activity
20172026
most citedPer-Pixel Classification is Not All You Need for Semantic Segmentation

167 citations · 223 across the 8 of their papers we have counts for

collaborators
Showing cs.CVShow all

18 papers · 1 filter

cs.CV2026

PhysInOne: Visual Physics Learning and Reasoning in One Suite

Siyuan Zhou, Hejun Wang, Hu Cheng +36

We present PhysInOne, a large-scale synthetic dataset addressing the critical scarcity of physically-grounded training data for AI systems. Unlike existing datasets limited to mere…

cs.CV2021167 cited

Per-Pixel Classification is Not All You Need for Semantic Segmentation

Bowen Cheng, Alexander G. 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…

cs.CV2021

Pseudo-IoU: Improving Label Assignment in Anchor-Free Object Detection

Jiachen Li, Bowen Cheng, Rogerio Feris +4

Current anchor-free object detectors are quite simple and effective yet lack accurate label assignment methods, which limits their potential in competing with classic anchor-based…

cs.CV202128 cited

Boundary IoU: Improving Object-Centric Image Segmentation Evaluation

Bowen Cheng, Ross Girshick, Piotr Dollár +2

We present Boundary IoU (Intersection-over-Union), a new segmentation evaluation measure focused on boundary quality. We perform an extensive analysis across different error types…

cs.CV20206 cited

ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual Recognition

Hsin-Pai Cheng, Feng Liang, Meng Li +5

Scale variance among different sizes of body parts and objects is a challenging problem for visual recognition tasks. Existing works usually design dedicated backbone or apply Neur…

cs.CV202012 cited

Naive-Student: Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation

Liang-Chieh Chen, Raphael Gontijo Lopes, Bowen Cheng +5

Supervised learning in large discriminative models is a mainstay for modern computer vision. Such an approach necessitates investing in large-scale human-annotated datasets for ach…