ImageNet16: Small scale ImageNet Classification

This is a subset of ImageNet called "ImageNet16" more suited for cases with limited computational budget and faster experimentation. 

Each class has 400 train images and 100 test images.

* Credit also goes to original creators that constructed the dataset. Unfortunately, I was not able to relocated it online so I reupload it here.

If used in your work please cite as follows:

C. Kyrkou, "Toward Efficient Convolutional Neural Networks With Structured Ternary Patterns," in IEEE Transactions on Neural Networks and Learning Systems, doi: 10.1109/TNNLS.2024.3380827.

The classes corresponding to imagenet1K:

• n02009912 American_egret

• n02113624 toy_poodle

•  n02123597 Siamese_cat

• n02132136 brown_bear

• n02504458 African_elephant

• n02690373 airliner

• n02835271 bicycle-built-for-two

• n02951358 canoe

• n03041632 cleaver

• n03085013 computer_keyboard

• n03196217 digital_clock

• n03977966 police_van

• n04099969 rocking_chair

• n04111531 rotisserie

• n04285008 sports_car

• n04591713 wine_bottle

From original map.txt

knife =    n03041632

keyboard = n03085013

elephant = n02504458

bicycle =  n02835271

airplane = n02690373

clock =    n03196217

oven =     n04111531

chair =    n04099969

bear =     n02132136

boat =     n02951358

cat =      n02123597

bottle =   n04591713

truck =    n03977966

car =      n04285008

bird =     n02009912

dog =      n02113624

Folder Structure

-<train>

  -- <class idx 1>

      --- <filename1>.JPEG

      --- <filename2>.JPEG

      --- ....

  -- <class idx 1>

  --...

-<val>

  -- <class idx 1>

      --- <filename1>.JPEG

      --- <filename2>.JPEG

      --- ....

  -- <class idx 1>

  --...

Some preliminary results:

Model Name
Accuracy (Top-1)

VGG16
85.3

ResNet50
88.2

MobileNetV2
91.0

EfficientNet B0
85.6

Massive Credit to original ImageNet authors[1] Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein, Alexander C. Berg and Li Fei-Fei.ImageNet Large Scale Visual Recognition Challenge. IJCV, 2015