Metraipolis › archive › dc_bcaf3b9ea283
An active-learning framework for real-time depth perception from monocular vision streams — arXiv:2608.04917
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.04917
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T11:48:14.693Z
- SHA-256 of the archived text
eeeafd022ef67f923a1b8a1398caa04b004e6677a952902efdedc05e4ba80abb- Stable URL of this page
https://metraipolis.com/documento/dc_bcaf3b9ea283
How to cite
An active-learning framework for real-time depth perception from monocular vision streams — arXiv:2608.04917 — arXiv (en), https://arxiv.org/abs/2608.04917 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bcaf3b9ea283 (Metraipolis archive dc_bcaf3b9ea283, sha256 eeeafd022ef67f923a1b8a1398caa04b004e6677a952902efdedc05e4ba80abb)
BibTeX
@misc{dcbcaf3b9ea283,
title = {An active-learning framework for real-time depth perception from monocular vision streams — arXiv:2608.04917},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.04917},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bcaf3b9ea283; sha256 eeeafd022ef67f923a1b8a1398caa04b004e6677a952902efdedc05e4ba80abb},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04917. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Biological visual systems can perceive depth from monocular vision flow, continuously integrating temporal visual cues while maintaining a balance between stability and plasticity in dynamic environments. In contrast, artificial perception models deployed on resource-constrained edge devices are typically trained in a static offline manner and remain frozen after deployment, often suffering severe performance degradation under domain shifts. While large-scale models may encode broad knowledge through massive parameter redundancy, lightweight networks face a static optimization dilemma: forcing compact models to learn universal geometric representations is computationally inefficient and often leads to performance saturation. To resolve this issue, an Online Active Learning (OAL) mechanism is introduced to endow compact neural networks with the capability to adapt continuously during operation. A closed-loop Predict-Evaluate-Correct learning paradigm is established to actively select high-confidence, information-rich signals from streaming visual input. Crucially, Elastic Weight Consolidation (EWC) is employed not merely to prevent catastrophic forgetting, but to enforce Selective Plasticity, preserving parameters that encode globally relevant structural knowledge while allowing local alignment to newly observed environments. Built upon a MobileNetV3-Small backbone, the proposed system achieves approximately a 75% reduction in computational cost while maintaining competitive depth estimation accuracy. Experimental results demonstrate that adaptability is not solely determined by model size, but rather by how effectively parameter plasticity is regulated in dynamic environments. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-06 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.04917 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-31T11:37:40.730Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).