Laplacian Pyramid Reconstruction and Refinement for Semantic Segmentation

8 May 2016Golnaz GhiasiCharless C. Fowlkes

CNN architectures have terrific recognition performance but rely on spatial pooling which makes it difficult to adapt them to tasks that require dense, pixel-accurate labeling. This paper makes two contributions: (1) We demonstrate that while the apparent spatial resolution of convolutional feature maps is low, the high-dimensional feature representation contains significant sub-pixel localization information... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Semantic Segmentation Cityscapes test LRR-4x Mean IoU (class) 71.8% # 40