AI Paper Atlas

Research map / Benchmarks / MS COCO 2014

MS COCO 2014 leaderboard

35 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on MS COCO 2014. Best mIoU (val): 56.7 (ModuSeg, ECCV 2026).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

MS COCO 2014 · mIoU (val)

35 papers, each with its best reported number for its own method; higher is better.

#mIoU ↑MethodPaperTopic
156.7ModuSegModuSeg: Decoupling Object Discovery and Semantic Retrieval for Training-Free Weakly Supervised Segmentation
ECCV 2026 · Table 1
Weakly supervised detection and segmentation
254.1CD-CLIP (Ours)
CLIP ViT-B/16
Leveraging Class Distributions in CLIP for Weakly Supervised Semantic Segmentation
CVPR 2026 · Table 2
Weakly supervised detection and segmentation
351.5DFA
CLIP ViT-B/16
Frequency-Aware Affinity for Weakly Supervised Semantic Segmentation
CVPR 2026 · Table 2
Weakly supervised detection and segmentation
451.4VDA
ViT-B (CLIP)
Beyond Text: Visual Description Assembly by Probabilistic Model for CLIP-based Weakly Supervised Semantic Segmentation
CVPR 2026 · Table 1
Open-set and few-shot detection
549.8CLIP-CPAL + VPL
CLIP
Toward Modality Gap: Vision Prototype Learning for Weakly-supervised Semantic Segmentation with CLIP
AAAI 2025 · Table 2
Cross-modal learning
649.8S2C
WRN38
From SAM to CAMs: Exploring Segment Anything Model for Weakly Supervised Semantic Segmentation
CVPR 2024 · Table 4
Weakly supervised detection and segmentation
749.4MARS (Ours)
ResNet-101
MARS: Model-agnostic Biased Object Removal without Additional Supervision for Weakly-Supervised Semantic Segmentation
ICCV 2023 · Table 1
Weakly supervised detection and segmentation
847.9CLIP-ES + Ours
CLIP-ES
POT: Prototypical Optimal Transport for Weakly Supervised Semantic Segmentation
CVPR 2025 · Table 2
Weakly supervised detection and segmentation
947.2PCRE
ViT-B/16
Weakly Supervised Semantic Segmentation via Progressive Confidence Region Expansion
CVPR 2025 · Table 2
Weakly supervised detection and segmentation
1047.2CLIP-ES + PSDPM
CLIP-ES
PSDPM: Prototype-based Secondary Discriminative Pixels Mining for Weakly Supervised Semantic Segmentation
CVPR 2024 · Table 3
Weakly supervised detection and segmentation
25 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.