight adapters, whose parameters are often forced…

Class Incremental Semantic Segmentation (CISS) aims to mitigate catastrophic forgetting by maintaining a balance between previously learned and newly introduced knowledge. Existing methods, primarily based on regularization techniques like…

Source-Free Unsupervised Domain Adaptation (SFUDA) addresses the realistic challenge of adapting a source-trained model to a target domain without access to the source data, driven by concerns over privacy and cost. Existing SFUDA methods…

Unlike traditional Multimodal Class-Incremental Learning (MCIL) methods that focus only on vision and text, this paper explores MCIL across vision, audio and text modalities, addressing challenges in integrating complementary information…

Mixture-of-Experts (MoE) has emerged as a powerful framework for multi-task learning (MTL). However, existing MoE-MTL methods often rely on single-task pretrained backbones and suffer from redundant adaptation and inefficient knowledge…