CMT DeepLab: Clustering Mask Transformers for Panoptic Segmentation | CVPR 2022

[CVPR 2021] MaX-DeepLab: End-to-End Panoptic Segmentation with Mask TransformersПодробнее

Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic SegmentationПодробнее

Single-shot Path Integrated Panoptic SegmentationПодробнее

Cross View Transformers for Real Time Map View Semantic Segmentation | CVPR 2022Подробнее

[CVPR 2022] TubeFormer-Deeplab: Video Mask TransformerПодробнее

Time-Space Transformers for Video Panoptic SegmentationПодробнее

CVPR 2022 Mask Transfiner for High-Quality Instance SegmentationПодробнее

MaskConver: Revisiting Pure Convolution Model for Panoptic SegmentationПодробнее

MIST: Medical Image Segmentation Transformer With Convolutional Attention Mixing (CAM) DecoderПодробнее

Rethinking Semantic Segmentation: A Prototype View | CVPR 2022Подробнее

EPro PnP: Generalized End to End Probabilistic Perspective N Points for Monocular Object | CVPR 2022Подробнее

AFTer-SAM: Adapting SAM With Axial Fusion Transformer for Medical Imaging SegmentationПодробнее

Panoptic Segmentation using DETRПодробнее

Panoptic Image Segmentation: Mask2Former explained | Identify all objects!Подробнее

End to End Referring Video Object Segmentation With Multimodal Transformers | CVPR'22Подробнее

HGFormer: Hierarchical Grouping Transformer for Domain Generalized Semantic SegmentationПодробнее

Masking in Gen AI Training: The Hidden Genius in TransformersПодробнее

Semantic Segmentation using DeepLabПодробнее