Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Datasets/ImageNet-100 (GCD split)

ImageNet-100 (GCD split)

Introduced 2022-01-07

This ImageNet-100 dataset was introduced in the following paper,

Vaze, S., Han, K., Vedaldi, A. and Zisserman, A., 2022. Generalized category discovery. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 7492-7501).

Related Benchmarks

ImageNet-100 (Class-IL, 5T)/Image Classification/Top 1 Accuracy ImageNet-100 (TEMI Split)/Image Classification/All accuracy (10% Labeled)ImageNet-100 (TEMI Split)/Image Classification/All accuracy (50% Labeled)ImageNet-100 (TEMI Split)/Image Classification/Novel accuracy (10% Labeled)ImageNet-100 (TEMI Split)/Image Classification/Novel accuracy (50% Labeled)ImageNet-100 (TEMI Split)/Image Classification/Params ImageNet-100 (TEMI Split)/Image Classification/Percentage correct ImageNet-100 (TEMI Split)/Image Classification/Seen accuracy (10% Labeled)ImageNet-100 (TEMI Split)/Image Classification/Seen accuracy (50% Labeled)ImageNet-100 (TEMI Split)/Image Clustering/ACCURACY ImageNet-100 (TEMI Split)/Image Clustering/ARI ImageNet-100 (TEMI Split)/Image Clustering/NMI ImageNet-100 (TEMI Split)/Self-Supervised Learning/Top-1 Accuracy ImageNet-100 (TEMI Split)/Semi-Supervised Image Classification/All accuracy (10% Labeled)ImageNet-100 (TEMI Split)/Semi-Supervised Image Classification/All accuracy (50% Labeled)ImageNet-100 (TEMI Split)/Semi-Supervised Image Classification/Novel accuracy (10% Labeled)ImageNet-100 (TEMI Split)/Semi-Supervised Image Classification/Novel accuracy (50% Labeled)ImageNet-100 (TEMI Split)/Semi-Supervised Image Classification/Seen accuracy (10% Labeled)ImageNet-100 (TEMI Split)/Semi-Supervised Image Classification/Seen accuracy (50% Labeled)ImageNet-100 - 50 classes + 10 steps of 5 classes/Incremental Learning/Average Incremental Accuracy ImageNet-100 - 50 classes + 25 steps of 2 classes/Incremental Learning/Average Incremental Accuracy ImageNet-100 - 50 classes + 5 steps of 10 classes/Incremental Learning/Average Incremental Accuracy ImageNet-100 - 50 classes + 5 steps of 10 classes/Object Localization/Average Top-1 localization accuracy ImageNet-100 - 50 classes + 50 steps of 1 class/Incremental Learning/Average Incremental Accuracy

Statistics

Papers: 2
Benchmarks: 0

Links