# Low-shot Image Classification on Places 205 (k-shot evaluation) Source: [Low-shot Image Classification on Places 205 (k-shot evaluation)]() Collection index: [llms.txt]() Data updated: 2026-02-27T06:30:53.952Z Evaluation of few-shot learning performance on the Places 205 dataset, measured by accuracy across various shot counts (k=1, 2, 4, 8, 16). A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Low-shot Image Classification | | Dataset (including any stated split) | Places 205 | | Metric | Accuracy (k=1) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 9 of 9 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Accuracy (k=1)](): Higher is better; unit: PERCENT. - [Accuracy (k=2)](): Higher is better; unit: PERCENT. - [Accuracy (k=4)](): Higher is better; unit: PERCENT. - [Accuracy (k=8)](): Higher is better; unit: PERCENT. - [Accuracy (k=16)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy (k=1) | Result date | Report paper | | --- | --- | --- | --- | | MoPro | 22.2 | Not recorded | 68fa684f1e209131cea1b57f | | CE | 21.8 | Not recorded | 68fa684f1e209131cea1b57f | | MoPro | 16.9 | Not recorded | 68fa684f1e209131cea1b57f | | CE | 15.1 | Not recorded | 68fa684f1e209131cea1b57f | | MoPro | 15 | Not recorded | 68fa684f1e209131cea1b57f | | CE (Sup.) | 14.9 | Not recorded | 68fa684f1e209131cea1b57f | | CE | 13.5 | Not recorded | 68fa684f1e209131cea1b57f | | PCL v2\* | 12.5 | Not recorded | 68fa684f1e209131cea1b57f | | MoCo v2\* | 11.9 | Not recorded | 68fa684f1e209131cea1b57f | ### MoPro Accuracy (k=1): 22.2. Result ID: 69a13a0435dfcabb00e59ebe. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pretrain dataset":"WebVision-V2.0","Classifier":"Linear SVM","Feature type":"Fixed representation"}. This record does not assert independent reproduction. ### CE Accuracy (k=1): 21.8. Result ID: 69a13a0435dfcabb00e59ebd. [Reporting paper]() Recorded evaluation configuration: {"Pretrain dataset":"WebVision-V2.0","Classifier":"Linear SVM","Feature type":"Fixed representation"}. This record does not assert independent reproduction. ### MoPro Accuracy (k=1): 16.9. Result ID: 69a13a0435dfcabb00e59ebc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pretrain dataset":"WebVision-V1.0","Classifier":"Linear SVM","Feature type":"Fixed representation"}. This record does not assert independent reproduction. ### CE Accuracy (k=1): 15.1. Result ID: 69a13a0435dfcabb00e59ebb. [Reporting paper]() Recorded evaluation configuration: {"Pretrain dataset":"WebVision-V1.0","Classifier":"Linear SVM","Feature type":"Fixed representation"}. This record does not assert independent reproduction. ### MoPro Accuracy (k=1): 15. Result ID: 69a13a0435dfcabb00e59eba. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pretrain dataset":"WebVision-V0.5","Classifier":"Linear SVM","Feature type":"Fixed representation"}. This record does not assert independent reproduction. ### CE (Sup.) Accuracy (k=1): 14.9. Result ID: 69a13a0435dfcabb00e59eb8. [Reporting paper]() Recorded evaluation configuration: {"Pretrain dataset":"ImageNet","Classifier":"Linear SVM","Feature type":"Fixed representation"}. This record does not assert independent reproduction. ### CE Accuracy (k=1): 13.5. Result ID: 69a13a0435dfcabb00e59eb9. [Reporting paper]() Recorded evaluation configuration: {"Pretrain dataset":"WebVision-V0.5","Classifier":"Linear SVM","Feature type":"Fixed representation"}. This record does not assert independent reproduction. ### PCL v2\* Accuracy (k=1): 12.5. Result ID: 69a13a0435dfcabb00e59eb7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pretrain dataset":"ImageNet","Classifier":"Linear SVM","Feature type":"Fixed representation"}. This record does not assert independent reproduction. ### MoCo v2\* Accuracy (k=1): 11.9. Result ID: 69a13a0435dfcabb00e59eb6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pretrain dataset":"ImageNet","Classifier":"Linear SVM","Feature type":"Fixed representation"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.