Pulling Target to Source: A New Perspective on Domain Adaptive Semantic Segmentation

Information Science, Computer Science, Automation, Artificial Intelligence,
domain adaptation   semantic segmentation   domain generalization   contrastive learning   cross-domain features  

A New Perspective on Domain Adaptive Semantic Segmentation: T2S-DA Study Background and Significance Semantic segmentation plays a crucial role in computer vision, but its performance often relies on extensive labeled data. However, acquiring labeled data is costly, especially in complex scenarios. To address this, many studies turn to synthetic da...

One-Shot Generative Domain Adaptation in 3D GANs

Information Science, Electronic Information, Computer Science, Artificial Intelligence,
3D-aware image generation   generative adversarial networks   one-shot domain adaptation   cross-domain consistency   multi-view consistency  

One-shot Generative Domain Adaptation in 3D GANs In recent years, Generative Adversarial Networks (GANs) have achieved remarkable progress in the field of image generation. While traditional 2D generative models exhibit impressive performance across various tasks, extending this technology to 3D domains (3D-aware image generation) remains challengi...

Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach

Information Science, Electronic Information, Computer Science, Automation, Artificial Intelligence,
attribution maps   perturbation evaluation   explainability   convolutional neural networks   smoothness   monotonicity   baseline checks  

Deep Learning Explainability Research: A Perturbation-Based Evaluation Method for Attribution Maps Background and Motivation With the remarkable success of deep learning models across various tasks, there is growing attention on the interpretability and transparency of these models. However, while these models excel in accuracy, their decision-maki...

A RAFT-based Network and Synthetic Dataset for Digital Video Stabilization

Information Science, Artificial Intelligence,
RAFT   video stabilization   synthetic dataset   deep learning   optical flow prediction  

Report on the Study of Deep Learning-Based Video Stabilization Methods and the SynthStab Synthetic Dataset Background Introduction Digital video stabilization technology, which removes unnecessary vibrations and camera motion artifacts through software, is a critical component in modern video processing, particularly for amateur video shooting. How...

MVTN: Learning Multi-View Transformations for 3D Understanding

MVTN: Learning Multi-View Transformations for 3D Understanding

Information Science, Artificial Intelligence,
multi-view   3D shape recognition   deep learning   3D point clouds   segmentation   rendering   model optimization  

Multi-View Transformation Network (MVTN): New Advances in 3D Understanding Research Background and Motivation Recent advancements in deep learning for 3D data in computer vision have achieved significant success, particularly in tasks like classification, segmentation, and retrieval. However, effectively utilizing 3D shape information remains a cha...

Cross-Scale Co-Occurrence Local Binary Pattern for Image Classification

Information Science, Electronic Information, Computer Science, Artificial Intelligence,
image classification   local binary pattern   cross-scale   co-occurrence LBP features   scale invariant   rotation invariant  

Research on Cross-Scale Co-Occurrence Local Binary Pattern (CS-COLBP) for Image Classification Image classification is a key area in computer vision, with feature extraction being its core research focus. The Local Binary Pattern (LBP), due to its efficiency and descriptive power, has been widely used in tasks such as texture classification and fac...