Related papers: Pseudo-label Alignment for Semi-supervised Instance Segmentation

Pseudo-label Alignment for Semi-supervised Instance Segmentation

URL: http://arxiv.org/abs/2308.05359v1
Date: Thu, 10 Aug 2023 05:56:53 GMT
Title: Pseudo-label Alignment for Semi-supervised Instance Segmentation
Authors: Jie Hu, Chen Chen, Liujuan Cao, Shengchuan Zhang, Annan Shu, Guannan Jiang, and Rongrong Ji
Abstract summary: Pseudo-labeling is significant for semi-supervised instance segmentation. In existing pipelines, pseudo-labels that contain valuable information may be filtered out due to mismatches in class and mask quality. We propose a novel framework, called pseudo-label aligning instance segmentation (PAIS), in this paper.
Score: 67.9616087910363
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Pseudo-labeling is significant for semi-supervised instance segmentation, which generates instance masks and classes from unannotated images for subsequent training. However, in existing pipelines, pseudo-labels that contain valuable information may be directly filtered out due to mismatches in class and mask quality. To address this issue, we propose a novel framework, called pseudo-label aligning instance segmentation (PAIS), in this paper. In PAIS, we devise a dynamic aligning loss (DALoss) that adjusts the weights of semi-supervised loss terms with varying class and mask score pairs. Through extensive experiments conducted on the COCO and Cityscapes datasets, we demonstrate that PAIS is a promising framework for semi-supervised instance segmentation, particularly in cases where labeled data is severely limited. Notably, with just 1\% labeled data, PAIS achieves 21.2 mAP (based on Mask-RCNN) and 19.9 mAP (based on K-Net) on the COCO dataset, outperforming the current state-of-the-art model, \ie, NoisyBoundary with 7.7 mAP, by a margin of over 12 points. Code is available at: \url{https://github.com/hujiecpp/PAIS}.

Related papers

SAM as the Guide: Mastering Pseudo-Label Refinement in Semi-Supervised Referring Expression Segmentation [66.92696817276288]
SemiRES is a semi-supervised framework that effectively leverages a combination of labeled and unlabeled data to perform RES. SemiRES incorporates the Segment Anything Model (SAM), renowned for its precise boundary demarcation. In instances where a precise mask cannot be matched from the available candidates, we develop the Pixel-Wise Adjustment (PWA) strategy.
arXiv Detail & Related papers (2024-06-03T15:42:30Z)
Enhancing Weakly Supervised Semantic Segmentation with Multi-modal Foundation Models: An End-to-End Approach [7.012760526318993]
Weakly-Supervised Semantic (WSSS) offers a cost-efficient workaround to extensive labeling. Existing WSSS methods have difficulties in learning the boundaries of objects leading to poor segmentation results. We propose a novel and effective framework that addresses these issues by leveraging visual foundation models inside the bounding box.
arXiv Detail & Related papers (2024-05-10T16:42:25Z)
The Devil is in the Points: Weakly Semi-Supervised Instance Segmentation via Point-Guided Mask Representation [61.027468209465354]
We introduce a novel learning scheme named weakly semi-supervised instance segmentation (WSSIS) with point labels. We propose a method for WSSIS that can effectively leverage the budget-friendly point labels as a powerful weak supervision source. We conduct extensive experiments on COCO and BDD100K datasets, and the proposed method achieves promising results comparable to those of the fully-supervised model.
arXiv Detail & Related papers (2023-03-27T10:11:22Z)
Scene Clustering Based Pseudo-labeling Strategy for Multi-modal Aerial View Object Classification [22.4510980822444]
Fine-grained data, class imbalance and various shooting conditions preclude the representational ability of general image classification. By exploiting these properties, we propose Scene Clustering Based Pseudo-labeling Strategy ( SCP-Label) SCP-Label brings greater accuracy by assigning the same label to objects within the same scene.
arXiv Detail & Related papers (2022-05-04T07:13:01Z)
GuidedMix-Net: Semi-supervised Semantic Segmentation by Using Labeled Images as Reference [90.5402652758316]
We propose a novel method for semi-supervised semantic segmentation named GuidedMix-Net. It uses labeled information to guide the learning of unlabeled instances. It achieves competitive segmentation accuracy and significantly improves the mIoU by +7$%$ compared to previous approaches.
arXiv Detail & Related papers (2021-12-28T06:48:03Z)
LabOR: Labeling Only if Required for Domain Adaptive Semantic Segmentation [79.96052264984469]
We propose a human-in-the-loop approach to adaptively give scarce labels to points that a UDA model is uncertain about. We show the advantages of this new framework for domain adaptive semantic segmentation while minimizing human labor costs.
arXiv Detail & Related papers (2021-08-12T07:35:40Z)
Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigation [30.688753736660725]
We present a simple and yet effective Distribution Alignment and Random Sampling (DARS) method to produce unbiased pseudo labels. Our method performs favorably in comparison with state-of-the-art approaches.
arXiv Detail & Related papers (2021-07-23T14:45:14Z)
Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision [56.950950382415925]
We propose a novel consistency regularization approach, called cross pseudo supervision (CPS) The CPS consistency has two roles: encourage high similarity between the predictions of two perturbed networks for the same input image, and expand training data by using the unlabeled data with pseudo labels. Experiment results show that our approach achieves the state-of-the-art semi-supervised segmentation performance on Cityscapes and PASCAL VOC 2012.
arXiv Detail & Related papers (2021-06-02T15:21:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.