Pith. sign in

REVIEW 5 cited by

Adversarial Learning for Semi-Supervised Semantic Segmentation

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1802.07934 v2 pith:6PMKXTCL submitted 2018-02-22 cs.CV

Wei-Chih Hung , Yi-Hsuan Tsai , Yan-Ting Liou , Yen-Yu Lin , Ming-Hsuan Yang This is my paper · ORCID
classification cs.CV
keywords segmentationimagesadversarialdiscriminatorproposedsemanticsemi-supervisedconvolutional
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We propose a method for semi-supervised semantic segmentation using an adversarial network. While most existing discriminators are trained to classify input images as real or fake on the image level, we design a discriminator in a fully convolutional manner to differentiate the predicted probability maps from the ground truth segmentation distribution with the consideration of the spatial resolution. We show that the proposed discriminator can be used to improve semantic segmentation accuracy by coupling the adversarial loss with the standard cross entropy loss of the proposed model. In addition, the fully convolutional discriminator enables semi-supervised learning through discovering the trustworthy regions in predicted results of unlabeled images, thereby providing additional supervisory signals. In contrast to existing methods that utilize weakly-labeled images, our method leverages unlabeled images to enhance the segmentation model. Experimental results on the PASCAL VOC 2012 and Cityscapes datasets demonstrate the effectiveness of the proposed algorithm.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Ensemble Foreground Management for Unsupervised Object Discovery

    cs.CV 2025-07 conditional novelty 6.0 of 10

    UnionCut and its distilled version UnionSeg detect the union of foreground regions in images and, when used as a prior, boost the performance of several unsupervised object discovery methods.

  2. MATCH: Multi-faceted Adaptive Topo-Consistency for Semi-Supervised Histopathology Segmentation

    cs.CV 2025-10 conditional novelty 5.0 of 10

    MATCH cuts topological segmentation errors in semi-supervised histopathology by matching 0-D components across MC-dropout and temporal predictions and enforcing consistency on them.

  3. Rethinking Semi-supervised Segmentation Beyond Accuracy: Reliability and Robustness

    cs.CV 2025-06 conditional novelty 5.0 of 10

    A new harmonic-mean metric, RSS, combines mIoU, calibration error, and two uncertainty-quality measures, and is used to show that SSL segmentation models like UniMatchV2 sacrifice reliability for accuracy.

  4. Multimodal Prototype Alignment for Semi-supervised Pathology Image Segmentation

    cs.CV 2025-08 conditional novelty 4.0 of 10

    MPAMatch combines a UNI-based encoder, UniMatch-style consistency, and image/text prototype contrastive losses to improve semi-supervised pathology segmentation, reporting state-of-the-art results on four public datasets.

  5. To GAN or Not To GAN: Segmentation Analysis on Mars DEM

    cs.LG 2026-06 unverdicted novelty 2.0 of 10

    GAN-augmented semantic segmentation does not outperform standard supervised segmentation for mound detection on Mars DEMs.

Pith tools