281 citations · 677 across the 14 of their papers we have counts for
15 papers
Team PFDet's Methods for Open Images Challenge 2019
Yusuke Niitani, Toru Ogawa, Shuji Suzuki +4
We present the instance segmentation and the object detection method used by team PFDet for Open Images Challenge 2019. We tackle a massive dataset size, huge class imbalance and f…
Chainer: A Deep Learning Framework for Accelerating the Research Cycle
Seiya Tokui, Ryosuke Okuta, Takuya Akiba +7
Software frameworks for neural networks play a key role in the development and application of deep learning methods. In this paper, we introduce the Chainer framework, which intend…
Optuna: A Next-generation Hyperparameter Optimization Framework
Takuya Akiba, Shotaro Sano, Toshihiko Yanase +2
The purpose of this study is to introduce new design-criteria for next-generation hyperparameter optimization software. The criteria we propose include (1) define-by-run API that a…
A Graph Theoretic Framework of Recomputation Algorithms for Memory-Efficient Backpropagation
Mitsuru Kusumoto, Takuya Inoue, Gentaro Watanabe +2
Recomputation algorithms collectively refer to a family of methods that aims to reduce the memory consumption of the backpropagation by selectively discarding the intermediate resu…
Sampling Techniques for Large-Scale Object Detection from Sparsely Annotated Objects
Yusuke Niitani, Takuya Akiba, Tommi Kerola +3
Efficient and reliable methods for training of object detectors are in higher demand than ever, and more and more data relevant to the field is becoming available. However, large d…
PFDet: 2nd Place Solution to Open Images Challenge 2018 Object Detection Track
Takuya Akiba, Tommi Kerola, Yusuke Niitani +3
We present a large-scale object detection system by team PFDet. Our system enables training with huge datasets using 512 GPUs, handles sparsely verified classes, and massive class…
Adversarial Attacks and Defences Competition
Alexey Kurakin, Ian Goodfellow, Samy Bengio +20
To accelerate research on adversarial examples and robustness of machine learning classifiers, Google Brain organized a NIPS 2017 competition that encouraged researchers to develop…
Variance-based Gradient Compression for Efficient Distributed Deep Learning
Yusuke Tsuzuku, Hiroto Imachi, Takuya Akiba
Due to the substantial computational cost, training state-of-the-art deep neural networks for large-scale datasets often requires distributed training using multiple computation wo…
ShakeDrop Regularization for Deep Residual Learning
Yoshihiro Yamada, Masakazu Iwamura, Takuya Akiba +1
Overfitting is a crucial problem in deep neural networks, even in the latest network architectures. In this paper, to relieve the overfitting effect of ResNet and its improvements…
Extremely Large Minibatch SGD: Training ResNet-50 on ImageNet in 15 Minutes
Takuya Akiba, Shuji Suzuki, Keisuke Fukuda
We demonstrate that training ResNet-50 on ImageNet for 90 epochs can be achieved in 15 minutes with 1024 Tesla P100 GPUs. This was made possible by using a large minibatch size of…
ChainerMN: Scalable Distributed Deep Learning Framework
Takuya Akiba, Keisuke Fukuda, Shuji Suzuki
One of the keys for deep learning to have made a breakthrough in various fields was to utilize high computing powers centering around GPUs. Enabling the use of further computing ab…
Cut Tree Construction from Massive Graphs
Takuya Akiba, Yoichi Iwata, Yosuke Sameshima +2
The construction of cut trees (also known as Gomory-Hu trees) for a given graph enables the minimum-cut size of the original graph to be obtained for any pair of vertices. Cut tree…
Fractality of Massive Graphs: Scalable Analysis with Sketch-Based Box-Covering Algorithm
Takuya Akiba, Kenko Nakamura, Taro Takaguchi
Analysis and modeling of networked objects are fundamental pieces of modern data mining. Most real-world networks, from biological to social ones, are known to have common structur…
Branch-and-Reduce Exponential/FPT Algorithms in Practice: A Case Study of Vertex Cover
Takuya Akiba, Yoichi Iwata
We investigate the gap between theory and practice for exact branching algorithms. In theory, branch-and-reduce algorithms currently have the best time complexity for numerous impo…
Fast Exact Shortest-Path Distance Queries on Large Networks by Pruned Landmark Labeling
Takuya Akiba, Yoichi Iwata, Yuichi Yoshida
We propose a new exact method for shortest-path distance queries on large-scale networks. Our method precomputes distance labels for vertices by performing a breadth-first search f…