← Back to all news
arXiv Computer Vision By Jialin Li, Jinkun Jiang, Yuezun Li, Junyu Dong

Progressively Refining SAM for Accurate Phytoplankton Segmentation

Read the original on arXiv Computer Vision →

The paper introduces PhySeg, a SAM-based segmentation framework that uses a lightweight refinement module to progressively restore fine-grained details via multi-scale feature fusion, improving phytoplankton segmentation accuracy. It also presents a newly annotated phytoplankton dataset with instance-level masks, offering a valuable resource for future research. Experimental results confirm the effectiveness of the proposed module, and the code is publicly available on GitHub.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Machine Learning
Aug 19

Leveraging existing sparse point annotations for benthic imagery dense segmentation

The paper presents a method that leverages sparse expert point annotations from historical benthic surveys to improve dense segmentation of marine imagery. By using these points as visual prompts for the SAM2 foundation model and introducing a mechanism to filter out unreliable points, the authors generate high‑quality pseudo‑ground‑truth masks that train more accurate fine‑grained semantic segmentation models. The approach is validated on public benthic datasets and a new benchmark featuring real‑world sparse annotations, aiming to enable scalable ecological analysis.

By Cesar Borja, Breck A. McCollum, Jarret E. Byrnes, Kenneth Sebens, Ana C. Murillo
computer-visionbenchmarks
More like this →
arXiv Computer Vision
Sep 14

CoralscapesV2: Panoptic and Fine-Grained Visual Scene Understanding in Coral Reefs

CoralscapesV2 is an expanded dataset for coral reef visual scene understanding, increasing the number of fine‑grained classes from 39 to 95 and adding 65,000 exhaustive fish instance masks. It supports panoptic segmentation by providing high‑quality semantic and instance labels across diverse, unconstrained reef imagery. The dataset serves as a challenging benchmark for modern segmentation models and enables broader applications such as benthic cover mapping and automated fish‑reef interaction analysis.

By Jonathan Sauder, Thomas Ruckli, Gabriel\.e Strodomskyt\.e, Ibrahim Souleiman Abdallah, Rahma Hassan Abdi, Djama Goumaneh Awaleh, Mohamed Houssein Farah, Moustapha Nour, Osama Sharhubil Saad, Mustafa Mohammed Khalafallah Altaib, Maysoon Kteifan, Farah Alsoqi, Eyad Zgool, Jafar Al-Omari, Temesgen Gebremeskel Gebreluel, Zekaria Zekeria Abdulkerim, Meron Ghirmay, Teklehaimanot Beraki, Devis Tuia, Guilhem Banc-Prandi
computer-visionroboticsbenchmarks
More like this →
arXiv Computer Vision
Oct 22

GuidedSAM-Plume: An Expert-Guided Segmentation Framework for Volcanic Plumes

GuidedSAM‑Plume is an open‑source, expert‑guided framework that enhances the interactive segmentation of volcanic plumes and clouds using the zero‑shot, spatial prompt‑based capabilities of SAM2. It was validated on a challenging dataset with dedicated segmentation metrics and volcanological descriptors, showing that minimal user input can significantly improve performance over fully automatic solutions while maintaining reliable derived parameters. The framework requires no retraining, lowering adoption barriers, and its re‑annotated dataset, produced under expert guidance, offers a more standardized release for broader environmental science applications.

By Taddeo D'Adamo (LIRIS, imagine), Simon Thivet (UNIGE), Catherine Pothier (LIRIS, imagine), Riccardo Simionato (UNIGE), Allan Fries (UNIGE), Jonathan Lemus (UNIGE), Costanza Bonadonna (UNIGE), Laure Tougne Rodet (LIRIS, imagine), Bertrand Kerautret (LIRIS, imagine)
computer-vision
More like this →