AI Paper Atlas

Research map / Benchmarks / PASCAL-Person-Part

PASCAL-Person-Part leaderboard

14 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on PASCAL-Person-Part. Best mIoU: 74.96 (SST (Transfer-ATR&CIHP), CVPR 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.

PASCAL-Person-Part · mIoU

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

#mIoU ↑MethodPaperTopic
174.96SST (Transfer-ATR&CIHP)
ResNet-101
Semantic Human Parsing via Scalable Semantic Transfer Over Multiple Label Domains
CVPR 2023 · Table 1
Recognition and long-tail
274.59PCNet
ResNet-101
Part-Aware Context Network for Human Parsing
CVPR 2020 · Table 3
CNN features
373.12Ours
DeepLabV3
Hierarchical Human Parsing With Typed Part-Relation Reasoning
CVPR 2020 · Table 2
Knowledge and temporal graphs
471.65Grapy-ML
DeepLab v3+
Grapy-ML: Graph Pyramid Mutual Learning for Cross-Dataset Human Parsing
AAAI 2020 · Main results table
Knowledge and temporal graphs
571.14Graphonomy (CIHP)Graphonomy: Universal Image Parsing via Graph Reasoning and Transfer
TPAMI 2020 · Table 1
Knowledge and temporal graphs
671.14Graphonomy (CIHP)
DeepLab v3+
Graphonomy: Universal Human Parsing via Graph Transfer Learning
CVPR 2019 · Table 1
Graph self-supervised learning
770.76Ours (compositional neural information fusion)
ResNet101
Learning Compositional Neural Information Fusion for Human Parsing
ICCV 2019 · Table 3
CNN features
868.6Ours (single scale)
ResNeXt-101
Dense Decoder Shortcut Connections for Single-Pass Semantic Segmentation
CVPR 2018 · Table 7
CNN features
967.6Ours (ResNet-101, +ms)
ResNet-101
Weakly and Semi Supervised Human Body Part Parsing via Pose-Guided Knowledge Transfer
CVPR 2018 · Table: Comparison of semantic
Weakly supervised detection and segmentation
1064.94DeepLab ResNet-101 + MSC + COCO + Aug + CRF
ResNet-101
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
TPAMI 2017 · Table 8
CNN features
4 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.