Related papers: Learning at a Glance: Towards Interpretable Data-l…

Learners sharing similar implicit cognitive states often display comparable observable problem-solving performances. Leveraging collaborative connections among such similar learners proves valuable in comprehending human learning. Motivated…

In Large Visual Language Models (LVLMs), the efficacy of In-Context Learning (ICL) remains limited by challenges in cross-modal interactions and representation disparities. To overcome these challenges, we introduce a novel Visual…

This paper proposes a scalable and straightforward pre-training paradigm for efficient visual conceptual representation called occluded image contrastive learning (OCL). Our OCL approach is simple: we randomly mask patches to generate…

Continual learning (CL) aims to enable information systems to learn from a continuous data stream across time. However, it is difficult for existing deep learning architectures to learn a new task without largely forgetting previously…

Text-Attributed Graphs (TAGs) are graphs of connected textual documents. Graph models can efficiently learn TAGs, but their training heavily relies on human-annotated labels, which are scarce or even unavailable in many applications. Large…

Deep neural networks have achieved impressive performance across a wide range of tasks, but this success often comes with substantial computational and storage costs due to large-scale training data. Dataset distillation addresses this…

Graph contrastive learning defines a contrastive task to pull similar instances close and push dissimilar instances away. It learns discriminative node embeddings without supervised labels, which has aroused increasing attention in the past…

Node classification is a key task in temporal graph learning (TGL). Real-life temporal graphs often introduce new node classes over time, but existing TGL methods assume a fixed set of classes. This assumption brings limitations, as…

Recent efforts in multi-domain learning for semantic segmentation attempt to learn multiple geographical datasets in a universal, joint model. A simple fine-tuning experiment performed sequentially on three popular road scene segmentation…

Deep neural networks often severely forget previously learned knowledge when learning new knowledge. Various continual learning (CL) methods have been proposed to handle such a catastrophic forgetting issue from different perspectives and…

Federated Continual Learning (FCL) enables distributed clients to collaboratively train a global model from online task streams in dynamic real-world scenarios. However, existing FCL methods face challenges of both spatial data…

We investigated domain adaptive semantic segmentation in foggy weather scenarios, which aims to enhance the utilization of unlabeled foggy data and improve the model's adaptability to foggy conditions. Current methods rely on clear images…

Continual graph learning (CGL) is purposed to continuously update a graph model with graph data being fed in a streaming manner. Since the model easily forgets previously learned knowledge when training with new-coming data, the…

In medical image segmentation, heterogeneous privacy policies across institutions often make joint training on pooled datasets infeasible, motivating continual image segmentation-learning from data streams without catastrophic forgetting.…

Contrastive Learning (CL) has been proved to be a powerful self-supervised approach for a wide range of domains, including computer vision and graph representation learning. However, the incremental learning issue of CL has rarely been…

Continual learning (CL) aims to learn a sequence of tasks without forgetting the previously acquired knowledge. However, recent CL advances are restricted to supervised continual learning (SCL) scenarios. Consequently, they are not scalable…

Generalized Category Discovery (GCD) seeks to uncover novel categories in unlabeled data while preserving recognition of known categories, yet prevailing visual-only pipelines and the loose coupling between supervised learning and discovery…

One of the fundamental representation learning tasks is unsupervised sequential disentanglement, where latent codes of inputs are decomposed to a single static factor and a sequence of dynamic factors. To extract this latent information,…

Despite the remarkable success of Self-Supervised Learning (SSL), its generalization is fundamentally hindered by Shortcut Learning, where models exploit superficial features like texture instead of intrinsic structure. We experimentally…

In-context learning (ICL) enables medical image segmentation models to adapt to new anatomical structures from limited examples, reducing the clinical annotation burden. However, standard ICL methods typically rely on dense, global…