Related papers: BOFA: Bridge-Layer Orthogonal Low-Rank Fusion for …
Incremental Learning (IL) aims to accumulate knowledge from sequential input tasks while overcoming catastrophic forgetting. Existing IL methods typically assume that an incoming task has only increments of classes or domains, referred to…
Federated learning (FL) provides a decentralized machine learning paradigm where a server collaborates with a group of clients to learn a global model without accessing the clients' data. User heterogeneity is a significant challenge for…
Traditional learning systems are trained in closed-world for a fixed number of classes, and need pre-collected datasets in advance. However, new classes often emerge in real-world applications and should be learned incrementally. For…
Continual learning with vision-language models like CLIP offers a pathway toward scalable machine learning systems by leveraging its transferable representations. Existing CLIP-based methods adapt the pre-trained image encoder by adding…
Exemplar-free class-incremental learning (EFCIL) aims to mitigate catastrophic forgetting in class-incremental learning (CIL) without available historical training samples as exemplars. Compared with its exemplar-based CIL counterpart that…
Multimodal learning, which integrates data from diverse sensory modes, plays a pivotal role in artificial intelligence. However, existing multimodal learning methods often struggle with challenges where some modalities appear more dominant…
The large-scale pretrained model CLIP, trained on 400 million image-text pairs, offers a promising paradigm for tackling vision tasks, albeit at the image level. Later works, such as DenseCLIP and LSeg, extend this paradigm to dense…
Complementary-label learning (CLL) is a weakly supervised paradigm where instances are labeled with classes they do not belong to. Despite a decade of research, CLL methods remain competitive mainly on 10-class classification, with scaling…
Class-Incremental Learning (CIL) requires models to continuously acquire new classes without forgetting previously learned ones. A dominant paradigm involves freezing a pre-trained model and training lightweight, task-specific adapters.…
We introduce Correspondence-Oriented Imitation Learning (COIL), a conditional policy learning framework for visuomotor control with a flexible task representation in 3D. At the core of our approach, each task is defined by the intended…
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.…
Class-incremental learning (CIL) aims to enable models to continuously learn new classes while overcoming catastrophic forgetting. The introduction of pre-trained models has brought new tuning paradigms to CIL. In this paper, we revisit…
With the advent of large-scale pre-trained models, interest in adapting and exploiting them for continual learning scenarios has grown. In this paper, we propose an approach to exploiting pre-trained vision-language models (e.g. CLIP) that…
Class-Incremental Learning (CIL) enables learning systems to continuously adapt to evolving data streams. With the advancement of pre-training, leveraging pre-trained vision-language models (e.g., CLIP) offers a promising starting point for…
Class incremental learning (CIL) algorithms aim to continually learn new object classes from incrementally arriving data while not forgetting past learned classes. The common evaluation protocol for CIL algorithms is to measure the average…
Recent years have witnessed the great success of blind image quality assessment (BIQA) in various task-specific scenarios, which present invariable distortion types and evaluation criteria. However, due to the rigid structure and learning…
In online continual learning (CL), models trained on changing distributions easily forget previously learned knowledge and bias toward newly received tasks. To address this issue, we present Continual Bias Adaptor (CBA), a bi-level…
Concept Bottleneck Models (CBMs) enhance the interpretability of AI systems, particularly by bridging visual input with human-understandable concepts, effectively acting as a form of multimodal interpretability model. However, existing CBMs…
In the rapidly evolving field of artificial intelligence, multimodal models, e.g., integrating vision and language into visual-language models (VLMs), have become pivotal for many applications, ranging from image captioning to multimodal…
Class-incremental learning (CIL) poses significant challenges in open-world scenarios, where models must not only learn new classes over time without forgetting previous ones but also handle inputs from unknown classes that a closed-set…