Related papers: Multi-Level Heterogeneous Knowledge Transfer Netwo…
Multi-source transfer learning provides an effective solution to data scarcity in real-world supervised learning scenarios by leveraging multiple source tasks. In this field, existing works typically use all available samples from sources…
Generalized few-shot semantic segmentation (GFSS) aims to segment objects of both base and novel classes, using sufficient samples of base classes and few samples of novel classes. Representative GFSS approaches typically employ a two-phase…
Accurate segmentation of brain tumors from 3D multimodal MRI is vital for diagnosis and treatment planning across diverse brain tumors. This paper addresses the challenges posed by the BraTS 2023, presenting a unified transfer learning…
In the rapidly advancing realm of educational technology, it becomes critical to accurately trace and understand student knowledge states. Conventional Knowledge Tracing (KT) models have mainly focused on binary responses (i.e., correct and…
With the development of edge networks and mobile computing, the need to serve heterogeneous data sources at the network edge requires the design of new distributed machine learning mechanisms. As a prevalent approach, Federated Learning…
Exploring and mining subtle yet distinctive features between sub-categories with similar appearances is crucial for fine-grained visual categorization (FGVC). However, less effort has been devoted to assessing the quality of extracted…
Sample efficiency is central to developing practical reinforcement learning (RL) for complex and large-scale decision-making problems. The ability to transfer and generalize knowledge gained from previous experiences to downstream tasks can…
Remote sensing images captured by different platforms exhibit significant disparities in spatial resolution. Large scale factor super-resolution (SR) algorithms are vital for maximizing the utilization of low-resolution (LR) satellite data…
Knowledge Tracing (KT) is a fundamental task in Intelligent Tutoring Systems (ITS), which aims to model the dynamic knowledge states of students based on their interaction histories. However, existing KT models often rely on a global…
Annotating automatic target recognition (ATR) is a highly challenging task, primarily due to the unavailability of labeled data in the target domain. Hence, it is essential to construct an optimal target domain classifier by utilizing the…
Infrared small target detection (IRSTD) has recently benefitted greatly from U-shaped neural models. However, largely overlooking effective global information modeling, existing techniques struggle when the target has high similarities with…
Large Language Models (LLMs) offer a transparent brain with accessible parameters that encode extensive knowledge, which can be analyzed, located and transferred. Consequently, a key research challenge is to transcend traditional knowledge…
Fabric defect segmentation is integral to textile quality control. Despite this, the scarcity of high-quality annotated data and the diversity of fabric defects present significant challenges to the application of deep learning in this…
Cross-corpus speech emotion recognition (SER) poses a challenge due to feature distribution mismatch, potentially degrading the performance of established SER methods. In this paper, we tackle this challenge by proposing a novel transfer…
Deep networks can learn to accurately recognize objects of a category by training on a large number of annotated images. However, a meta-learning challenge known as a low-shot image recognition task comes when only a few images with…
Generally, current image manipulation detection models are simply built on manipulation traces. However, we argue that those models achieve sub-optimal detection performance as it tends to: 1) distinguish the manipulation traces from a lot…
Hyperspectral image (HSI) classification presents inherent challenges due to high spectral dimensionality, significant domain shifts, and limited availability of labeled data. To address these issues, we propose a novel Active Transfer…
Segment Anything Model (SAM) is drastically accelerating the speed and accuracy of automatically segmenting and labeling large Red-Green-Blue (RGB) imagery datasets. However, SAM is unable to segment and label images outside of the visible…
To eliminate the requirement of fully-labeled data for supervised model training in traditional Federated Learning (FL), extensive attention has been paid to the application of Self-supervised Learning (SSL) approaches on FL to tackle the…
Low-latency and high-precision vehicle localization plays a significant role in enhancing traffic safety and improving traffic management for intelligent transportation. However, in complex road environments, the low latency and high…