Places-LT

Dataset Information
Modalities
Images
Introduced
2019
License
Unknown
Homepage
Official Website
Contents

Overview

Places-LT has an imbalanced training set with 62,500 images for 365 classes from Places-2. The class frequencies follow a natural power law distribution with a maximum number of 4,980 images per class and a minimum number of 5 images per class. The validation and testing sets are balanced and contain 20 and 100 images per class respectively.

Source: Long-Tailed Recognition Using Class-Balanced Experts

Variants: Places-LT

Associated Benchmarks

This dataset is used in 1 benchmark:

Recent Benchmark Submissions

Task Model Paper Date
Long-tail Learning APA (SE-ResNet-50) Adaptive Parametric Activation 2024-07-11
Long-tail Learning LIFT (ViT-L/14) Long-Tail Learning with Foundation Model: … 2023-09-18
Long-tail Learning LIFT (ViT-B/16) Long-Tail Learning with Foundation Model: … 2023-09-18
Long-tail Learning MAM (ViT-B/16) Improving Image Recognition by Retrieving … 2023-04-11
Long-tail Learning GPaCo (ResNet-152) Generalized Parametric Contrastive Learning 2022-09-26
Long-tail Learning Difficulty-Net (ResNet-152) Difficulty-Net: Learning to Predict Difficulty … 2022-09-07
Long-tail Learning NCL(ResNet-152) Nested Collaborative Learning for Long-Tailed … 2022-03-29
Long-tail Learning RAC (ViT-B-16) Retrieval Augmented Classification for Long-Tail … 2022-02-22
Long-tail Learning OPeN (ResNet-152) Pure Noise to the Rescue … 2021-12-16
Long-tail Learning BALLAD(ResNet-50×16) A Simple Long-Tailed Recognition Baseline … 2021-11-29
Long-tail Learning BALLAD(ResNet-101) A Simple Long-Tailed Recognition Baseline … 2021-11-29
Long-tail Learning BALLAD(ResNet-50) A Simple Long-Tailed Recognition Baseline … 2021-11-29
Long-tail Learning BALLAD(ViT-B-16) A Simple Long-Tailed Recognition Baseline … 2021-11-29
Long-tail Learning VL-LTR (ResNet-50) VL-LTR: Learning Class-wise Visual-Linguistic Representation … 2021-11-26
Long-tail Learning VL-LTR (ViT-B-16) VL-LTR: Learning Class-wise Visual-Linguistic Representation … 2021-11-26
Long-tail Learning PaCo Parametric Contrastive Learning 2021-07-26
Long-tail Learning TADE Self-Supervised Aggregation of Diverse Experts … 2021-07-20
Long-tail Learning LDAM-DRS-RSG RSG: A Simple but Effective … 2021-06-18
Long-tail Learning DisAlign Distribution Alignment: A Unified Framework … 2021-03-30
Long-tail Learning LADE Disentangling Label Distribution for Long-tailed … 2020-12-01

Research Papers

Recent papers with results on this dataset:

External Links: