This is the toolkit and instruction page for the Places Challenge 2017. There are three tasks in Places Challenge 2017: Scene Parsing, Scene Instance Segmentation, and Semantic Boundary Detection. The data for all the three tasks are from the fully annotated image dataset ADE20K, there are 20K images for training, 2K images for validation, and 3K images for testing. Teams could particpate in one or two or three of the tasks. Click the instruction below for the detail of each task.

• Instruction for Scene Parsing Task is here
• Instruction for Instance Segmentation Task is here
• Instruction for Semantic Boundary Segmentation Task is here