paper-with-me

Referring Expression Segmentation 벤치마크

Referring Expression Segmentation on RefCOCO+ testA

60개 결과 · ⬇ CSV · JSON

Overall IoU

47.6 56.58 65.55 74.53 83.5 2018-01 2026-11 MattNet — 52.39 (2018-01-24) MattNet — 52.39 (2018-01-24) CMSA — 47.6 (2019-04-09) CMSA — 47.6 (2019-04-09) STEP (5-fold) — 52.33 (2019-10-01) STEP (5-fold) — 52.33 (2019-10-01) BRINet — 52.87 (2020-06-01) BRINet — 52.87 (2020-06-01) CPMC — 53.44 (2020-10-01) RefVOS with BERT + MLM Loss — 49.73 (2020-10-01) CPMC — 53.44 (2020-10-01) RefVOS with BERT + MLM Loss — 49.73 (2020-10-01) SHNet — 58.46 (2021-04-21) SHNet — 58.46 (2021-04-21) VLT — 59.2 (2021-08-12) VLT — 59.2 (2021-08-12) MaIL — 65.92 (2021-11-21) MaIL — 65.92 (2021-11-21) CRIS — 68.08 (2021-11-30) CRIS — 68.08 (2021-11-30) LAVT — 68.38 (2021-12-04) LAVT — 68.38 (2021-12-04) VLT — 68.43 (2022-10-28) VLT — 68.43 (2022-10-28) PolyFormer-L — 74.56 (2023-02-14) PolyFormer-B — 72.89 (2023-02-14) PolyFormer-L — 74.56 (2023-02-14) PolyFormer-B — 72.89 (2023-02-14) UNINEXT-H — 76.42 (2023-03-12) UNINEXT-H — 76.42 (2023-03-12) ReLA — 71.02 (2023-06-01) ReLA — 71.02 (2023-06-01) UniLSeg-100 — 78.29 (2023-12-04) UniLSeg-20 — 77.02 (2023-12-04) UniLSeg-100 — 78.29 (2023-12-04) UniLSeg-20 — 77.02 (2023-12-04) MagNet — 71.32 (2023-12-19) MagNet — 71.32 (2023-12-19) GROUNDHOG — 75.0 (2024-02-26) GROUNDHOG — 75.0 (2024-02-26) EVF-SAM — 80.0 (2024-06-28) EVF-SAM — 80.0 (2024-06-28) SafaRi-B — 74.53 (2024-07-02) SafaRi-B — 74.53 (2024-07-02) MLCD-Seg-7B — 82.9 (2024-07-24) MLCD-Seg-7B — 82.9 (2024-07-24) HyperSeg — 83.5 (2024-11-26) HyperSeg — 83.5 (2024-11-26) MaskRIS (Swin-B, combined DB) — 75.15 (2024-11-28) MaskRIS (Swin-B) — 74.46 (2024-11-28) MaskRIS (Swin-B, combined DB) — 75.15 (2024-11-28) MaskRIS (Swin-B) — 74.46 (2024-11-28) C3VG — 77.96 (2025-01-12) C3VG — 77.96 (2025-01-12) DETRIS — 78.6 (2025-01-15) DETRIS — 78.6 (2025-01-15) DeRIS-L — 82.34 (2025-07-02) DeRIS-L — 82.34 (2025-07-02) MattNet — 52.39 (2018-01-24) BRINet — 52.87 (2020-06-01) CPMC — 53.44 (2020-10-01) SHNet — 58.46 (2021-04-21) VLT — 59.2 (2021-08-12) MaIL — 65.92 (2021-11-21) CRIS — 68.08 (2021-11-30) LAVT — 68.38 (2021-12-04) VLT — 68.43 (2022-10-28) PolyFormer-L — 74.56 (2023-02-14) UNINEXT-H — 76.42 (2023-03-12) UniLSeg-100 — 78.29 (2023-12-04) EVF-SAM — 80.0 (2024-06-28) MLCD-Seg-7B — 82.9 (2024-07-24) HyperSeg — 83.5 (2024-11-26)
RankModel Overall IoUMean IoUmIoU Extra Training Data PaperCodeYear
1 HyperSeg 83.5–– ✓ HyperSeg: Towards Universal Visual Segmentation with Large Language Model congvvc/HyperSeg 2024
2 MLCD-Seg-7B 82.9–– ✓ Multi-label Cluster Discrimination for Visual Representation Learning deepglint/unicom 2024
3 DeRIS-L 82.3483.74– DeRIS: Decoupling Perception and Cognition for Enhanced Referring Image Segmentation through Loopback Synergy Dmmm1997/DeRIS 2025
4 EVF-SAM 80–– ✓ EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model hustvl/evf-sam 2024
5 DETRIS 78.6–– Densely Connected Parameter-Efficient Tuning for Referring Image Segmentation jiaqihuang01/detris 2025
6 UniLSeg-100 78.29–– ✓ Universal Segmentation at Arbitrary Granularity with Language Instruction yongliu20/UniLSeg · workforai/UniLSeg 2023
7 C3VG 77.96–– Multi-task Visual Grounding with Coarse-to-Fine Consistency Constraints dmmm1997/c3vg 2025
8 UniLSeg-20 77.02–– ✓ Universal Segmentation at Arbitrary Granularity with Language Instruction yongliu20/UniLSeg · workforai/UniLSeg 2023
9 UNINEXT-H 76.42–– ✓ Universal Instance Perception as Object Discovery and Retrieval MasterBin-IIAU/UNINEXT 2023
10 MaskRIS (Swin-B, combined DB) 75.15–– MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation naver-ai/maskris 2024
11 GROUNDHOG 75.0–– ✓ GROUNDHOG: Grounding Large Language Models to Holistic Segmentation 2024
12 PolyFormer-L 74.5675.71– ✓ PolyFormer: Referring Image Segmentation as Sequential Polygon Generation amazon-science/polygon-transformer 2023
13 SafaRi-B 74.53–– SafaRi:Adaptive Sequence Transformer for Weakly Supervised Referring Expression Segmentation 2024
14 MaskRIS (Swin-B) 74.4676.73– MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation naver-ai/maskris 2024
15 PolyFormer-B 72.8974.51– ✓ PolyFormer: Referring Image Segmentation as Sequential Polygon Generation amazon-science/polygon-transformer 2023
16 MagNet 71.32–– Mask Grounding for Referring Image Segmentation yxchng/mask-grounding 2023
17 ReLA 71.02–– GRES: Generalized Referring Expression Segmentation henghuiding/ReLA · henghuiding/grefcoco 2023
18 VLT 68.43–– VLT: Vision-Language Transformer and Query Generation for Referring Segmentation henghuiding/Vision-Language-Transformer 2022
19 LAVT 68.38–– LAVT: Language-Aware Vision Transformer for Referring Image Segmentation yz93/lavt-ris 2021
20 CRIS 68.08–– CRIS: CLIP-Driven Referring Image Segmentation DerrickWang005/CRIS.pytorch 2021
1–20 / 60 다음 → 페이지당 10 20 50 100