Pith. sign in

REVIEW 8 cited by

Loss Functions in the Era of Semantic Segmentation: A Survey and Outlook

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 2312.05391 v1 pith:ZF22POCL submitted 2023-12-08 cs.CV

Reza Azad , Moein Heidary , Kadir Yilmaz , Michael Hüttemann , Sanaz Karimijafarbigloo , Yuli Wu , Anke Schmeink , Dorit Merhof This is my paper
classification cs.CV
keywords lossfunctionsimagesegmentationreviewidentifyingparticularperformance
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Semantic image segmentation, the process of classifying each pixel in an image into a particular class, plays an important role in many visual understanding systems. As the predominant criterion for evaluating the performance of statistical models, loss functions are crucial for shaping the development of deep learning-based segmentation algorithms and improving their overall performance. To aid researchers in identifying the optimal loss function for their particular application, this survey provides a comprehensive and unified review of $25$ loss functions utilized in image segmentation. We provide a novel taxonomy and thorough review of how these loss functions are customized and leveraged in image segmentation, with a systematic categorization emphasizing their significant features and applications. Furthermore, to evaluate the efficacy of these methods in real-world scenarios, we propose unbiased evaluations of some distinct and renowned loss functions on established medical and natural image datasets. We conclude this review by identifying current challenges and unveiling future research opportunities. Finally, we have compiled the reviewed studies that have open-source implementations on our GitHub page.

Discussion (0). Sign in to comment.

Forward citations

Cited by 8 Pith papers

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

  1. AG-TAL: Anatomically-Guided Topology-Aware Loss for Multiclass Segmentation of the Circle of Willis Using Large-Scale Multi-Center Datasets

    cs.LG 2026-04 conditional novelty 7.0 of 10

    AG-TAL loss improves multiclass Circle of Willis segmentation to 80.85% average Dice with 1-3% gains on small arteries across multi-center datasets by embedding anatomical priors into topology-aware terms.

  2. MonoUNet: A Robust Tiny Neural Network for Automated Knee Cartilage Segmentation on Point-of-Care Ultrasound Devices

    eess.IV 2026-04 conditional novelty 6.0 of 10

    MonoUNet achieves 92.62-94.82% Dice and 0.133-0.254 mm MASD on multi-device knee cartilage ultrasound while using 10-700x fewer parameters than prior lightweight models by adding a trainable monogenic phase block and ...

  3. MonoUNet: A Robust Tiny Neural Network for Automated Knee Cartilage Segmentation on Point-of-Care Ultrasound Devices

    eess.IV 2026-04 unverdicted novelty 6.0 of 10

    MonoUNet is a tiny segmentation network that achieves 92-95% Dice scores on multi-device knee cartilage ultrasound while using 10-700x fewer parameters than prior lightweight models by injecting trainable local phase ...

  4. Sapiens2

    cs.CV 2026-04 unverdicted novelty 5.0 of 10

    Sapiens2 improves pretraining, data scale, and architecture over its predecessor to set new state-of-the-art results on human pose estimation, body-part segmentation, normal estimation, and new tasks like pointmap and...

  5. MambaLiteUNet: Cross-Gated Adaptive Feature Fusion for Robust Skin Lesion Segmentation

    cs.CV 2026-04 unverdicted novelty 5.0 of 10

    MambaLiteUNet integrates Mamba into U-Net with adaptive fusion, local-global mixing, and cross-gated attention modules to reach 87.12% IoU and 93.09% Dice on skin lesion datasets while cutting parameters by 93.6%.

  6. A drone-based framework for coral habitat mapping via weakly supervised segmentation

    cs.CV 2025-08 unverdicted novelty 5.0 of 10

    A multi-scale weakly supervised framework converts underwater point classifications into coarse masks to train UAV coral segmentation models, then refines them via self-training to reach 86.07% pixel accuracy and 52.2...

  7. Mapping Tomato Cropping Systems in California Using AlphaEarth Geospatial Embeddings and Deep Learning Analysis

    eess.IV 2026-05 unverdicted novelty 4.0 of 10

    A U-Net segmentation model trained on 64-band AlphaEarth embedding chips achieves 99.19% pixel accuracy and 99.04% F1 on an independent test set for distinguishing tomato from non-tomato fields in California.

  8. An Uncertainty-Aware Loss Function Incorporating Fuzzy Logic: Application to MRI Brain Image Segmentation

    cs.CV 2026-04 unverdicted novelty 4.0 of 10

    A loss function merging categorical cross-entropy with fuzzy entropy yields better segmentation metrics than standard cross-entropy on IBSR and OASIS brain MRI datasets using U-Net and U-Net++.

Pith tools