{"task":"Small Data Image Classification","dataset":"DEIC Benchmark","metric_names":["Average Balanced Accuracy (across datasets)"],"rows":[{"id":71905,"task":"Small Data Image Classification","parent_task":"Image Classification","dataset":"DEIC Benchmark","model_name":"Harmonic Networks","metrics":{"Average Balanced Accuracy (across datasets)":"68.70"},"paper_url":"https://arxiv.org/abs/2108.13122v1","paper_title":"Tune It or Don't Use It: Benchmarking Data-Efficient Image Classification","paper_date":"2021-08-30","code_links":[{"title":"cvjena/deic","url":"https://github.com/cvjena/deic"}],"metrics_order":"[\"Average Balanced Accuracy (across datasets)\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":71906,"task":"Small Data Image Classification","parent_task":"Image Classification","dataset":"DEIC Benchmark","model_name":"Cross-Entropy baseline","metrics":{"Average Balanced Accuracy (across datasets)":"67.90"},"paper_url":"https://arxiv.org/abs/2108.13122v1","paper_title":"Tune It or Don't Use It: Benchmarking Data-Efficient Image Classification","paper_date":"2021-08-30","code_links":[{"title":"cvjena/deic","url":"https://github.com/cvjena/deic"}],"metrics_order":"[\"Average Balanced Accuracy (across datasets)\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":71907,"task":"Small Data Image Classification","parent_task":"Image Classification","dataset":"DEIC Benchmark","model_name":"Cosine + Cross-Entropy Loss","metrics":{"Average Balanced Accuracy (across datasets)":"64.92"},"paper_url":"https://arxiv.org/abs/2108.13122v1","paper_title":"Tune It or Don't Use It: Benchmarking Data-Efficient Image Classification","paper_date":"2021-08-30","code_links":[{"title":"cvjena/deic","url":"https://github.com/cvjena/deic"}],"metrics_order":"[\"Average Balanced Accuracy (across datasets)\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":71908,"task":"Small Data Image Classification","parent_task":"Image Classification","dataset":"DEIC Benchmark","model_name":"T-vMF Similarity","metrics":{"Average Balanced Accuracy (across datasets)":"64.67"},"paper_url":"https://arxiv.org/abs/2108.13122v1","paper_title":"Tune It or Don't Use It: Benchmarking Data-Efficient Image Classification","paper_date":"2021-08-30","code_links":[{"title":"cvjena/deic","url":"https://github.com/cvjena/deic"}],"metrics_order":"[\"Average Balanced Accuracy (across datasets)\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":71909,"task":"Small Data Image Classification","parent_task":"Image Classification","dataset":"DEIC Benchmark","model_name":"DSK Networks","metrics":{"Average Balanced Accuracy (across datasets)":"64.64"},"paper_url":"https://arxiv.org/abs/2108.13122v1","paper_title":"Tune It or Don't Use It: Benchmarking Data-Efficient Image Classification","paper_date":"2021-08-30","code_links":[{"title":"cvjena/deic","url":"https://github.com/cvjena/deic"}],"metrics_order":"[\"Average Balanced Accuracy (across datasets)\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":71910,"task":"Small Data Image Classification","parent_task":"Image Classification","dataset":"DEIC Benchmark","model_name":"OLÉ","metrics":{"Average Balanced Accuracy (across datasets)":"64.15"},"paper_url":"https://arxiv.org/abs/2108.13122v1","paper_title":"Tune It or Don't Use It: Benchmarking Data-Efficient Image Classification","paper_date":"2021-08-30","code_links":[{"title":"cvjena/deic","url":"https://github.com/cvjena/deic"}],"metrics_order":"[\"Average Balanced Accuracy (across datasets)\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":71911,"task":"Small Data Image Classification","parent_task":"Image Classification","dataset":"DEIC Benchmark","model_name":"Cosine Loss","metrics":{"Average Balanced Accuracy (across datasets)":"62.73"},"paper_url":"https://arxiv.org/abs/2108.13122v1","paper_title":"Tune It or Don't Use It: Benchmarking Data-Efficient Image Classification","paper_date":"2021-08-30","code_links":[{"title":"cvjena/deic","url":"https://github.com/cvjena/deic"}],"metrics_order":"[\"Average Balanced Accuracy (across datasets)\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":71912,"task":"Small Data Image Classification","parent_task":"Image Classification","dataset":"DEIC Benchmark","model_name":"Full Convolution","metrics":{"Average Balanced Accuracy (across datasets)":"62.06"},"paper_url":"https://arxiv.org/abs/2108.13122v1","paper_title":"Tune It or Don't Use It: Benchmarking Data-Efficient Image Classification","paper_date":"2021-08-30","code_links":[{"title":"cvjena/deic","url":"https://github.com/cvjena/deic"}],"metrics_order":"[\"Average Balanced Accuracy (across datasets)\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":71913,"task":"Small Data Image Classification","parent_task":"Image Classification","dataset":"DEIC Benchmark","model_name":"Deep Hybrid Networks","metrics":{"Average Balanced Accuracy (across datasets)":"60.33"},"paper_url":"https://arxiv.org/abs/2108.13122v1","paper_title":"Tune It or Don't Use It: Benchmarking Data-Efficient Image Classification","paper_date":"2021-08-30","code_links":[{"title":"cvjena/deic","url":"https://github.com/cvjena/deic"}],"metrics_order":"[\"Average Balanced Accuracy (across datasets)\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":71914,"task":"Small Data Image Classification","parent_task":"Image Classification","dataset":"DEIC Benchmark","model_name":"Grad-l2 Penalty","metrics":{"Average Balanced Accuracy (across datasets)":"55.47"},"paper_url":"https://arxiv.org/abs/2108.13122v1","paper_title":"Tune It or Don't Use It: Benchmarking Data-Efficient Image Classification","paper_date":"2021-08-30","code_links":[{"title":"cvjena/deic","url":"https://github.com/cvjena/deic"}],"metrics_order":"[\"Average Balanced Accuracy (across datasets)\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]}]}