ImageNet: A large-scale hierarchical image database
Citations
33,301 citations
Cites background from "ImageNet: A large-scale hierarchica..."
...Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L. ImageNet: A large-scale hierarchical image database....
[...]
...ImageNet consists of variable-resolution images, while our system requires a constant input dimensionality....
[...]
...The specific contributions of this paper are as follows: we trained one of the largest CNNs to date on the subsets of ImageNet used in the ImageNet Large-Scale Visual Recognition Challenge (ILSVRC)-2010 and ILSVRC-2012 competitions2 and achieved by far the best results ever reported on these datasets....
[...]
...Luckily, current GPUs, paired with a highly optimized implementation of 2D convolution, are powerful enough to facilitate the training of interestinglylarge CNNs, and recent datasets such as ImageNet contain enough labeled examples to train such models without severe overfitting....
[...]
...The second-best contest entry achieved an error rate of 26.2% with an approach that averages the predictions of several classifiers trained on FVs computed from different types of densely sampled features.6 Finally, we also report our error rates on the Fall 2009 version of ImageNet with 10,184 categories and 8.9 million images....
[...]
30,811 citations
30,462 citations
Cites background or methods or result from "ImageNet: A large-scale hierarchica..."
...Recently, ImageNet [1] made a striking departure from the incremental increase in dataset sizes....
[...]
...These include ImageNet [1], PASCAL VOC 2012 [2], and SUN [3]....
[...]
...In contrast to the popular ImageNet dataset [1], COCO has fewer categories but more instances per category....
[...]
...Recently, the ImageNet dataset [1] containing millions of images has enabled breakthroughs in both object classification and detection research using a new class of deep learning algorithms [5], [6], [7]....
[...]
...Other important decisions are whether to include both “thing” and “stuff” categories [39] and whether fine-grained [31], [1] and object-part categories should be included....
[...]
29,480 citations
Cites background from "ImageNet: A large-scale hierarchica..."
...Computer vision research has also demonstrated the importance of transfer learning from large pre-trained models, where an effective recipe is to fine-tune models pre-trained with ImageNet (Deng et al., 2009; Yosinski et al., 2014)....
[...]
...Outside of NLP, computer vision research has also demonstrated the importance of transfer learning from large pre-trained models, where an effective recipe is to fine-tune models pre-trained on ImageNet (Deng et al., 2009; Yosinski et al., 2014)....
[...]
27,821 citations
References
46,906 citations
"ImageNet: A large-scale hierarchica..." refers methods in this paper
...SIFT [15] descriptors are used in this experiment....
[...]
13,049 citations
"ImageNet: A large-scale hierarchica..." refers background or methods in this paper
...ImageNet uses the hierarchical structure of WordNet [9]....
[...]
...The main asset of WordNet [9] lies in its semantic structure, i....
[...]
5,742 citations
"ImageNet: A large-scale hierarchica..." refers methods in this paper
...Special purpose datasets, such as FERET faces [19], Labeled faces in the Wild [13] and the Mammal Benchmark by Fink and Ullman [11] are not included....
[...]
4,302 citations
"ImageNet: A large-scale hierarchica..." refers background in this paper
...Rosch and Lloyd [ 20 ] have demonstrated that humans tend to label visual objects at an easily accessible semantic level termed as “basic level” (e.g....
[...]
4,024 citations
Additional excerpts
...[16, 17, 28, 18])....
[...]