CityPersons: A Diverse Dataset for Pedestrian Detection
Shanshan Zhang,Rodrigo Benenson,Bernt Schiele +2 more
- 21 Jul 2017
- pp 4457-4465
TL;DR: In this paper, a new set of person annotations on top of the Cityscapes dataset is introduced, CityPersons, which allows the first time to train one single CNN model that generalizes well over multiple benchmarks.
read more
Abstract: Convnets have enabled significant progress in pedestrian detection recently, but there are still open questions regarding suitable architectures and training data. We revisit CNN design and point out key adaptations, enabling plain FasterRCNN to obtain state-of-the-art results on the Caltech dataset. To achieve further improvement from more and better data, we introduce CityPersons, a new set of person annotations on top of the Cityscapes dataset. The diversity of CityPersons allows us for the first time to train one single CNN model that generalizes well over multiple benchmarks. Moreover, with additional training with CityPersons, we obtain top results using FasterRCNN on Caltech, improving especially for more difficult cases (heavy occlusion and small scale) and providing higher localization quality.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Small-scale Pedestrian Detection Based on Feature Enhancement Strategy
Yong Chen,Manli Jin,Huanlin Liu,Bo Wang,Meiyong Huang +4 more
TL;DR: A feature enhancement module is proposed to improve small-scale pedestrian detection, combining feature fusion and self-attention modules to retain and enhance pedestrian features while suppressing background information, achieving 19.8% detection accuracy and 22 FPS on CrowdHuman dataset.
Occlusion Handling and Multi-Scale Pedestrian Detection Based on Deep Learning: A Review
01 Jan 2022
TL;DR: A detailed review of recent progress in pedestrian detection can be found in this article , where a brief progress of pedestrian detection in the past two decades is summarized and several deep learning methods focusing on occlusion and scale variance are analyzed.
FSTrack: One-Shot Multi-Object Tracking Algorithm Based on Feature Enhancement and Similarity Estimation
Botong He,Liang Yuan,Kai Lv +2 more
TL;DR: FSTrack is a novel one-shot multi-object tracking algorithm that incorporates feature enhancement and similarity estimation techniques to improve model performance. It utilizes an efficient channel attention module and a novel similarity matrix to achieve superior tracking accuracy and continuity.
Nighttime FIR Pedestrian Detection Benchmark Dataset for ADAS
Zhewei Xu,Jiajun Zhuang,Qiong Liu,Jingkai Zhou,Shaowu Peng +4 more
- 23 Nov 2018
TL;DR: A nighttime FIR pedestrian dataset that contains fine-grained annotated video, recorded from diverse road scenes and detailed statistical analysis is introduced, which shows that CNN-based detectors obtained good performance on FIR image.
H2P×PKD: Progressive Training Pipeline with Knowledge Distillation for Lightweight Backbones in Pedestrian Detection
Duc-Nhuan Le,Hoang-Phuc Nguyen,Vinh-Toan Vong,N. X. Luong,Trong-Le Do +4 more
- 15 Aug 2024
TL;DR: This study proposes H2P×PKD, a progressive training pipeline with knowledge distillation for lightweight pedestrian detection models, achieving 8.59% MR−2 on CityPersons' validation set with a downscaled InternImage-M backbone.
References
Deep Residual Learning for Image Recognition
Kaiming He,Xiangyu Zhang,Shaoqing Ren,Jian Sun +3 more
- 27 Jun 2016
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
•Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
- 01 Jan 2015
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
138.5K
•Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
Alex Krizhevsky,Ilya Sutskever,Geoffrey E. Hinton +2 more
- 03 Dec 2012
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
•Posted Content
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: In this article, the adaptive estimates of lower-order moments are used for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimate of lowerorder moments.
82.5K
You Only Look Once: Unified, Real-Time Object Detection
Joseph Redmon,Santosh K. Divvala,Ross Girshick,Ali Farhadi +3 more
- 27 Jun 2016
TL;DR: Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background, and outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.