Timezone: »

 
Spotlight
Per-Pixel Classification is Not All You Need for Semantic Segmentation
Bowen Cheng · Alex Schwing · Alexander Kirillov

@

Modern approaches typically formulate semantic segmentation as a per-pixel classification task, while instance-level segmentation is handled with an alternative mask classification. Our key insight: mask classification is sufficiently general to solve both semantic- and instance-level segmentation tasks in a unified manner using the exact same model, loss, and training procedure. Following this observation, we propose MaskFormer, a simple mask classification model which predicts a set of binary masks, each associated with a single global class label prediction. Overall, the proposed mask classification-based method simplifies the landscape of effective approaches to semantic and panoptic segmentation tasks and shows excellent empirical results. In particular, we observe that MaskFormer outperforms per-pixel classification baselines when the number of classes is large. Our mask classification-based method outperforms both current state-of-the-art semantic (55.6 mIoU on ADE20K) and panoptic segmentation (52.7 PQ on COCO) models.

Author Information

Bowen Cheng (University of Illinois, Urbana Champaign)
Alex Schwing (University of Illinois at Urbana-Champaign)
Alexander Kirillov (Meta AI Research)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors