TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/Efficient Self-Ensemble for Semantic Segmentation

Efficient Self-Ensemble for Semantic Segmentation

Walid Bousselham, Guillaume Thibault, Lucas Pagano, Archana Machireddy, Joe Gray, Young Hwan Chang, Xubo Song

2021-11-26arXiv 2021 11SegmentationSemantic Segmentation
PaperPDFCode(official)

Abstract

Ensemble of predictions is known to perform better than individual predictions taken separately. However, for tasks that require heavy computational resources, e.g. semantic segmentation, creating an ensemble of learners that needs to be trained separately is hardly tractable. In this work, we propose to leverage the performance boost offered by ensemble methods to enhance the semantic segmentation, while avoiding the traditional heavy training cost of the ensemble. Our self-ensemble approach takes advantage of the multi-scale features set produced by feature pyramid network methods to feed independent decoders, thus creating an ensemble within a single model. Similar to the ensemble, the final prediction is the aggregation of the prediction made by each learner. In contrast to previous works, our model can be trained end-to-end, alleviating the traditional cumbersome multi-stage training of ensembles. Our self-ensemble approach outperforms the current state-of-the-art on the benchmark datasets Pascal Context and COCO-Stuff-10K for semantic segmentation and is competitive on ADE20K and Cityscapes. Code is publicly available at github.com/WalBouss/SenFormer.

Results

TaskDatasetMetricValueModel
Semantic SegmentationADE20K valmIoU57.1SenFormer (BEiT-L)
Semantic SegmentationADE20K valmIoU54.2SenFormer (Swin-L)
Semantic SegmentationPASCAL ContextmIoU64SenFormer (Swin-L)
Semantic SegmentationPASCAL ContextmIoU56.6SenFormer (ResNet-101)
Semantic SegmentationADE20KValidation mIoU57.1SenFormer (BEiT-L)
Semantic SegmentationADE20KValidation mIoU54.2SenFormer (Swin-L)
10-shot image generationADE20K valmIoU57.1SenFormer (BEiT-L)
10-shot image generationADE20K valmIoU54.2SenFormer (Swin-L)
10-shot image generationPASCAL ContextmIoU64SenFormer (Swin-L)
10-shot image generationPASCAL ContextmIoU56.6SenFormer (ResNet-101)
10-shot image generationADE20KValidation mIoU57.1SenFormer (BEiT-L)
10-shot image generationADE20KValidation mIoU54.2SenFormer (Swin-L)

Related Papers

SeC: Advancing Complex Video Object Segmentation via Progressive Concept Construction2025-07-21Deep Learning-Based Fetal Lung Segmentation from Diffusion-weighted MRI Images and Lung Maturity Evaluation for Fetal Growth Restriction2025-07-17DiffOSeg: Omni Medical Image Segmentation via Multi-Expert Collaboration Diffusion Model2025-07-17From Variability To Accuracy: Conditional Bernoulli Diffusion Models with Consensus-Driven Correction for Thin Structure Segmentation2025-07-17Unleashing Vision Foundation Models for Coronary Artery Segmentation: Parallel ViT-CNN Encoding and Variational Fusion2025-07-17SCORE: Scene Context Matters in Open-Vocabulary Remote Sensing Instance Segmentation2025-07-17Unified Medical Image Segmentation with State Space Modeling Snake2025-07-17A Privacy-Preserving Semantic-Segmentation Method Using Domain-Adaptation Technique2025-07-17