Search Results for author:
Found 11 papers, 6 papers with code
NeRF-Det++: Incorporating Semantic Cues and Perspective-aware Depth Supervision for Indoor Multi-View 3D Detection
We project the freely available 3D segmentation annotations onto the 2D plane and leverage the corresponding 2D semantic maps as the supervision signal, significantly enhancing the semantic awareness of multi-view detectors.
Towards Head Computed Tomography Image Reconstruction Standardization with Deep Learning Assisted Automatic Detection
Three-dimensional (3D) reconstruction of head Computed Tomography (CT) images elucidates the intricate spatial relationships of tissue structures, thereby assisting in accurate diagnosis.
Shuffled Differentially Private Federated Learning for Time Series Data Analytics
Specifically, we employ local differential privacy to extend the privacy protection trust boundary to the clients.
Neural Collapse Inspired Federated Learning with Non-iid Data
One of the challenges in federated learning is the non-independent and identically distributed (non-iid) characteristics between heterogeneous devices, which cause significant differences in local updates and affect the performance of the central server.
OBMO: One Bounding Box Multiple Objects for Monocular 3D Object Detection
Unfortunately, the network cannot accurately distinguish different depths from such non-discriminative visual features, resulting in unstable depth training.
Self-supervised and Weakly Supervised Contrastive Learning for Frame-wise Action Representations
In this paper, we introduce a new framework of contrastive action representation learning (CARL) to learn frame-wise action representation in a self-supervised or weakly-supervised manner, especially for long videos.
S$^2$-FPN: Scale-ware Strip Attention Guided Feature Pyramid Network for Real-time Semantic Segmentation
This paper presents a new model to achieve a trade-off between accuracy/speed for real-time road scene semantic segmentation.
Ranked #1 on
Real-Time Semantic Segmentation
on Cityscapes
Technical Report on Subspace Pyramid Fusion Network for Semantic Segmentation
The following is a technical report to test the validity of the proposed Subspace Pyramid Fusion Module (SPFM) to capture multi-scale feature representations, which is more useful for semantic segmentation.
Sparse Fuse Dense: Towards High Quality 3D Detection with Depth Completion
Many multi-modal methods are proposed to alleviate this issue, while different representations of images and point clouds make it difficult to fuse them, resulting in suboptimal performance.
Digging Into Output Representation for Monocular 3D Object Detection
This characteristic indicates that monocular 3D detection is inherently different from other typical detection tasks that have the same dimensional input and output.
Learning Rate Dropout
The uncertainty of the descent path helps the model avoid saddle points and bad local minima.
