Related papers: Hierarchical Dual-Subspace Decoupling for Continua…

Large language-vision models (LVLMs) such as CLIP, Flamingo, and BLIP have revolutionized AI by enabling understanding across textual and visual modalities. These models excel at tasks like image captioning, visual question answering, and…

This paper proposes a novel face recognition algorithm based on large-scale supervised hierarchical feature learning. The approach consists of two parts: hierarchical feature learning and large-scale model learning. The hierarchical feature…

Continual Learning is considered a key step toward next-generation Artificial Intelligence. Among various methods, replay-based approaches that maintain and replay a small episodic memory of previous samples are one of the most successful…

Multimodal image registration is a fundamental task and a prerequisite for downstream cross-modal analysis. Despite recent progress in shared feature extraction and multi-scale architectures, two key limitations remain. First, some methods…

Deep Metric Learning (DML) proposes to learn metric spaces which encode semantic similarities as embedding space distances. These spaces should be transferable to classes beyond those seen during training. Commonly, DML methods task…

Existing Masked Image Modeling methods apply fixed mask patterns to guide the self-supervised training. As those mask patterns resort to different criteria to depict image contents, sticking to a fixed pattern leads to a limited vision cues…

Vision-language models (VLMs) raise growing concerns about privacy, copyright, and bias, motivating machine unlearning to remove sensitive knowledge. However, existing methods primarily fine-tune the language decoder, leading to superficial…

Multiple modalities can provide more valuable information than single one by describing the same contents in various ways. Hence, it is highly expected to learn effective joint representation by fusing the features of different modalities.…

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…

This paper presents DFR (Decompose, Fuse and Reconstruct), a novel framework that addresses the fundamental challenge of effectively utilizing multi-modal guidance in few-shot segmentation (FSS). While existing approaches primarily rely on…

Deep metric learning (DML) is a cornerstone of many computer vision applications. It aims at learning a mapping from the input domain to an embedding space, where semantically similar objects are located nearby and dissimilar objects far…

Malignant brain tumors have become an aggressive and dangerous disease that leads to death worldwide.Multi-modal MRI data is crucial for accurate brain tumor segmentation, but missing modalities common in clinical practice can severely…

Humans learn to recognize and manipulate new objects in lifelong settings without forgetting the previously gained knowledge under non-stationary and sequential conditions. In autonomous systems, the agents also need to mitigate similar…

Prompt learning as a parameter-efficient method that has been widely adopted to adapt Vision-Language Models (VLMs) to downstream tasks. While hard-prompt design requires domain expertise and iterative optimization, soft-prompt methods rely…

Large language models (LLMs) exhibit exceptional performance but pose substantial privacy risks due to training data memorization, particularly within healthcare contexts involving imperfect or privacy-sensitive patient information. We…

Brain-inspired Hyperdimensional (HD) computing is an emerging technique for cognitive tasks in the field of low-power design. As a fast-learning and energy-efficient computational paradigm, HD computing has shown great success in many…

Multi-task learning (MTL) paradigm focuses on jointly learning two or more tasks, aiming for significant improvement w.r.t model's generalizability, performance, and training/inference memory footprint. The aforementioned benefits become…

We propose a compact and effective framework to fuse multimodal features at multiple layers in a single network. The framework consists of two innovative fusion schemes. Firstly, unlike existing multimodal methods that necessitate…

Large Language Models (LLMs) have attracted significant attention in recommender systems for their excellent world knowledge capabilities. However, existing methods that rely on Euclidean space struggle to capture the rich hierarchical…

Self-supervised learning has recently emerged as a strong alternative in document analysis. These approaches are now capable of learning high-quality image representations and overcoming the limitations of supervised methods, which require…