{"url":"/dataset/imagenet-9","name":"ImageNet-9","full_name":null,"description_markdown":"ImageNet-9 consists of images with different amounts of background and foreground signal, which you can use to measure the extent to which your models rely on image backgrounds. This dataset is helpful in testing the robustness of vision models with respect to their dependence on the backgrounds of images.","description_withheld":null,"homepage":"https://github.com/MadryLab/backgrounds_challenge","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Image Classification","url":"/task/image-classification","datasets_with_task":"/datasets/task/image-classification"}],"languages":[],"variants":["ImageNet-9"],"data_loaders":[{"repo":"https://github.com/MadryLab/backgrounds_challenge","url":"https://github.com/MadryLab/backgrounds_challenge","frameworks":["pytorch"]}],"num_papers_in_archive":7,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/image-classification-on-imagenet-9","task":"Image Classification","dataset_variant":"ImageNet-9","rows":1,"metrics":["Top 1 Accuracy"],"first_row_in_archive_order":{"model":"SqueezeNet + Simple Bypass","paper":"/paper/squeezenet-alexnet-level-accuracy-with-50x","metrics":{"Top 1 Accuracy":"60.4%"},"code_links":[{"title":"pytorch/vision","url":"https://github.com/pytorch/vision"},{"title":"PaddlePaddle/PaddleClas","url":"https://github.com/PaddlePaddle/PaddleClas"},{"title":"osmr/imgclsmob","url":"https://github.com/osmr/imgclsmob"},{"title":"DeepScale/SqueezeNet","url":"https://github.com/DeepScale/SqueezeNet"},{"title":"jiweibo/imagenet","url":"https://github.com/jiweibo/imagenet"},{"title":"rcmalli/keras-squeezenet","url":"https://github.com/rcmalli/keras-squeezenet"},{"title":"songhan/SqueezeNet-Deep-Compression","url":"https://github.com/songhan/SqueezeNet-Deep-Compression"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/research/cv/squeezenet"},{"title":"mindspore-ecosystem/mindcv","url":"https://github.com/mindspore-ecosystem/mindcv/blob/main/mindcv/models/squeezenet.py"},{"title":"mindlab-ai/mindcv","url":"https://github.com/mindlab-ai/mindcv/blob/main/mindcv/models/squeezenet.py"},{"title":"DT42/squeezenet_demo","url":"https://github.com/DT42/squeezenet_demo"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/official/cv/squeezenet"},{"title":"Mayurji/Image-Classification-PyTorch","url":"https://github.com/Mayurji/Image-Classification-PyTorch"},{"title":"Element-Research/dpnn","url":"https://github.com/Element-Research/dpnn"},{"title":"dividiti/ck-caffe","url":"https://github.com/dividiti/ck-caffe"},{"title":"vonclites/squeezenet","url":"https://github.com/vonclites/squeezenet"},{"title":"marload/ConvNets-TensorFlow2","url":"https://github.com/marload/ConvNets-TensorFlow2"},{"title":"gsp-27/pytorch_Squeezenet","url":"https://github.com/gsp-27/pytorch_Squeezenet"},{"title":"lizeng614/SqueezeNet-Neural-Style-Pytorch","url":"https://github.com/lizeng614/SqueezeNet-Neural-Style-Pytorch"},{"title":"mtmd/Mobile_ConvNet","url":"https://github.com/mtmd/Mobile_ConvNet"},{"title":"Kaido0/Brain-Tissue-Segment-Keras","url":"https://github.com/Kaido0/Brain-Tissue-Segment-Keras"},{"title":"matteo-rizzo/fc4-pytorch","url":"https://github.com/matteo-rizzo/fc4-pytorch"},{"title":"avoroshilov/tf-squeezenet","url":"https://github.com/avoroshilov/tf-squeezenet"},{"title":"ejlb/squeezenet-chainer","url":"https://github.com/ejlb/squeezenet-chainer"},{"title":"haria/SqueezeNet","url":"https://github.com/haria/SqueezeNet"},{"title":"cmasch/squeezenet","url":"https://github.com/cmasch/squeezenet"},{"title":"milliemince/eBay-shipping-predictions","url":"https://github.com/milliemince/eBay-shipping-predictions"},{"title":"birder/birder","url":"https://gitlab.com/birder/birder"},{"title":"Dawars/SqueezeNet-tf","url":"https://github.com/Dawars/SqueezeNet-tf"},{"title":"Banus/caffe-demo","url":"https://github.com/Banus/caffe-demo"},{"title":"zjZSTU/LightWeightCNN","url":"https://github.com/zjZSTU/LightWeightCNN"},{"title":"deep-learning-algorithm/LightWeightCNN","url":"https://github.com/deep-learning-algorithm/LightWeightCNN"},{"title":"KentaItakura/Classify-crack-image-and-explain-why-using-MATLAB","url":"https://github.com/KentaItakura/Classify-crack-image-and-explain-why-using-MATLAB"},{"title":"mindspore-courses/heads-on-mindspore","url":"https://github.com/mindspore-courses/heads-on-mindspore/blob/main/1-best-practice/models"},{"title":"MS-Mind/MS-Code-02","url":"https://github.com/MS-Mind/MS-Code-02/tree/main/configs/squeezenet"},{"title":"MrRen-sdhm/Embedded_Multi_Object_Detection_CNN","url":"https://github.com/MrRen-sdhm/Embedded_Multi_Object_Detection_CNN"},{"title":"King-Otaku/Emotion_Recognition_DNN","url":"https://github.com/King-Otaku/Emotion_Recognition_DNN"},{"title":"xin-w8023/SqueezeNet-PyTorch","url":"https://github.com/xin-w8023/SqueezeNet-PyTorch"},{"title":"Qengineering/SqueezeNet-ncnn","url":"https://github.com/Qengineering/SqueezeNet-ncnn"},{"title":"m1lhaus/SimpleSqueezeNet","url":"https://github.com/m1lhaus/SimpleSqueezeNet"},{"title":"2023-MindSpore-1/ms-code-217","url":"https://github.com/2023-MindSpore-1/ms-code-217/tree/main/squeezenet"},{"title":"brianjychan/landuse","url":"https://github.com/brianjychan/landuse"},{"title":"AlexandruBurlacu/keras_squeezenet","url":"https://github.com/AlexandruBurlacu/keras_squeezenet"},{"title":"taltole/LiteNetwork_Image_Classification","url":"https://github.com/taltole/LiteNetwork_Image_Classification"},{"title":"taltole/CIFAR10_SqueezeNet","url":"https://github.com/taltole/CIFAR10_SqueezeNet"},{"title":"maxemerling/COVID_CT","url":"https://github.com/maxemerling/COVID_CT"},{"title":"Mind23-2/MindCode-116","url":"https://github.com/Mind23-2/MindCode-116"},{"title":"2023-MindSpore-4/Code11","url":"https://github.com/2023-MindSpore-4/Code11/tree/main/squeezenet"},{"title":"adeely9/experiment_2_python3","url":"https://github.com/adeely9/experiment_2_python3"},{"title":"vibhu444/alexnet-squeeze-mnist","url":"https://github.com/vibhu444/alexnet-squeeze-mnist"},{"title":"bogireddytejareddy/3d-squeezenet","url":"https://github.com/bogireddytejareddy/3d-squeezenet"},{"title":"code-implementation1/Code8","url":"https://github.com/code-implementation1/Code8/tree/main/squeezenet"},{"title":"mdsarfarazulh/fire-module","url":"https://github.com/mdsarfarazulh/fire-module"},{"title":"johngear/eecs504","url":"https://github.com/johngear/eecs504"},{"title":"Jastot/Rodinka_Neural_Network","url":"https://github.com/Jastot/Rodinka_Neural_Network"},{"title":"kingcong/squeezenet","url":"https://github.com/kingcong/squeezenet"},{"title":"Goandwanderfaraway/squeezenet-mindspore","url":"https://github.com/Goandwanderfaraway/squeezenet-mindspore"},{"title":"modelhub-ai/squeezenet","url":"https://github.com/modelhub-ai/squeezenet"},{"title":"Mind23-2/MindCode-80","url":"https://github.com/Mind23-2/MindCode-80"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/squeezenet-alexnet-level-accuracy-with-50x","title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size","date":"2016-02-24","rows_on_this_dataset":1,"code_links":59,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":4,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":4,"samples_ran":4,"samples_unverified":0,"pointer_only_for_licence":2,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}