https://github.com/joe-siyuan-qiao/ViP-DeepLab
공식 코드ViP-DeepLab: Learning Visual Perception with Depth-aware Video Panoptic Segmentation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
ViP-DeepLab: Learning Visual Perception with Depth-aware Video Panoptic Segmentation
Micro-Batch Training with Batch-Channel Normalization and Weight Standardization
Topology-aware Robust Optimization for Out-of-distribution Generalization
Trapped in texture bias? A large scale comparison of deep instance segmentation
Fast and Accurate Scene Parsing via Bi-direction Alignment Networks
Semantic Segmentation-assisted Scene Completion for LiDAR Point Clouds
Mask3D: Mask Transformer for 3D Semantic Instance Segmentation
Continual Unsupervised Domain Adaptation for Semantic Segmentation
HyperDense-Net: A hyper-densely connected CNN for multi-modal image segmentation
Teach me to segment with mixed supervision: Confident students become masters
Deep CNN ensembles and suggestive annotations for infant brain MRI segmentation
Translated Skip Connections -- Expanding the Receptive Fields of Fully Convolutional Neural Networks
Bridging the Inter-Domain Gap through Low-Level Features for Cross-Modal Medical Image Segmentation
A Skeleton-based Approach For Rock Crack Detection Towards A Climbing Robot Application
CIAN: Cross-Image Affinity Net for Weakly Supervised Semantic Segmentation
Panoptic SwiftNet: Pyramidal Fusion for Real-time Panoptic Segmentation
Scale-Adaptive Neural Dense Features: Learning via Hierarchical Context Aggregation
SemSegDepth: A Combined Model for Semantic Segmentation and Depth Completion
Domain generalization of 3D semantic segmentation in autonomous driving
COLA: COarse LAbel pre-training for 3D semantic segmentation of sparse LiDAR datasets
U-MixFormer: UNet-like Transformer with Mix-Attention for Efficient Semantic Segmentation
CATALOG: A Camera Trap Language-guided Contrastive Learning Model
Contextual Embedding Learning to Enhance 2D Networks for Volumetric Image Segmentation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.