arXiv (Cornell University) · 2017 · 29 citations · 30 references
ComputingComputer ScienceHigh-performance ComputingComputer VisionMachine LearningMachine VisionDeep LearningGraphics Processing UnitsHardware AccelerationObject DetectionObject RecognitionRepresentation LearningDeep Learning DetectionDeep Learning On GpusMini-batch TrainingTrainingTraining Time
The improvements in recent CNN-based object detection works, from R-CNN [11], Fast/Faster R-CNN [10, 31] to recent Mask R-CNN [14] and RetinaNet [24], mainly come from new network, new framework, or novel loss design. But mini-batch size, a key factor in the training, has not been well studied. In this paper, we propose a Large MiniBatch Object Detector (MegDet) to enable the training with much larger mini-batch size than before (e.g. from 16 to 256), so that we can effectively utilize multiple GPUs (up to 128 in our experiments) to significantly shorten the training time. Technically, we suggest a learning rate policy and Cross-GPU Batch Normalization, which together allow us to successfully train a large mini-batch detector in much less time (e.g., from 33 hours to 4 hours), and achieve even better accuracy. The MegDet is the backbone of our submission (mmAP 52.5%) to COCO 2017 Challenge, where we won the 1st place of Detection task.
30
ImageNet: A large-scale hierarchical image database
Jia Deng, Wei Dong, Richard Socher et al. · 2009 IEEE Conference on Computer Vision and Pattern Recognition · 2009 · 61.8K citations
Squeeze-and-Excitation Networks
Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos et al. · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2017 · 22.1K citations
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · arXiv (Cornell University) · 2015 · 4.7K citations · Full text