Leveraging existing sparse point annotations for benthic imagery dense segmentation

• URL: http://arxiv.org/abs/2608.17561v1
• Date: Tue, 18 Aug 2026 09:22:31 GMT
• Title: Leveraging existing sparse point annotations for benthic imagery dense segmentation
• Abstract summary: We bridge state-of-the-art foundation models with existing sparse supervision.<n>Our primary contribution is a novel mechanism to automatically identify which of these points are suitable, and which are actively harmful, when used for propagation.<n>We demonstrate the effectiveness of our approach on public benthic data and introduce a new, challenging benchmark featuring real-world sparse expert annotations, paving the way for scalable ecological analysis.
• Score: 4.264200809234798
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The health of marine ecosystems is a critical indicator of global environmental change, yet the physical constraints of underwater observation and the intrinsic challenges of processing marine imagery severely limit the scalability of systematic monitoring. While recent visual foundation models such as the Segment Anything Model (SAM) series show great promise, they still struggle with the fine-grained recognition required in these complex scenarios and still require expert supervision. Our work addresses this gap by bridging state-of-the-art foundation models with existing sparse supervision. Because historical benthic surveys are typically annotated with only a few sparse expert points per image, we utilize these legacy point-labels as visual prompts for SAM2. Our primary contribution is a novel mechanism to automatically identify which of these points are suitable, and which are actively harmful, when used for propagation. By filtering out unreliable points, we extract high-quality pseudo-ground-truth masks capable of training more accurate, fine-grained semantic segmentation models. We demonstrate the effectiveness of our approach on public benthic data and introduce a new, challenging benchmark featuring real-world sparse expert annotations, paving the way for scalable ecological analysis.

Related papers

• Domain-Guided Prompting of the Segment Anything Model for Seismic Interpretation: The Role of Attributes, Visualization, and Hybrid Prompts [0.1529342790344802]
  We introduce a principled framework for zero shot adaptation of foundation models to seismic data.<n>The framework is built on two key components: (1) aligning seismic attributes and visualization choices with the geological target of interest, and (2) employing a hybrid prompting strategy.<n>Our results demonstrate that geologic target aware selection of seismic attributes and colormaps, combined with hybrid prompting, enhances the separability of geological features.
  arXiv  Detail & Related papers  (2026-06-14T12:40:02Z)
• Real-time Appearance-based Gaze Estimation for Open Domains [15.195617974731766]
  We propose a robust AGE framework that enhances generalization without requiring additional human-annotated data.<n>To mitigate the impact of anisotropic inter-dataset label deviation, we reformulate gaze regression as a multi-task learning problem.<n>Our MobileNet-based lightweight model generalization achieves performance competitive with the state-of-the-art (SOTA) UniGaze-H.
  arXiv  Detail & Related papers  (2026-03-27T19:33:18Z)
• Harmonizing the Deep: A Unified Information Pipeline for Robust Marine Biodiversity Assessment Across Heterogeneous Domains [0.769971486557519]
  This work establishes the foundational detection layer for a multi-year invasive species monitoring initiative targeting Arctic and Atlantic marine ecosystems.<n>We develop a Unified Information Pipeline that standardises heterogeneous datasets into a comparable information flow.<n>We find that structural factors, such as scene composition, object density, and contextual redundancy, explain cross-domain performance loss.
  arXiv  Detail & Related papers  (2026-01-20T13:51:55Z)
• Wetland mapping from sparse annotations with satellite image time series and temporal-aware segment anything model [37.47356246646521]
  We propose WetSAM, a framework that integrates satellite image time series for wetland mapping from sparse point supervision through a dual-branch design.<n>We show that WetSAM substantially outperforms state-of-the-art methods, achieving an average F1-score of 85.58%, and delivering accurate and structurally consistent wetland segmentation with minimal labeling effort.
  arXiv  Detail & Related papers  (2026-01-16T16:10:32Z)
• Expose Camouflage in the Water: Underwater Camouflaged Instance Segmentation and Dataset [76.92197418745822]
  camouflaged instance segmentation (CIS) faces greater challenges in accurately segmenting objects that blend closely with their surroundings.<n>Traditional camouflaged instance segmentation methods, trained on terrestrial-dominated datasets with limited underwater samples, may exhibit inadequate performance in underwater scenes.<n>We introduce the first underwater camouflaged instance segmentation dataset, UCIS4K, which comprises 3,953 images of camouflaged marine organisms with instance-level annotations.
  arXiv  Detail & Related papers  (2025-10-20T14:34:51Z)
• MARIS: Marine Open-Vocabulary Instance Segmentation with Geometric Enhancement and Semantic Alignment [56.88334234553316]
  We introduce textbfMARIS (underlineMarine Open-Vocabulary underlineInstance underlineSegmentation), the first large-scale fine-grained benchmark for underwater Open-Vocabulary (OV) segmentation.<n>Our framework consistently outperforms existing OV baselines both In-Domain and Cross-Domain setting.
  arXiv  Detail & Related papers  (2025-10-17T07:50:58Z)
• ConformalSAM: Unlocking the Potential of Foundational Segmentation Models in Semi-Supervised Semantic Segmentation with Conformal Prediction [57.930531826380836]
  This work explores whether a foundational segmentation model can address label scarcity in the pixel-level vision task as an annotator for unlabeled images.<n>We propose ConformalSAM, a novel SSSS framework which first calibrates the foundation model using the target domain's labeled data and then filters out unreliable pixel labels of unlabeled data.
  arXiv  Detail & Related papers  (2025-07-21T17:02:57Z)
• Real-time Seafloor Segmentation and Mapping [0.0]
  Posidonia oceanica meadows are a species of seagrass highly dependent on rocks for their survival and conservation.<n>Deep learning-based semantic segmentation and visual automated monitoring systems have shown promise in a variety of applications.<n>This paper introduces a framework that combines machine learning and computer vision techniques to enable an autonomous underwater vehicle (AUV) to inspect the boundaries of Posidonia oceanica meadows autonomously.
  arXiv  Detail & Related papers  (2025-04-14T22:49:08Z)
• Robust Saliency-Aware Distillation for Few-shot Fine-grained Visual Recognition [57.08108545219043]
  Recognizing novel sub-categories with scarce samples is an essential and challenging research topic in computer vision. Existing literature addresses this challenge by employing local-based representation approaches. This article proposes a novel model, Robust Saliency-aware Distillation (RSaD), for few-shot fine-grained visual recognition.
  arXiv  Detail & Related papers  (2023-05-12T00:13:17Z)
• Toward Certified Robustness Against Real-World Distribution Shifts [65.66374339500025]
  We train a generative model to learn perturbations from data and define specifications with respect to the output of the learned model. A unique challenge arising from this setting is that existing verifiers cannot tightly approximate sigmoid activations. We propose a general meta-algorithm for handling sigmoid activations which leverages classical notions of counter-example-guided abstraction refinement.
  arXiv  Detail & Related papers  (2022-06-08T04:09:13Z)
• Robust and Precise Facial Landmark Detection by Self-Calibrated Pose Attention Network [73.56802915291917]
  We propose a semi-supervised framework to achieve more robust and precise facial landmark detection. A Boundary-Aware Landmark Intensity (BALI) field is proposed to model more effective facial shape constraints. A Self-Calibrated Pose Attention (SCPA) model is designed to provide a self-learned objective function that enforces intermediate supervision.
  arXiv  Detail & Related papers  (2021-12-23T02:51:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.