AI Paper Atlas

Research map / Benchmarks / Places365

Places365 leaderboard

32 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on Places365. Best accuracy: 65.1 (Ours, CVPR 2024).

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.

Places365 · accuracy

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

#accuracy ↑MethodPaperTopic
165.1OursOmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning
CVPR 2024 · Table 1
Cross-modal learning
261.3LoSA with backbone output
ViT-g
Time- Memory- and Parameter-Efficient Visual Adaptation
CVPR 2024 · Table 6
Pruning and efficient tuning
360.3MAE ViT-H 448
ViT-H
Masked Autoencoders Are Scalable Vision Learners
CVPR 2022 · Transfer learning classificati
Attention and transformers
460.1OmniMAE ViT-H
ViT-H
OmniMAE: Single Model Masked Pretraining on Images and Videos
CVPR 2023 · Table: Comparing OmniMAE with
Video segmentation and tracking
559.9Omnivore (Swin-L, higher resolution)
Swin-L
Omnivore: A Single Model for Many Visual Modalities
CVPR 2022 · Table: image classification fi
Cross-modal learning
659MixMAE
Swin-B/W14
MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers
CVPR 2023 · Classification transfer table
Attention and transformers
756.69TopViT, ReLU, exp, t=1, synced
ViT-B/16
Fast Tree-Field Integrators: From Low Displacement Rank to Topological Transformers
NeurIPS 2024 · Topological Vision Transformer
Graph algorithms and clustering
855.21Scene EssenceScene Essence
CVPR 2021 · Table 8
Open-set and few-shot detection
955.13OTF-CBM (ours)
DINOv2 ViT-L/14
Bridging Vision and Language Concepts through Optimal Transport Semantic Flow
ECCV 2026 · Table 2
Optimal transport
1055.1DN-CBM
CLIP ViT-B/16
Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery
ECCV 2024 · Table 1
Recognition and long-tail
22 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.