paper-with-me

ImageNet

홈페이지 · 논문 15,430편

The ImageNet dataset contains 14,197,122 annotated images according to the WordNet hierarchy. Since 2010 the dataset is used in the ImageNet Large Scale Visual Recognition Challenge (ILSVRC), a benchmark in image classification and object detection. The publicly released dataset contains a set of manually annotated training images. A set of test images is also released, with the manual annotations withheld. ILSVRC annotations fall into one of two categories: (1) image-level annotation of a binary label for the presence or absence of an object class in the image, e.g., “there are cars in this image” but “there are no tigers,” and (2) object-level annotation of a tight bounding box and class label around an object instance in the image, e.g., “there is a screwdriver centered at position (20,25) with width of 50 pixels and height of 30 pixels”. The ImageNet project does not own the copyright of the images, therefore only thumbnails and URLs of images are provided. * Total number of non-empty WordNet synsets: 21841 * Total number of images: 14197122 * Number of images with bounding box annotations: 1,034,908 * Number of synsets with SIFT features: 1000 * Number of images with SIFT features: 1.2 million Source: ImageNet Large Scale Visual Recognition Challenge Image Source: https://cs.stanford.edu/people/karpathy/cnnembed/

Images Chinese

벤치마크

Image Classification on ImageNet 결과 1080개
Self-Supervised Image Classification on ImageNet 결과 288개
Neural Architecture Search on ImageNet 결과 275개
Semi-Supervised Image Classification on ImageNet - 10% labeled data 결과 150개
Self-Supervised Image Classification on ImageNet (finetuned) 결과 130개
Semi-Supervised Image Classification on ImageNet - 1% labeled data 결과 130개
Knowledge Distillation on ImageNet 결과 59개
Quantization on ImageNet 결과 34개
Image Classification on ImageNet V2 결과 33개
Image Super-Resolution on ImageNet 결과 24개
Zero-Shot Transfer Image Classification on ImageNet 결과 23개
Zero-Shot Composed Image Retrieval (ZS-CIR) on ImageNet 결과 22개
Weakly Supervised Object Detection on ImageNet 결과 20개
Data Augmentation on ImageNet 결과 19개
Network Pruning on ImageNet 결과 17개
Contrastive Learning on imagenet-1k 결과 16개
Few-Shot Image Classification on ImageNet - 1-shot 결과 16개
Few-Shot Image Classification on ImageNet - 5-shot 결과 16개
Image Deblurring on ImageNet 결과 15개
Image Reconstruction on ImageNet 결과 15개
Prompt Engineering on ImageNet 결과 15개
Few-Shot Image Classification on ImageNet - 10-shot 결과 14개
Model Compression on ImageNet 결과 14개
Image Clustering on ImageNet 결과 13개
Zero-Shot Transfer Image Classification on ImageNet V2 결과 13개
Few-Shot Image Classification on ImageNet - 0-Shot 결과 10개
Image Inpainting on ImageNet 결과 10개
Unsupervised Image Classification on ImageNet 결과 10개
Sparse Learning on ImageNet 결과 9개
Feature Upsampling on ImageNet 결과 8개
Image Classification on imagenet-1k 결과 8개
Prompt Engineering on ImageNet V2 결과 8개
Adversarial Robustness on ImageNet 결과 6개
JPEG Decompression on ImageNet 결과 6개
Semi-Supervised Image Classification on ImageNet - 0.2% labeled data 결과 6개
Weakly-Supervised Object Localization on ImageNet 결과 6개
Adversarial Defense on ImageNet 결과 4개
Color Image Denoising on ImageNet sigma100 결과 4개
Color Image Denoising on ImageNet sigma150 결과 4개
Color Image Denoising on ImageNet sigma200 결과 4개
Color Image Denoising on ImageNet sigma250 결과 4개
Color Image Denoising on ImageNet sigma50 결과 4개
Image Classification with Differential Privacy on ImageNet 결과 4개
Image Colorization on ImageNet 결과 4개
Medical Image Classification on ImageNet 결과 4개
Image Segmentation on ImageNet 결과 2개
Zero-Shot Learning on ImageNet 결과 2개
Image Clustering on imagenet-1k 결과 1개
Transductive Zero-Shot Classification on ImageNet 결과 1개
Visual Question Answering (VQA) on ImageNet 결과 1개