ORCA: Object Recognition and Comprehension for Archiving Marine Species

• URL: http://arxiv.org/abs/2512.21150v1
• Date: Wed, 24 Dec 2025 12:36:57 GMT
• Title: ORCA: Object Recognition and Comprehension for Archiving Marine Species
• Abstract summary: ORCA is a multi-modal benchmark for marine research comprising 14,647 images from 478 species.<n>The dataset provides fine-grained visual and textual annotations that capture morphology-oriented attributes across diverse marine species.<n>Results highlight key challenges, including species diversity, morphological overlap, and specialized domain demands.
• Score: 19.88077587860992
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Marine visual understanding is essential for monitoring and protecting marine ecosystems, enabling automatic and scalable biological surveys. However, progress is hindered by limited training data and the lack of a systematic task formulation that aligns domain-specific marine challenges with well-defined computer vision tasks, thereby limiting effective model application. To address this gap, we present ORCA, a multi-modal benchmark for marine research comprising 14,647 images from 478 species, with 42,217 bounding box annotations and 22,321 expert-verified instance captions. The dataset provides fine-grained visual and textual annotations that capture morphology-oriented attributes across diverse marine species. To catalyze methodological advances, we evaluate 18 state-of-the-art models on three tasks: object detection (closed-set and open-vocabulary), instance captioning, and visual grounding. Results highlight key challenges, including species diversity, morphological overlap, and specialized domain demands, underscoring the difficulty of marine understanding. ORCA thus establishes a comprehensive benchmark to advance research in marine domain. Project Page: http://orca.hkustvgd.com/.

Related papers

• Leveraging existing sparse point annotations for benthic imagery dense segmentation [4.264200809234798]
  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.
  arXiv  Detail & Related papers  (2026-08-18T09:22:31Z)
• OceanPile: A Large-Scale Multimodal Ocean Corpus for Foundation Models [57.19693589926157]
  OceanPile is a large-scale multimodal corpus designed for ocean foundation models.<n>It comprises three key components: OceanCorpus, OceanInstruction, and OceanBenchmark.<n>All datasets are publicly released to advance the field of marine artificial intelligence.
  arXiv  Detail & Related papers  (2026-04-25T14:53:37Z)
• WUTDet: A 100K-Scale Ship Detection Dataset and Benchmarks with Dense Small Objects [68.44670476527155]
  WUTDet is a large-scale ship detection dataset with 100,576 images and 381,378 annotated ship instances.<n>We systematically evaluate 20 baseline models from three mainstream detection architectures, namely CNN, Transformer, and Mamba.<n>Results on Ship-GEN show that models trained on WUTDet exhibit stronger generalization under different data distributions.
  arXiv  Detail & Related papers  (2026-04-09T03:28:05Z)
• UWBench: A Comprehensive Vision-Language Benchmark for Underwater Understanding [54.16709436340606]
  Large vision-language models (VLMs) have achieved remarkable success in natural scene understanding.<n>Underwater imagery presents unique challenges including severe light attenuation, color distortion, and suspended particle scattering.<n>We introduce UWBench, a benchmark specifically designed for underwater vision-language understanding.
  arXiv  Detail & Related papers  (2025-10-21T03:32:15Z)
• 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)
• Neptune-X: Active X-to-Maritime Generation for Universal Maritime Object Detection [54.1960918379255]
  Neptune-X is a data-centric generative-selection framework for maritime object detection.<n>X-to-Maritime is a multi-modality-conditioned generative model that synthesizes diverse and realistic maritime scenes.<n>Our approach sets a new benchmark in maritime scene synthesis, significantly improving detection accuracy.
  arXiv  Detail & Related papers  (2025-09-25T04:59:02Z)
• Tree-Mamba: A Tree-Aware Mamba for Underwater Monocular Depth Estimation [85.17735565146106]
  Underwater Monocular Depth Estimation (UMDE) is a critical task that aims to estimate high-precision depth maps from underwater degraded images.<n>We develop a novel tree-aware Mamba method, dubbed Tree-Mamba, for estimating accurate monocular depth maps from underwater degraded images.<n>We construct an underwater depth estimation benchmark (called BlueDepth), which consists of 38,162 underwater image pairs with reliable depth labels.
  arXiv  Detail & Related papers  (2025-07-10T12:10:51Z)
• Marine Saliency Segmenter: Object-Focused Conditional Diffusion with Region-Level Semantic Knowledge Distillation [44.50637633194709]
  Marine Saliency (MSS) plays a pivotal role in various vision-based marine exploration tasks.<n>We propose DiffMSS, a novel marine saliency segmenter based on the diffusion model.<n>We develop the dedicated deterministic consensus sampling to suppress overconfident missegmentations.
  arXiv  Detail & Related papers  (2025-04-03T08:31:36Z)
• Reducing Label Dependency for Underwater Scene Understanding: A Survey of Datasets, Techniques and Applications [3.4210271593052606]
  Survey focuses on approaches which reduce dependency on human expert input. We provide background on weakly and self-supervised deep learning and integrate these elements into a taxonomy that centres on the intersection of underwater monitoring, computer vision, and deep learning.
  arXiv  Detail & Related papers  (2024-11-18T05:16:09Z)
• WhaleNet: a Novel Deep Learning Architecture for Marine Mammals Vocalizations on Watkins Marine Mammal Sound Database [49.1574468325115]
  We introduce textbfWhaleNet (Wavelet Highly Adaptive Learning Ensemble Network), a sophisticated deep ensemble architecture for the classification of marine mammal vocalizations. We achieve an improvement in classification accuracy by $8-10%$ over existing architectures, corresponding to a classification accuracy of $97.61%$.
  arXiv  Detail & Related papers  (2024-02-20T11:36:23Z)
• MarineDet: Towards Open-Marine Object Detection [13.58409623192008]
  Open-marine object detection (OMOD for short) is required to detect diverse and unseen marine objects, performing categorization and localization simultaneously. We formulate a joint visual-text semantic space through pre-training and then perform marine-specific training to achieve in-air-to-marine knowledge transfer. experimental results demonstrate the superior performance of MarineDet over existing generalist and specialist object detection algorithms.
  arXiv  Detail & Related papers  (2023-10-03T10:13:42Z)
• Weakly supervised marine animal detection from remote sensing images using vector-quantized variational autoencoder [4.812718493682454]
  This paper studies a reconstruction-based approach for weakly-supervised animal detection from aerial images in marine environments. An anomaly detection framework computes metrics directly on the input space, enhancing interpretability and anomaly localization. Our framework offers improved interpretability and localization of anomalies, providing valuable insights for monitoring marine ecosystems.
  arXiv  Detail & Related papers  (2023-07-13T12:26:27Z)
• 1st Workshop on Maritime Computer Vision (MaCVi) 2023: Challenge Results [152.54137779547068]
  This report summarizes the main findings of the individual subchallenges and introduces a new benchmark, called SeaDronesSee Object Detection v2. The datasets, evaluation code and the leaderboard are publicly available at https://seadronessee.cs.uni-tuebingen.de/macvi.
  arXiv  Detail & Related papers  (2022-11-24T09:59:13Z)

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.