Weakly Supervised Scene Parsing with Point-based Distance Metric Learning

11/06/2018
by   Rui Qian, et al.
4

Semantic scene parsing is suffering from the fact that pixel-level annotations are hard to be collected. To tackle this issue, we propose a Point-based Distance Metric Learning (PDML) in this paper. PDML does not require dense annotated masks and only leverages several labeled points that are much easier to obtain to guide the training process. Concretely, we leverage semantic relationship among the annotated points by encouraging the feature representations of the intra- and inter-category points to keep consistent, i.e. points within the same category should have more similar feature representations compared to those from different categories. We formulate such a characteristic into a simple distance metric loss, which collaborates with the point-wise cross-entropy loss to optimize the deep neural networks. Furthermore, to fully exploit the limited annotations, distance metric learning is conducted across different training images instead of simply adopting an image-dependent manner. We conduct extensive experiments on two challenging scene parsing benchmarks of PASCAL-Context and ADE 20K to validate the effectiveness of our PDML, and competitive mIoU scores are achieved.

READ FULL TEXT
research
07/29/2019

Consensus Feature Network for Scene Parsing

Scene parsing is challenging as it aims to assign one of the semantic ca...
research
10/17/2020

LID 2020: The Learning from Imperfect Data Challenge Results

Learning from imperfect data becomes an issue in many industrial applica...
research
02/03/2021

Multimodal-Aware Weakly Supervised Metric Learning with Self-weighting Triplet Loss

In recent years, we have witnessed a surge of interests in learning a su...
research
07/19/2023

CPCM: Contextual Point Cloud Modeling for Weakly-supervised Point Cloud Semantic Segmentation

We study the task of weakly-supervised point cloud semantic segmentation...
research
03/10/2020

Realizing Pixel-Level Semantic Learning in Complex Driving Scenes based on Only One Annotated Pixel per Class

Semantic segmentation tasks based on weakly supervised condition have be...
research
03/29/2023

DPF: Learning Dense Prediction Fields with Weak Supervision

Nowadays, many visual scene understanding problems are addressed by dens...
research
09/27/2017

Scene Parsing by Weakly Supervised Learning with Image Descriptions

This paper investigates a fundamental problem of scene understanding: ho...

Please sign up or login with your details

Forgot password? Click here to reset