pith. sign in

arxiv: 1504.08083 · v2 · pith:7R64TNCDnew · submitted 2015-04-30 · 💻 cs.CV

Fast R-CNN

classification 💻 cs.CV
keywords fastr-cnnfastercomparedconvolutionaldeepdetectionnetwork
0
0 comments X
read the original abstract

This paper proposes a Fast Region-based Convolutional Network method (Fast R-CNN) for object detection. Fast R-CNN builds on previous work to efficiently classify object proposals using deep convolutional networks. Compared to previous work, Fast R-CNN employs several innovations to improve training and testing speed while also increasing detection accuracy. Fast R-CNN trains the very deep VGG16 network 9x faster than R-CNN, is 213x faster at test-time, and achieves a higher mAP on PASCAL VOC 2012. Compared to SPPnet, Fast R-CNN trains VGG16 3x faster, tests 10x faster, and is more accurate. Fast R-CNN is implemented in Python and C++ (using Caffe) and is available under the open-source MIT License at https://github.com/rbgirshick/fast-rcnn.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 11 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Pose Estimation for Non-Cooperative Rendezvous Using Neural Networks

    cs.CV 2019-06 unverdicted novelty 7.0

    SPN is a CNN that detects a spacecraft bounding box, classifies then regresses attitude, and optimizes position via Gauss-Newton, achieving degree-level attitude and cm-level position errors on real images after train...

  2. Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding

    cs.CV 2015-10 conditional novelty 7.0

    A pruning-quantization-Huffman pipeline compresses deep neural networks 35-49x without accuracy loss.

  3. AMAR: Lightweight Attention-Based Multi-User Activity Recognition from Wi-Fi CSI

    eess.SP 2026-05 unverdicted novelty 6.0

    AMAR uses a transformer with learnable query embeddings for set-based prediction of concurrent activities from composite Wi-Fi CSI, combined with edge feature extraction and vector quantization for bandwidth-efficient...

  4. CalibFree: Self-Supervised View Feature Separation for Calibration-Free Multi-Camera Multi-Object Tracking

    cs.CV 2026-05 unverdicted novelty 6.0

    CalibFree enables calibration-free multi-camera tracking via self-supervised feature separation through single-view distillation and cross-view reconstruction, reporting 3% higher accuracy and 7.5% better F1 on tested...

  5. A Multitask Network for Localization and Recognition of Text in Images

    cs.CL 2019-06 unverdicted novelty 6.0

    Presents an end-to-end multitask CNN with FPN, dynamic RoI pooling, and convolutional attention for simultaneous lexicon-free text localization and recognition in complex images.

  6. Efficient Multi-Domain Network Learning by Covariance Normalization

    cs.CV 2019-06 unverdicted novelty 5.0

    CovNorm reduces parameters in domain-adaptive layers via two PCAs and a mini-adaptation layer, enabling efficient multi-domain learning with performance close to full fine-tuning.

  7. Label-Efficient School Detection from Aerial Imagery via Weakly Supervised Pretraining and Fine-Tuning

    cs.CV 2026-05 unverdicted novelty 4.0

    A two-stage weakly supervised pipeline pretrains on auto-generated school labels from sparse points and fine-tunes on only 50 manual examples to achieve strong detection performance in aerial imagery.

  8. Learning to count small and clustered objects with application to bacterial colonies

    cs.CV 2026-04 unverdicted novelty 4.0

    ACFamNet Pro reaches 9.64% mean normalized absolute error on bacterial colony images under 5-fold cross-validation, beating FamNet by 12.71%.

  9. GarmNet: Improving Global with Local Perception for Robotic Laundry Folding

    cs.RO 2019-06 unverdicted novelty 4.0

    GarmNet jointly localizes garments and detects grasp landmarks on the CloPeMa dataset, reducing localization error by 24.7% when landmark detection is included.

  10. RGB-D image-based Object Detection: from Traditional Methods to Deep Learning Techniques

    cs.CV 2019-07 unverdicted novelty 2.0

    A survey of RGB-D object detection from traditional hand-crafted features with machine learning to deep learning techniques.

  11. Understanding Deep Learning Techniques for Image Segmentation

    cs.CV 2019-07 unverdicted novelty 1.0

    A 2019 survey that categorizes and intuitively explains major deep learning techniques for image segmentation, progressing from classical methods to modern neural architectures.