res_236471abOur main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3 × 3) convolution filters, which shows that a significant improvement on … (excerpt)
arXiv 1409.1556 · cs.CV
Read on arXiv · arXiv non-exclusive license
Claims were extracted automatically by reducer-1 on 2026-11-12. The paper's license does not allow republishing it, so long claims are shortened to a quotation. Read the full text on arXiv.
res_236471abOur main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3 × 3) convolution filters, which shows that a significant improvement on … (excerpt)
clm_8b5bdf00As a result, we come up with significantly more accurate ConvN et architectures, which not only achieve the state-of-the-art accuracy on ILSVRC classifica tion and localisation tasks, but are also … (excerpt)
res_c6455f004, such normalisation does not improve the performance on the ILSVRC dataset, but l eads to increased memory consumption and computation time.
res_2d9549e5The width of conv. layers (the number of channels) is rather small, sta rting from 64 in the first layer and then increasing by a factor of 2 after each … (excerpt)
res_b62c9b4bThe learning rate was initially set to 10−2, and then decreased by a factor of 10 when the validation set accuracy stopped improving.
res_df145a244, using several values of Q for each S leads to improved performance).
res_12073591Notably, in spite of the same de pth, the configuration C (which contains three 1 × 1 conv. layers), performs worse than the configuration D, which uses 3 × 3 … (excerpt)
res_39ef9449The error rate of our arc hitecture saturates when the depth reaches 19 layers, but even deeper models might be beneficial for largerdatasets.
res_8fffbfabThe top-1 error of the shallow net wa s measured to be 7% higher than that of B (on a center crop), which confirms that a deep net with smal … (excerpt)
res_d18cbd9cFinally, scale jittering at training time ( S ∈ [256; 512]) leads to significantly better results than training on images with fixed smallest side ( S = 256 or S … (excerpt)
res_d6897fbe6 Published as a conference paper at ICLR 2015 The results, presented in Table 4, indicate that scale jittering at test time leads to better performance (as compared to evaluating … (excerpt)
res_ce9322d7On the test set, the configuration E achieves 7.3% top-5 error.
clm_9f97c7d2As can be seen, using multiple crops performs sl ightly better than dense evaluation, and the two approaches are indeed complementary, as their combination outperforms each of them.
res_9fc7ff3cFor refere nce, our best-performing single model achieves 7.1% error (model E, Table 5).
res_2ed33d97As can be seen from Table 7, our very deep ConvNets significantly outperform the previous generation of models, which achieved the best results in the ILSVR C-2012 and ILSVRC-2013 competitions.
res_e6d4b0c1Our result is also competitive with respect to the cla ssification task winner (GoogLeNet with 6.7% error) and substantially outperforms the ILSVRC-2013 winn ing submission Clarifai, which achieved 11.2% with … (excerpt)
res_0a89ad14In terms of the single-net performance , our architecture achieves the best result (7.0% test error), outperforming a single GoogLeNet by 0.9%.
clm_47b76fdcIn the appendix, we also show that our models generalise well to a wide range of tasks and datasets, matching or outperformin g more complex recognition pipelines built around less … (excerpt)
res_2e9fbcfeAs can be seen from Table 9, application of the localisation ConvNet to the whole image substantially improves the results compared to using a center crop (Table 8), despite using … (excerpt)
res_154b9d934), testing at several scales and combining the predictions of multiple networks further improves the performance.
clm_7abeda1eFollowing that line of work, we investigate if our models lead to better performance than more shallow models utilised in the state-of-the-art methods.
res_457d53cbIt is worth noting though that the improvement over a smalle r range of {256, 384, 512} was rather marginal (0.3%).
res_b6754b42Our methods set the new state of the art across image representations, pretrained on the ILSVRC dataset, outperforming the previous b est result of Chatfield et al. (2014) by more … (excerpt)
res_8f8e1478As can be seen, the deeper 19-layer Net-E performs better than the 16-layer Net-D, and their combination further improves the performance.
res_49cbeceeOn Caltech-256, our features outperform the state of the art (Chatfield et al., 2014) by a large margin (8.6%).
clm_b4c2a409Since the public release of our models, they have been active ly used by the research community for a wide range of image recogniti on tasks, consistently outperforming more shallow … (excerpt)
res_71c947fc(2014) achieve the state of the object detection results by replacing the ConvNet of Krizhe vsky et al. (2012) with our 16-layer model.
Record your result in the Mearc app on your own machine, then use Publish this result with this paper's id (1409.1556) and the claim id shown next to the claim. Mearc creates a file that holds only what you choose to publish. Add it to the public claim data by pull request; a maintainer other than you reviews it before it counts.