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.

Models/kNN-CLIP

kNN-CLIP

Reported on 6 benchmarks across 3 tasks · 1 paper · 3 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision3 results

Image ClassificationonSTL-10
Percentage correct· uses extra data· 2022-04-03
99.6
best: 99.64 (µ2Net+ (ViT-L/16))
SOTA
Revisiting a kNN-based Image Classification System with High-capacity Storage arXiv:2204.01186
Image ClassificationonCIFAR-10
Percentage correct· uses extra data· 2022-04-03
97.3
best: 99.5 (ViT-H/14)
Revisiting a kNN-based Image Classification System with High-capacity Storage arXiv:2204.01186
Image ClassificationonCIFAR-100
Percentage correct· uses extra data· 2022-04-03
81.7
best: 96.08 (EffNet-L2 (SAM))
Revisiting a kNN-based Image Classification System with High-capacity Storage arXiv:2204.01186

Methodology3 results

Incremental LearningonImageNet - 10 steps
Average Incremental Accuracy· uses extra data· 2022-04-03
85.5
SOTA
Revisiting a kNN-based Image Classification System with High-capacity Storage arXiv:2204.01186
Incremental LearningonImageNet100 - 10 steps
Average Incremental Accuracy· uses extra data· 2022-04-03
85.1
SOTA
Revisiting a kNN-based Image Classification System with High-capacity Storage arXiv:2204.01186
Continual LearningonCifar100 (20 tasks)
Average Accuracy· uses extra data· 2022-04-03
90.8
best: 94.99 (Model Zoo-Continual)
Revisiting a kNN-based Image Classification System with High-capacity Storage arXiv:2204.01186