# CoRef-DETR: Decoupled Global Context and Selective Boundary-Category Refinement for Underwater Instance Segmentation

arXiv: https://arxiv.org/abs/2606.08002 · HTML: https://mlsanity.com/paper/2606.08002/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 32 references that are in the map.
- First posted on arXiv 6 Jun 2026.

## Builds on (most cited first, 29 of 29)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [DETRs Beat YOLOs on Real-time Object Detection](https://mlsanity.com/paper/2304.08069/) (2023)
- [YOLACT: Real-time Instance Segmentation](https://mlsanity.com/paper/1904.02689/) (2019)
- [PointRend: Image Segmentation as Rendering](https://mlsanity.com/paper/1912.08193/) (2019)
- [Conditional Convolutions for Instance Segmentation](https://mlsanity.com/paper/2003.05664/) (2020)
- [SOLO: Segmenting Objects by Locations](https://mlsanity.com/paper/1912.04488/) (2019)
- [Mask Scoring R-CNN](https://mlsanity.com/paper/1903.00241/) (2019)
- [EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything](https://mlsanity.com/paper/2312.00863/) (2023)
- [Instances as Queries](https://mlsanity.com/paper/2105.01928/) (2021)
- [RF-DETR: Neural Architecture Search for Real-Time Detection Transformers](https://mlsanity.com/paper/2511.09554/) (2025)
- [Boundary-preserving Mask R-CNN](https://mlsanity.com/paper/2007.08921/) (2020)
- [Sparse Instance Activation for Real-Time Instance Segmentation](https://mlsanity.com/paper/2203.12827/) (2022)
- [Diving into Underwater: Segment Anything Model Guided Underwater Salient Instance Segmentation and A Large-scale Dataset](https://mlsanity.com/paper/2406.06039/) (2024)
- [USIS16K: High-Quality Dataset for Underwater Salient Instance Segmentation](https://mlsanity.com/paper/2506.19472/) (2025)
- [Empowering DINO Representations for Underwater Instance Segmentation via Aligner and Prompter](https://mlsanity.com/paper/2511.08334/) (2025)
- [UIS-Mamba: Exploring Mamba for Underwater Instance Segmentation via Dynamic Tree Scan and Hidden State Weaken](https://mlsanity.com/paper/2508.00421/) (2025)
- [Advancing Marine Research: UWSAM Framework and UIIS10K Dataset for Precise Underwater Instance Segmentation](https://mlsanity.com/paper/2505.15581/) (2025)
- [USIS-PGM: Photometric Gaussian Mixtures for Underwater Salient Instance Segmentation](https://mlsanity.com/paper/2603.13961/) (2026)

## Abstract (arXiv)

Underwater instance segmentation supports marine surveys, aquaculture, and underwater robotics. Haze, colour casts, and low contrast blur object boundaries, and recent benchmarks distinguish up to 158 fine-grained categories. The strongest published methods mostly have 219 to 632 million parameters. This paper proposes CoRef-DETR, a compact detection transformer that targets three error sources of a real-time detector: context, boundaries, and categories. First, a decoupled global context (DGC) detector, with the base detector's 33.4 M parameters, applies global self-attention to a 384-pixel token grid but supervises and decodes masks in a 576-pixel frame. Second, a posterior-conditioned boundary refiner with 47.7 k parameters corrects mask logits on predicted boundaries, and a quality score on the corrected masks re-ranks the detections. Third, a crop-probe category branch on frozen DINOv2 features revises the categories of at most three masks per image, where a rule fixed on validation data chooses soft fusion or a confident-disagreement gate. On five protocols of UIIS, UIIS10K, USIS10K, and USIS16K, CoRef-DETR achieves state-of-the-art mask average precision (AP), exceeding the strongest published results by 2.3 to 5.2 points, and outperforms three reproduced recent methods on the same test images (on USIS16K, with its category branch). In half precision with TensorRT, it processes an image in a median of 34 to 40 ms, JPEG decoding included, on a T4 GPU, 1.4 to 11 times faster than these methods. Ablations attribute most of DGC's gain to the larger frame; an error analysis locates the remaining error in crowds of small objects.