Research map / Detection and segmentation / Open-set and few-shot detection
Nereus: A Large-Scale Underwater Dataset for Fine-Grained Attribute Understanding and Grounded Counting Perception
Jingtao Deng, Zihao Jin, Yuehe Chen, Feixiang He, Shuiwang Li, Dan Zeng
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Introduces Nereus, a large-scale underwater dataset aimed at fine-grained attribute understanding and grounded counting perception, motivated by the coarse category labels in existing underwater datasets.
Problem
Existing underwater imagery datasets provide coarse category labels, which do not support recognizing fine-grained biological traits or reasoning over spatially grounded evidence needed for science communication, fishery monitoring, ecological conservation, and oceanographic research.
Approach
A large-scale underwater dataset that annotates fine-grained biological attributes and supports grounded counting, going beyond coarse category labels. Full details unavailable beyond the abstract.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| fine-tune on Nereus instead of NautData | LLaVA-OneVision-7B · Nereus attribute test | overall accuracy (%): 11.27 -> 51.44 | Improved |
| fine-tune on Nereus instead of NautData | InternVL2.5-8B · Nereus attribute test | overall accuracy (%): 15.13 -> 51.88 | Improved |
| fine-tune on Nereus instead of NautData | Qwen2.5-VL-7B · Nereus attribute test | overall accuracy (%): 17.53 -> 46.17 | Improved |
| fine-tune on MarineInst20M instead of zero-shot | InternVL2.5-8B · Nereus attribute test | overall accuracy (%): 13.41 -> 11.67 | Hurt |
| use structured attribute set supervision instead of single-attribute QA pairs (ablation) | Qwen2.5-VL-7B · Nereus attribute test | overall accuracy (%): 39.08 -> 41.55 | Improved |
| use structured attribute set supervision instead of object-level captions (ablation) | Qwen2.5-VL-7B · Nereus attribute test | overall accuracy (%): 16.78 -> 41.55 | Improved |
| add degradation type and level as textual priors (ablation) | Qwen2.5-VL-7B structured SFT · Nereus attribute test | overall accuracy / semantic similarity: Acc 41.55 -> 40.51; Sim 73.10 -> 74.60 | Mixed |
| add DTIUIE image enhancement on top of degradation prior (ablation) | Qwen2.5-VL-7B structured SFT · Nereus attribute test | overall accuracy: 41.55 -> 37.36 | Hurt |
| add count-only SFT (ablation) | InternVL2.5-8B · Nereus counting Track A | MAE: 87.38 -> 31.72 | Improved |
| add region, grid and visibility QA supervision to count-only SFT (QAS) (ablation) | InternVL2.5-8B · Nereus counting Track A | MAE: 31.72 -> 25.99 | Improved |
| add region/grid QA supervision to count-only SFT (ablation) | InternVL2.5-8B · Nereus counting Track A | densest cell accuracy (%): 20.81 -> 52.70 | Improved |
| add Track-B density supervision to QAS (Full) (ablation) | InternVL2.5-8B · Nereus counting Track A | MAE: 25.99 -> 30.48 | Hurt |
Closest papers by meaning
- NAUTILUS: A Large Multimodal Model for Underwater Scene Understanding (NeurIPS 2025 · similarity 0.87)
- Enhancing Vision-Language Models with Morphological and Taxonomic Knowledge: Towards Coral Recognition for Ocean Health (AAAI 2025 · similarity 0.86)
- Fantastic Animals and Where to Find Them: Segment Any Marine Animal with Dual SAM (CVPR 2024 · similarity 0.86)
- CoralVQA: A Large-Scale Visual Question Answering Dataset for Coral Reef Image Understanding (NeurIPS 2025 · similarity 0.85)
- SeafloorAI: A Large-scale Vision-Language Dataset for Seafloor Geological Survey (NeurIPS 2024 · similarity 0.85)
- ReefNet: A Large-Scale Dataset and Benchmark for Fine-Grained Coral Reef Recognition (NeurIPS 2026 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
