Masked image modeling (MIM) is a highly popular and effective self-supervised learning
method for image understanding. The existing MIM-based methods mostly focus on spatial …

Recently model merging techniques have surfaced as a solution to combine multiple single-
talent models into a single multi-talent model. However previous endeavors in this field have …

Few-class object detection is a critical task in numerous scenes, such as autonomous
driving and intelligent surveillance. The current researches mainly focus on the correlation …

Existing cross-domain classification and detection methods usually apply a consistency
constraint between the target sample and its self-augmentation for unsupervised learning …

Abstract Unsupervised Knowledge Amalgamation (UKA) trains a versatile student model
with an unlabeled dataset to handle joint objectives of multiple off-the-shelf teacher models …

With breakthroughs in pretrained language models, a large number of finetuned models
specialized in distinct domains have surfaced online. Yet, when faced with a fresh dataset …

In this paper, we present a novel transformer architecture tailored for learning robust power
system state representations, which strives to optimize power dispatch for the power flow …

In the current work, we explored a new knowledge amalgamation problem, termed
Federated Selective Aggregation for on-device knowledge amalgamation (FedSA). FedSA …

Non-blind rotary motion deblurring (RMD) aims to recover the latent clear image from a
rotary motion blurred (RMB) image. The rotation center is a crucial input parameter in non …

Artificial Intelligence (AI) has exploded into mainstream consciousness with commercial
investments exceeding $90 billion in the last year alone. Inasmuch as consumer-facing …