Papers › DropBlock: A regularization method for convolutional networks

DropBlock: A regularization method for convolutional networks

30 Oct 2018NeurIPS 2018 12arXiv:1810.12890archive 2025-07-28

Golnaz Ghiasi, Tsung-Yi Lin, Quoc V. Le

Deep neural networks often work well when they are over-parameterized and trained with a massive amount of noise and regularization, such as weight decay and dropout. Although dropout is widely used as a regularization technique for fully connected layers, it is often less effective for convolutional layers. This lack of success of dropout for convolutional layers is perhaps due to the fact that activation units in convolutional layers are spatially correlated so information can still flow through convolutional networks despite dropout. Thus a structured form of dropout is needed to regularize convolutional networks. In this paper, we introduce DropBlock, a form of structured dropout, where units in a contiguous region of a feature map are dropped together. We found that applying DropbBlock in skip connections in addition to the convolution layers increases the accuracy. Also, gradually increasing number of dropped units during training leads to better accuracy and more robust to hyperparameter choices. Extensive experiments show that DropBlock works better than dropout in regularizing convolutional networks. On ImageNet classification, ResNet-50 architecture with DropBlock achieves 78.13% accuracy, which is more than 1.6% improvement on the baseline. On COCO detection, DropBlock improves Average Precision of RetinaNet from 36.8% to 38.4%.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

DHZS/tf-dropblock mentioned on GitHubtfMIT report
gan3sh500/dropblock mentioned on GitHubpytorch report
miguelvr/dropblock mentioned on GitHubpytorchMIT report
rwightman/pytorch-image-models mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image ClassificationObject Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet ResNet-50 + DropBlock (0.9 kp, 0.1 label smoothing) Top 1 Accuracy 78.35% #840 of 1060 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: DropBlock

1x1 ConvolutionConvolutionDropBlockDropoutFPNFocal LossRetinaNet

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections