| DeRIS: Decoupling Perception and Cognition for Enhanced Referring Image Segmentation through Loopback Synergy | ✓ Link | 77.67 | 72.00 | DeRIS-L | 2025-07-02 |
| Semantic-Spatial Discriminability Enhancement for Generalized Visual Grounding | ✓ Link | 74.83 | 70.09 | SSDE | 2026-08-31 |
| Improving Generalized Visual Grounding with Instance-aware Joint Learning | ✓ Link | 73.36 | 69.22 | InstanceVG | 2025-09-17 |
| PropVG: End-to-End Proposal-Driven Visual Grounding with Multi-Granularity Discrimination | ✓ Link | 73.29 | 69.23 | PropVG | 2025-09-05 |
| UGround: Towards Unified Visual Grounding with Unrolled Transformers | ✓ Link | 72.46 | 65.56 | UGround-LLaVA1.5-7B(ft) | 2025-10-04 |
| GSVA: Generalized Segmentation via Multimodal Large Language Models | ✓ Link | 70.04 | 66.38 | GSVA-Llama2-13B | 2023-12-15 |
| SSP-SAM: SAM with Semantic-Spatial Prompt for Referring Expression Segmentation | | 69.09 | 62.56 | SSP-SAM-336 | 2026-03-18 |
| SSP-SAM: SAM with Semantic-Spatial Prompt for Referring Expression Segmentation | | 68.87 | 61.28 | SSP-SAM-224 | 2026-03-18 |
| Bring Adaptive Binding Prototypes to Generalized Referring Expression Segmentation | ✓ Link | 68.79 | 65.69 | MABP | 2024-05-24 |
| CoHD: A Counting-Aware Hierarchical Decoding Framework for Generalized Referring Expression Segmentation | ✓ Link | 68.28 | 65.42 | HDC | 2024-05-24 |
| GSVA: Generalized Segmentation via Multimodal Large Language Models | ✓ Link | 68.01 | 64.05 | GSVA-Vicuna-13B-v1.1 | 2023-12-15 |
| GROUNDHOG: Grounding Large Language Models to Holistic Segmentation | | 66.70 | | GROUNDHOG | 2024-02-26 |
| GSVA: Generalized Segmentation via Multimodal Large Language Models | ✓ Link | 66.47 | 63.29 | GSVA-Vicuna-7B-v1.1 | 2023-12-15 |
| GRES: Generalized Referring Expression Segmentation | ✓ Link | 63.60 | 62.42 | ReLA | 2023-06-01 |
| GREx: Generalized Referring Expression Segmentation, Comprehension, and Generation | | 61.32 | 61.23 | LAVT+ReLA | 2026-01-08 |
| GREx: Generalized Referring Expression Segmentation, Comprehension, and Generation | | 59.43 | 58.65 | VLT+ReLA | 2026-01-08 |
| LAVT: Language-Aware Vision Transformer for Referring Image Segmentation | ✓ Link | 58.40 | 57.64 | LAVT | 2021-12-04 |
| Train the Agent, Not the Expert: Learning to Harness Heterogeneous Experts for Multi-Turn Visual Reasoning | | 56.80 | 60.60 | VisHarness | 2026-05-28 |
| CRIS: CLIP-Driven Referring Image Segmentation | ✓ Link | 56.27 | 55.34 | CRIS | 2021-11-30 |
| Locate then Segment: A Strong Pipeline for Referring Image Segmentation | | 52.70 | 52.30 | LTS | 2021-03-30 |
| Vision-Language Transformer and Query Generation for Referring Segmentation | ✓ Link | 52.00 | 52.51 | VLT | 2021-08-12 |
| MAttNet: Modular Attention Network for Referring Expression Comprehension | ✓ Link | 48.24 | 47.51 | MattNet | 2018-01-24 |