clm_3594e992DenseNets obtain significant improvements over the state-of-the-art on most of them, whilst requiring less computation to achieve high performance.
arXiv 1608.06993 · cs.CV cs.LG
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.
clm_3594e992DenseNets obtain significant improvements over the state-of-the-art on most of them, whilst requiring less computation to achieve high performance.
res_659164ad1 arXiv:1608.06993v5 [cs.CV] 28 Jan 2018 In this paper, we propose an architecture that distills this insight into a simple connectivity pattern: to ensure maximum information flow between layers in … (excerpt)
clm_8605cb0bFurther, we significantly outperform the current state-ofthe-art results on most of the benchmark tasks.
clm_2ff1872dTo further improve the information flow between layers we propose a different connectivity pattern: we introduce direct connections from any layer to all subsequent layers.
clm_9c106c9eNote that each “conv” layer shown in the table corresponds the sequence BN-ReLU-Conv. obtain state-of-the-art results on the datasets that we tested on.
clm_1bf37010To highlight general trends, we mark all results that outperform the existing state-of-the-art inboldface and the overall best result in blue.
res_e31de8f3Possibly the most noticeable trend may originate from the bottom row of Table 2, which shows that DenseNet-BC with L = 190 and k = 40 outperforms the existing state-of-the-art … (excerpt)
res_255ef9a7Our best results on C10 and C100 (without data augmentation) are even more encouraging: both are close to 30% lower than Fractal- Net with drop-path regularization [17].
res_ab079de7On SVHN, with dropout, the DenseNet with L = 100 and k = 24 also surpasses the current best result achieved by wide ResNet.
res_3efaccebHowever, the 250-layer DenseNet-BC doesn’t further improve the performance over its shorter counterpart.
res_1beb2c91For example, our 250-layer model only has 15.3M parameters, but it consistently outperforms other models such as FractalNet and Wide ResNets that have more than 30M parameters.
res_40baf50bWe also highlight that DenseNet-BC with L = 100 andk = 12 achieves comparable performance (e.g., 4.51% vs 4.62% error on C10+, 22.27% vs 22.71% error on C100+) as the … (excerpt)
res_ea42285eThe 1001-layer deep ResNet converges to a lower training loss value but a similar test error.
res_2f2a2ee2On C10, the improvement denotes a 29% relative reduction in error from 7.33% to 5.19%.
res_ec08ce07DenseNet-BC requires about 1/3 of the parameters as ResNet to achieve comparable accuracy.
res_bc777ceeFurther, to achieve the same level of accuracy, DenseNet-BC only requires around 1/3 of the parameters of ResNets (middle plot).
clm_cb5fed73Under multiple settings, it achieved state-of-the-art results across several highly competitive datasets.
clm_eefc2c3aMoreover, DenseNets require substantially fewer parameters and less computation to achieve state-of-the-art performances.
clm_dc23903fBecause we adopted hyperparameter settings optimized for residual networks in our study, we believe that further gains in accuracy of DenseNets may be obtained by more detailed tuning of hyperparameters … (excerpt)
Record your result in the Mearc app on your own machine, then use Publish this result with this paper's id (1608.06993) 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.