MMSegmentation v1.2.0 (10/12/2023)

From v1.1.0 to v1.2.0, we are delighted that MMSegmentation supports full-flow open-vocabulary semantic segmentation and monocular depth estimation tasks!

• Open-vocabulary semantic segmentation: SAN and CAT-Seg:

  • Side Adapter Network for Open-Vocabulary Semantic Segmentation
    
  • Cost Aggregation for Open-Vocabulary Semantic Segmentation
    

• Monocular depth estimation: VPD and AdaBins:

  • Visual Perception with Pre-trained Diffusion Models
    
  • AdaBins: Depth Estimation using Adaptive Bins:
    

Features

• Support Side Adapter Network (#3232)

Bug Fixes

• fix wrong variables passing for set_dataset_meta (#3348)

Documentation

• add documentation of Finetune ONNX Models (MMSegemetation) Inference for NVIDIA Jetson (#3372)