Parallel learning: Overview and perspective for computational learning across Syn2Real and Sim2Real
Q Miao, Y Lv, M Huang, X Wang… - IEEE/CAA Journal of …, 2023 - ieeexplore.ieee.org
The virtual-to-real paradigm, ie, training models on virtual data and then applying them to
solve real-world problems, has attracted more and more attention from various domains by …
solve real-world problems, has attracted more and more attention from various domains by …
Image data augmentation approaches: A comprehensive survey and future directions
Deep learning algorithms have exhibited impressive performance across various computer
vision tasks; however, the challenge of overfitting persists, especially when dealing with …
vision tasks; however, the challenge of overfitting persists, especially when dealing with …
Enhancing sample utilization through sample adaptive augmentation in semi-supervised learning
In semi-supervised learning, unlabeled samples can be utilized through augmentation and
consistency regularization. However, we observed certain samples, even undergoing strong …
consistency regularization. However, we observed certain samples, even undergoing strong …
DiffuseMix: Label-Preserving Data Augmentation with Diffusion Models
Recently a number of image-mixing-based augmentation techniques have been introduced
to improve the generalization of deep neural networks. In these techniques two or more …
to improve the generalization of deep neural networks. In these techniques two or more …
GW-net: An efficient grad-CAM consistency neural network with weakening of random erasing features for semi-supervised person re-identification
S Zhu, Y Zhang, Y Feng - Image and Vision Computing, 2023 - Elsevier
Person re-identification (Re-ID) subject to loss of detailed information (sacrificing certain
intricate body details) in samples caused by conventional regularization algorithms and …
intricate body details) in samples caused by conventional regularization algorithms and …
Dynamic Feature Learning and Matching for Class-Incremental Learning
Class-incremental learning (CIL) has emerged as a means to learn new classes
incrementally without catastrophic forgetting of previous classes. Recently, CIL has …
incrementally without catastrophic forgetting of previous classes. Recently, CIL has …
Detection of calf abnormal respiratory behavior based on frame difference and improved YOLOv5 method
F Zeng, B Li, H Wang, J Zhu, N Jia, Y Zhao… - … and Electronics in …, 2023 - Elsevier
Bovine respiratory disease (BRD) is the leading cause of death in calves. Abnormal
respiratory behavior (ARB) is one of the prevalent clinical signs of BRD in calves …
respiratory behavior (ARB) is one of the prevalent clinical signs of BRD in calves …
GAN-Based Sub-Instance Augmentation for Open-Pit Mine Change Detection in Remote Sensing Images
Z Xie, J Jiang, D Yuan, K Li, Z Liu - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Remote sensing (RS) change detection (CD) for open-pit mines plays a critical role in both
mineral development and environmental conservation. The performance of supervised deep …
mineral development and environmental conservation. The performance of supervised deep …
Recognition and estimation of human finger pointing with an RGB camera for robot directive
E Bamani, E Nissinman, L Koenigsberg, I Meir… - arXiv preprint arXiv …, 2023 - arxiv.org
In communication between humans, gestures are often preferred or complementary to
verbal expression since the former offers better spatial referral. Finger pointing gesture …
verbal expression since the former offers better spatial referral. Finger pointing gesture …
CutFreq: Cut-and-Swap Frequency Components for Low-Level Vision Augmentation
Low-level vision plays a crucial role in a wide range of imaging quality and image
recognition applications. However, the limited size, quality, and diversity of datasets often …
recognition applications. However, the limited size, quality, and diversity of datasets often …