analiza aiqbench
This research introduces DASA, a framework that enhances semantic segmentation by dynamically allocating data augmentation strength based on multi-factor difficulty metrics like prediction ambiguity and boundary complexity. By moving beyond single-signal adaptation, the method significantly improves model performance across various architectures without requiring architectural changes.
Difficulty-Aware Sample Allocation for Adaptive Data Augmentation in Semantic Segmentation
arXiv:2608.25710v1 Announce Type: cross Abstract: Data augmentation is a standard component of modern semantic segmentation pipelines, but most augmentation techniques allocate transformations uniformly across training samples or adapt to a single difficulty signal such as loss. This ignores the fact that segmentation difficulty is multi-factorial, since ambiguous predictions, persistent optimization errors, rare classes, and complex object boundaries can each make a sample informative in different ways. This paper introduces Difficulty-Aware Sample Allocation (DASA), an architecture-agnostic framework that assigns stronger augmentation to samples estimated to be more difficult. DASA combines prediction ambiguity, training loss, class rarity, and boundary complexity into a normalized difficulty score, then maps that score to sample-specific augmentation strength during iterative training. Experiments on Oxford-IIIT Pet and binary Pascal VOC segmentation with U-Net, DeepLabV3, and SegFormer-B0 show that DASA improves over standard training and is competitive with or stronger than single-signal adaptive baselines. On Oxford-IIIT Pet, DASA improves DeepLabV3 from 0.633 to 0.740 mIoU. On binary Pascal VOC, DASA obtains the best foreground IoU for all three evaluated architectures. These results attest to the value of multi-factor difficulty estimation as a practical mechanism for directing augmentation where it is most useful.
Abstract:Data augmentation is a standard component of modern semantic segmentation pipelines, but most augmentation techniques allocate transformations uniformly across training samples or adapt to a single difficulty signal such as loss. This ignores the fact that segmentation difficulty is multi-factorial, since ambiguous predictions, persistent optimization errors, rare classes, and complex object boundaries can each make a sample informative in different ways. This paper introduces Difficulty-Aware Sample Allocation (DASA), an architecture-agnostic framework that assigns stronger augmentation to samples estimated to be more difficult. DASA combines prediction ambiguity, training loss, class rarity, and boundary complexity into a normalized difficulty score, then maps that score to sample-specific augmentation strength during iterative training. Experiments on Oxford-IIIT Pet and binary Pascal VOC segmentation with U-Net, DeepLabV3, and SegFormer-B0 show that DASA improves over standard training and is competitive with or stronger than single-signal adaptive baselines. On Oxford-IIIT Pet, DASA improves DeepLabV3 from 0.633 to 0.740 mIoU. On binary Pascal VOC, DASA obtains the best foreground IoU for all three evaluated architectures. These results attest to the value of multi-factor difficulty estimation as a practical mechanism for directing augmentation where it is most useful.
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
arXiv:2608.25710 [cs.CV]
(or arXiv:2608.25710v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2608.25710 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 286 cuvinte
Subiecte conexe
SharP: Soft and Hard Prompt-Guided Augmentation with LLM for Low Resource Fake News Detection
arXiv · 12 oct. 2026
CADER: Confidence-Aware Dynamic Evidence Reasoning for Long-Video Understanding
arXiv · 28 iul. 2026
MARS: Margin and Semantic-Aware Data Augmentation for Reward Modeling
arXiv · 7 aug. 2026
Efficient RLVR Scheduling via Graph-Structured Online Difficulty Estimation
arXiv · 20 aug. 2026