Pointly-Supervised Panoptic Segmentation

10/25/2022
by   Junsong Fan, et al.
0

In this paper, we propose a new approach to applying point-level annotations for weakly-supervised panoptic segmentation. Instead of the dense pixel-level labels used by fully supervised methods, point-level labels only provide a single point for each target as supervision, significantly reducing the annotation burden. We formulate the problem in an end-to-end framework by simultaneously generating panoptic pseudo-masks from point-level labels and learning from them. To tackle the core challenge, i.e., panoptic pseudo-mask generation, we propose a principled approach to parsing pixels by minimizing pixel-to-point traversing costs, which model semantic similarity, low-level texture cues, and high-level manifold knowledge to discriminate panoptic targets. We conduct experiments on the Pascal VOC and the MS COCO datasets to demonstrate the approach's effectiveness and show state-of-the-art performance in the weakly-supervised panoptic segmentation problem. Codes are available at https://github.com/BraveGroup/PSPS.git.

READ FULL TEXT

page 3

page 14

research
04/10/2023

Monte Carlo Linear Clustering with Single-Point Supervision is Enough for Infrared Small Target Detection

Single-frame infrared small target (SIRST) detection aims at separating ...
research
03/29/2023

DPF: Learning Dense Prediction Fields with Weak Supervision

Nowadays, many visual scene understanding problems are addressed by dens...
research
02/27/2023

Self Correspondence Distillation for End-to-End Weakly-Supervised Semantic Segmentation

Efficiently training accurate deep models for weakly supervised semantic...
research
12/14/2021

Uncertainty Estimation via Response Scaling for Pseudo-mask Noise Mitigation in Weakly-supervised Semantic Segmentation

Weakly-Supervised Semantic Segmentation (WSSS) segments objects without ...
research
06/15/2019

Mask Based Unsupervised Content Transfer

We consider the problem of translating, in an unsupervised manner, betwe...
research
03/23/2017

Weakly Supervised Object Localization Using Things and Stuff Transfer

We propose to help weakly supervised object localization for classes whe...
research
03/23/2022

Activation-Based Sampling for Pixel- to Image-Level Aggregation in Weakly-Supervised Segmentation

Classification networks can be used to localize and segment objects in i...

Please sign up or login with your details

Forgot password? Click here to reset