Papers › The GIST and RIST of Iterative Self-Training for Semi-Supervised Segmentation

The GIST and RIST of Iterative Self-Training for Semi-Supervised Segmentation

31 Mar 2021arXiv:2103.17105archive 2025-07-28

Eu Wern Teh, Terrance DeVries, Brendan Duke, Ruowei Jiang, Parham Aarabi, Graham W. Taylor

We consider the task of semi-supervised semantic segmentation, where we aim to produce pixel-wise semantic object masks given only a small number of human-labeled training examples. We focus on iterative self-training methods in which we explore the behavior of self-training over multiple refinement stages. We show that iterative self-training leads to performance degradation if done na\"ively with a fixed ratio of human-labeled to pseudo-labeled training examples. We propose Greedy Iterative Self-Training (GIST) and Random Iterative Self-Training (RIST) strategies that alternate between training on either human-labeled data or pseudo-labeled data at each refinement stage, resulting in a performance boost rather than degradation. We further show that GIST and RIST can be combined with existing semi-supervised learning methods to boost performance.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Semantic SegmentationSemi-Supervised Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semi-Supervised Semantic Segmentation Cityscapes 100 samples labeled GIST and RIST (DeepLabv2 with ResNet101, MSCOCO pre-trained) Validation mIoU 58.70% #8 of 13 Archive leaderboard report
Semi-Supervised Semantic Segmentation Cityscapes 12.5% labeled GIST and RIST (DeepLabv2 with ResNet101, MSCOCO pre-trained) Validation mIoU 62.57% #29 of 33 Archive leaderboard report
Semi-Supervised Semantic Segmentation Cityscapes 2% labeled GIST and RIST (DeepLabv2 with ResNet101, MSCOCO pre-trained) Validation mIoU 53.51% #1 of 3 Archive leaderboard report
Semi-Supervised Semantic Segmentation Cityscapes 25% labeled GIST and RIST (DeepLabv2 with ResNet101, MSCOCO pre-trained) Validation mIoU 65.14% #26 of 30 Archive leaderboard report
Semi-Supervised Semantic Segmentation Cityscapes 5% labeled GIST and RIST (DeepLabv2 with ResNet101, MSCOCO pre-trained) Validation mIoU 59.98% #1 of 3 Archive leaderboard report
Semi-Supervised Semantic Segmentation Pascal VOC 2012 12.5% labeled GIST and RIST Validation mIoU 70.76% #32 of 38 Archive leaderboard report
Semi-Supervised Semantic Segmentation Pascal VOC 2012 2% labeled GIST and RIST (DeepLabv2 with ResNet101, MSCOCO pre-trained) Validation mIoU 67.21% #3 of 12 Archive leaderboard report
Semi-Supervised Semantic Segmentation Pascal VOC 2012 5% labeled GIST and RIST (DeepLabv2 with ResNet101, MSCOCO pre-trained) Validation mIoU 69.40% #7 of 14 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections