Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations

2019/04/10 by Jiwoon Ahn, Sunghyun Cho, Ahn, Jiwoon +3 · 11 citations
Computer Science · #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #Digital Imaging for Blood Diseases #FOS: Computer and information sciences #Image and Object Detection Techniques #Machine Learning (cs.LG)

paper · pdf · doi:10.48550/arxiv.1904.05044

openalex publication_date 2019/04/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This paper presents a novel approach for learning instance segmentation with image-level class labels as supervision. Our approach generates pseudo instance segmentation labels of training images, which are used to train a fully supervised model. For generating the pseudo labels, we first identify confident seed areas of object classes from attention maps of an image classification model, and propagate them to discover the entire instance areas with accurate boundaries. To this end, we propose IRNet, which estimates rough areas of individual instances and detects boundaries between different object classes. It thus enables to assign instance labels to the seeds and to propagate them within the boundaries so that the entire areas of instances can be estimated accurately. Furthermore, IRNet is trained with inter-pixel relations on the attention maps, thus no extra supervision is required. Our method with IRNet achieves an outstanding performance on the PASCAL VOC 2012 dataset, surpassing not only previous state-of-the-art trained with the same level of supervision, but also some of previous models relying on stronger supervision.

Citations

• ImageNet Large Scale Visual Recognition Challenge
• Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry\n and Semantics

Cited by

• SynthSeg-Agents: Multi-Agent Synthetic Data Generation for Zero-Shot Weakly Supervised Semantic Segmentation
• SSR: Semantic and Spatial Rectification for CLIP-based Weakly Supervised Segmentation
• Lightweight Transformer Framework for Weakly Supervised Semantic Segmentation
• Region-CAM: Towards Accurate Object Regions in Class Activation Maps for Weakly Supervised Learning Tasks
• Sample-Centric Multi-Task Learning for Detection and Segmentation of Industrial Surface Defects
• Machine Learning Frameworks for Large-Scale Radio Surveys: A Summary of Recent Studies
• Super-BPD: Super Boundary-to-Pixel Direction for Fast Image Segmentation
• Localized Region Guidance for Class Activation Mapping in WSSS
• Dual-Thresholding Heatmaps to Cluster Proposals for Weakly Supervised Object Detection
• NoPeopleAllowed: The Three-Step Approach to Weakly Supervised Semantic Segmentation
• Deep Learning for Crack Detection: A Review of Learning Paradigms, Generalizability, and Datasets

Related

• Label-PEnet: Sequential Label Propagation and Enhancement Networks for Weakly Supervised Instance Segmentation
• Weakly Supervised Instance Segmentation using Class Peak Response
• Where are the Masks: Instance Segmentation with Image-level Supervision
• Instance Segmentation with Point Supervision
• From Image-level to Pixel-level Labeling with Convolutional Networks