AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

Fully Convolutional Networks for Panoptic Segmentation with Point-based Supervision

Yanwei Li, Hengshuang Zhao, Xiaojuan Qi, Yukang Chen, Lu Qi, Liwei Wang, Zeming Li, Jian Sun, Jiaya Jia

TPAMI 2022 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 57 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add kernel-level fusion (ablation)Panoptic FCN · COCO valPQ (%): 38.7 -> 41.3Improved
add Matrix NMS on top of kernel fusion (ablation)Panoptic FCN · COCO valPQ (%): 41.3 -> 41.3No clear effect
add relative coordinates to both kernel head and feature encoder (ablation)Panoptic FCN · COCO valPQ (%): 39.9 -> 41.3Improved
add coordinates to kernel head only (ablation)Panoptic FCN · COCO valPQ (%): 39.9 -> 39.9No clear effect
add deformable convolutions to position head (ablation)Panoptic FCN · COCO valPQ (%): 39.2 -> 39.9Improved
add weighted dice loss sampling k=7 kernels (ablation)Panoptic FCN · COCO valPQ (%): 40.2 -> 41.3Improved
use mass center instead of box center for ground truth (ablation)Panoptic FCN · COCO valPQ (%): 40.6 -> 41.3Improved
use Semantic FPN feature instead of FPN-P2 (ablation)Panoptic FCN · COCO valPQ (%): 40.6 -> 41.3Improved
raise feature encoder channels from 16 to 64 (ablation)Panoptic FCN · COCO valPQ (%): 39.9 -> 41.3Improved
add dilated shape augmentation to P20 supervision (ablation)Panoptic FCN P20 · COCO valPQ (%): 32.7 -> 34.0Improved
increase training schedule from 1x to 2x (ablation)Panoptic FCN · COCO valPQ (%): 41.3 -> 43.2Improved
use concave instead of convex target with P100 points (ablation)Panoptic FCN P100 · COCO valPQ (%): 33.4 -> 37.0Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy