AI Paper Atlas

Research map / Benchmarks / MIT67

MIT67 leaderboard

24 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on MIT67. Best accuracy: 98.58 (TANSR, AAAI 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.

MIT67 · accuracy

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

#accuracy ↑MethodPaperTopic
198.58TANSR
ViT-B
Topology-Aware Vision Transformers for Enhanced Scene Recognition
AAAI 2026 · Table 1
Graph self-supervised learning
289.3TAFT-1
ViT-L/16
Tangent Transformers for Composition,Privacy and Removal
ICLR 2024 · Table 1
Pruning and efficient tuning
386.2Deep PT
ViT-B/16
A-La-Carte Prompt Tuning (APT): Combining Distinct Data via Composable Prompting
CVPR 2023 · Table: Finetuning vs. Prompt T
Pruning and efficient tuning
484.69CLDL-VGGNet-(11/16/11)Collaborative Layer-Wise Discriminative Learning in Deep Neural Networks
ECCV 2016 · Table 4
CNN design
584.3Places VGGnet + Spectral FeaturesScene Categorization With Spectral Features
ICCV 2017 · Table 1
CNN features
683.92Scene EssenceScene Essence
CVPR 2021 · Table 1
Open-set and few-shot detection
783.7Unsupervised parts, Hungarian sBOP, K=100
VD16 Places205
Unsupervised Part Learning for Visual Recognition
CVPR 2017 · Table 6
Recognition and long-tail
880.2CNN + attention + affinity supervision
ResNet101
Affinity Graph Supervision for Visual Recognition
CVPR 2020 · Table: MIT67 Scene Categorizat
Knowledge and temporal graphs
979.5HSCFVC
VGG-19
Compositional Model Based Fisher Vector Coding for Image Classification
TPAMI 2017 · Table 2
CNN design
1079.3WA-CNN
AlexNet
Growing a Brain: Fine-Tuning by Increasing Model Capacity
CVPR 2017 · Table 8
Pruning and efficient tuning
14 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.