Deep Pyramidal Residual Networks with Separated Stochastic Depth
Yoshihiro Yamada, Masakazu Iwamura, Koichi Kise
2016-12-05Object Recognition
Abstract
On general object recognition, Deep Convolutional Neural Networks (DCNNs) achieve high accuracy. In particular, ResNet and its improvements have broken the lowest error rate records. In this paper, we propose a method to successfully combine two ResNet improvements, ResDrop and PyramidNet. We confirmed that the proposed network outperformed the conventional methods; on CIFAR-100, the proposed network achieved an error rate of 16.18% in contrast to PiramidNet achieving that of 18.29% and ResNeXt 17.31%.
Related Papers
GeoMag: A Vision-Language Model for Pixel-level Fine-Grained Remote Sensing Image Parsing2025-07-08Out-of-distribution detection in 3D applications: a review2025-07-01SASep: Saliency-Aware Structured Separation of Geometry and Feature for Open Set Learning on Point Clouds2025-06-16Continual Hyperbolic Learning of Instances and Classes2025-06-12DCIRNet: Depth Completion with Iterative Refinement for Dexterous Grasping of Transparent and Reflective Objects2025-06-11Aligning Text, Images, and 3D Structure Token-by-Token2025-06-09STSBench: A Spatio-temporal Scenario Benchmark for Multi-modal Large Language Models in Autonomous Driving2025-06-06Feature-Based Lie Group Transformer for Real-World Applications2025-06-05