AI Paper Atlas

Research map / Benchmarks / LIP

LIP leaderboard

17 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on LIP. Best mIoU (val): 61.17 (UPerNet+IDRNet, NeurIPS 2023).

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.

LIP · mIoU (val)

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

#mIoU ↑MethodPaperTopic
161.17UPerNet+IDRNet
Swin-Large
IDRNet: Intervention-Driven Relation Network for Semantic Segmentation
NeurIPS 2023 · Table SOTA
CNN features
260.81HIPN(+HL)
HIPN
Hierarchical Information Passing Based Noise-Tolerant Hybrid Learning for Semi-Supervised Human Parsing
AAAI 2021 · Table 5
Semi-supervised learning
360.3CDGNet
CE2P, ResNet-101
CDGNet: Class Distribution Guided Network for Human Parsing
CVPR 2022 · Table: Comparison of different
Recognition and long-tail
459.36A-CE2P w/ SCHP (test-time aug)Self-Correction for Human Parsing
TPAMI 2020 · Table 1
Weakly supervised detection and segmentation
559.25Ours
DeepLabV3
Hierarchical Human Parsing With Typed Part-Relation Reasoning
CVPR 2020 · Table 1
Knowledge and temporal graphs
657.74Ours (compositional neural information fusion)
ResNet101
Learning Compositional Neural Information Fusion for Human Parsing
ICCV 2019 · Table 1
CNN features
756.82BGNetBlended Grammar Network for Human Parsing
ECCV 2020 · Table 4
CNN features
856.65OCR
HRNetV2-W48
Object-Contextual Representations for Semantic Segmentation
ECCV 2020 · Table 5
CNN features
956.35OCNet (w/ ASP-OC)
HRNetV2-W48
OCNet: Object Context for Semantic Segmentation
IJCV 2021 · Table 10
CNN features
1056.34Ours
CE2P
Self-Learning With Rectification Strategy for Human Parsing
CVPR 2020 · Table: Compare with state-of-t
Graph self-supervised learning
7 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.