paper-with-me

Referring Expression Segmentation 벤치마크

Referring Expression Segmentation on RefCOCO testB

26개 결과 · ⬇ CSV · JSON

Overall IoU

64.12 68.94 73.76 78.58 83.4 2022-03 2026-11 SeqTR — 64.12 (2022-03-30) SeqTR — 64.12 (2022-03-30) EVP — 72.94 (2023-12-13) EVP — 72.94 (2023-12-13) MagNet — 71.05 (2023-12-19) MagNet — 71.05 (2023-12-19) EVF-SAM — 80.2 (2024-06-28) EVF-SAM — 80.2 (2024-06-28) SafaRi — 70.71 (2024-07-02) SafaRi — 70.71 (2024-07-02) MLCD-Seg-7B — 81.5 (2024-07-24) MLCD-Seg-7B — 81.5 (2024-07-24) HyperSeg — 83.4 (2024-11-26) HyperSeg — 83.4 (2024-11-26) MaskRIS (Swin-B, combined DB) — 75.1 (2024-11-28) MaskRIS (Swin-B) — 73.96 (2024-11-28) MaskRIS (Swin-B, combined DB) — 75.1 (2024-11-28) MaskRIS (Swin-B) — 73.96 (2024-11-28) C3VG — 77.86 (2025-01-12) C3VG — 77.86 (2025-01-12) DETRIS — 79.0 (2025-01-15) DETRIS — 79.0 (2025-01-15) DeRIS-L — 82.87 (2025-07-02) DeRIS-L — 82.87 (2025-07-02) SeqTR — 64.12 (2022-03-30) EVP — 72.94 (2023-12-13) EVF-SAM — 80.2 (2024-06-28) MLCD-Seg-7B — 81.5 (2024-07-24) HyperSeg — 83.4 (2024-11-26)
RankModel Overall IoUmIoUMean IoU Extra Training Data PaperCodeYear
1 HyperSeg 83.4–– ✓ HyperSeg: Towards Universal Visual Segmentation with Large Language Model congvvc/HyperSeg 2024
2 DeRIS-L 82.87–84.52 DeRIS: Decoupling Perception and Cognition for Enhanced Referring Image Segmentation through Loopback Synergy Dmmm1997/DeRIS 2025
3 MLCD-Seg-7B 81.5–– ✓ Multi-label Cluster Discrimination for Visual Representation Learning deepglint/unicom 2024
4 EVF-SAM 80.2–– ✓ EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model hustvl/evf-sam 2024
5 DETRIS 79.0–– Densely Connected Parameter-Efficient Tuning for Referring Image Segmentation jiaqihuang01/detris 2025
6 C3VG 77.86–– Multi-task Visual Grounding with Coarse-to-Fine Consistency Constraints dmmm1997/c3vg 2025
7 MaskRIS (Swin-B, combined DB) 75.1–– MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation naver-ai/maskris 2024
8 MaskRIS (Swin-B) 73.96–76.06 MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation naver-ai/maskris 2024
9 EVP 72.94–– EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment lavreniuk/evp 2023
10 MagNet 71.05–– Mask Grounding for Referring Image Segmentation yxchng/mask-grounding 2023
11 SafaRi 70.71–– SafaRi:Adaptive Sequence Transformer for Weakly Supervised Referring Expression Segmentation 2024
12 SeqTR 64.12–– SeqTR: A Simple yet Universal Network for Visual Grounding seanzhuh/seqtr · sean-zhuh/seqtr · luogen1996/simrec 2022
13 VATEX –75.64– Vision-Aware Text Features in Referring Image Segmentation: From Object Understanding to Context Understanding nero1342/VATEX 2024
14 HyperSeg 83.4–– ✓ HyperSeg: Towards Universal Visual Segmentation with Large Language Model congvvc/HyperSeg 2024
15 DeRIS-L 82.87–84.52 DeRIS: Decoupling Perception and Cognition for Enhanced Referring Image Segmentation through Loopback Synergy Dmmm1997/DeRIS 2025
16 MLCD-Seg-7B 81.5–– ✓ Multi-label Cluster Discrimination for Visual Representation Learning deepglint/unicom 2024
17 EVF-SAM 80.2–– ✓ EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model hustvl/evf-sam 2024
18 DETRIS 79.0–– Densely Connected Parameter-Efficient Tuning for Referring Image Segmentation jiaqihuang01/detris 2025
19 C3VG 77.86–– Multi-task Visual Grounding with Coarse-to-Fine Consistency Constraints dmmm1997/c3vg 2025
20 MaskRIS (Swin-B, combined DB) 75.1–– MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation naver-ai/maskris 2024
1–20 / 26 다음 → 페이지당 10 20 50 100