Papers › ChainerCV: a Library for Deep Learning in Computer Vision

ChainerCV: a Library for Deep Learning in Computer Vision

28 Aug 2017arXiv:1708.08169archive 2025-07-28

Yusuke Niitani, Toru Ogawa, Shunta Saito, Masaki Saito

Despite significant progress of deep learning in the field of computer vision, there has not been a software library that covers these methods in a unifying manner. We introduce ChainerCV, a software library that is intended to fill this gap. ChainerCV supports numerous neural network models as well as software components needed to conduct research in computer vision. These implementations emphasize simplicity, flexibility and good software engineering practices. The library is designed to perform on par with the results reported in published papers and its tools can be used as a baseline for future research in computer vision. Our implementation includes sophisticated models like Faster R-CNN and SSD, and covers tasks such as object detection and semantic segmentation.

PaperPDFCode

Code

pfnet/chainercv officialmentioned in papermentioned on GitHub report
chainer/chainercv mentioned on GitHub 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

Deep LearningObject DetectionSemantic Segmentationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection COCO test-dev FPN (ResNet101 backbone) box mAP 39.5 #203 of 225 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

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionFPNFaster R-CNNGlobal Average PoolingKaiming InitializationMax PoolingNon Maximum SuppressionRPNReLUResidual BlockResidual ConnectionRoIPoolSSDSoftmax

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