ConvNets

KO | EN

gitlite — search

#javascript #python #hacktoberfest #react #ai #typescript #llm #go #golang #android #machine-learning #rust #deep-learning #linux

★ 24 Open GitHub ↗

research and implementations of CNNs and their applications

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

-----------

#### CNN Architectures

[Back to top](#applications)

- [LeNet(1998)] [[paper](http://yann.lecun.com/exdb/publis/pdf/lecun-01a.pdf)]
  - [LeNet-5 (2010)] [[paper](http://yann.lecun.com/exdb/lenet/)]
  - [AlexNet (2012)] [[paper](http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf)]
  - [ZFNet(2013)] [[paper](https://arxiv.org/pdf/1311.2901.pdf)]
  - [VGGNet (2014)] [[paper](https://arxiv.org/pdf/1409.1556.pdf)]
  - [GoogleNet/Inception(2014)] [[paper](https://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Szegedy_Going_Deeper_With_2015_CVPR_paper.pdf)]
  - [FCN(2014)] [[paper](https://arxiv.org/pdf/1411.4038.pdf)]
  - [RCNN(2014)] [[paper](https://arxiv.org/abs/1311.2524)]
  - [Deeply-supervised networks(2014)] [[paper](https://arxiv.org/pdf/1409.5185.pdf)]
  - [ResNet(2015)] [[paper](https://arxiv.org/pdf/1512.03385.pdf)]
  - [Ladder network(2015)] [[paper](https://arxiv.org/pdf/1507.02672.pdf)]
  - [YOLO(2015)] [[Paper](https://arxiv.org/pdf/1506.02640.pdf)]
  - [FractalNet (2016)] [[paper](https://arxiv.org/pdf/1605.07648.pdf)]
  - [PolyNet/Inception-Residual(2016)] [[paper](https://arxiv.org/pdf/1611.05725.pdf)]
  - [DenseNet(2016)] [[paper](https://arxiv.org/pdf/1608.06993.pdf)] [[code](https://github.com/liuzhuang13/DenseNet)] 
  - [SegNet(2016)] [[paper](https://arxiv.org/pdf/1511.00561.pdf)]
  - [fast region based CNN(2016)] [[paper](https://arxiv.org/pdf/1506.01497.pdf)]
  - [Look up based CNN(2016)] [[paper](https://arxiv.org/pdf/1611.06473.pdf)]
  - [Deep network with stochastic depth(2016)] [[paper](https://arxiv.org/pdf/1603.09382.pdf)]
  - [ResNeXt(2016)] [[paper](https://arxiv.org/pdf/1611.05431.pdf)]
  - [SqueezeNet(2016)] [[paper](https://arxiv.org/pdf/1602.07360.pdf)] [[code](https://github.com/DeepScale/SqueezeNet)]
  - [CapsNet(2017)] [[paper](https://arxiv.org/ftp/arxiv/papers/1805/1805.11195.pdf)]
  - [MobileNets(2017)] [[paper](https://arxiv.org/pdf/1704.04861.pdf)]
  - [Xception(2017)] [[paper](https://arxiv.org/abs/1610.02357)]
  - [IRCNN(2017)][[paper](https://arxiv.org/pdf/1704.03264.pdf)]
  - [ViP CNN(2017)] [[paper](https://arxiv.org/pdf/1702.07191.pdf)]
  - [Squeeze-and-Excitation Networks(2017)][[Paper](https://arxiv.org/pdf/1709.01507.pdf)] [[code](https://github.com/hujie-frank/SENet)]
  - [MobileFaceNets(2018)]  [[paper](https://arxiv.org/abs/1804.07573v1)]
  - [DCNet and DCNet++(2018)]  [[paper](https://arxiv.org/abs/1805.04001v1)]
  
--------------
#### Applications

[Back to top](#applications)

- [Object Recognition / Object Classification](#cnn-architectures)   [[SOTA](https://paperswithcode.com/task/image-classification/latest#code)]
   - [Object Detection](#object-detection) [[SOTA](https://paperswithcode.com/task/object-detection/latest#code)]
   - [Semantic Segmentation](#semantic-segmentation) [[SOTA](https://paperswithcode.com/task/semantic-segmentation/latest#code)]
   - [Object Tracking](https://github.com/handong1587/handong1587.github.io/blob/master/_posts/deep_learning/2015-10-09-tracking.md) [[SOTA]()]
   - [Activity/Action Recognition] [[SOTA]()]
   - [Face Recognition] 
   - [Pose estimation] 
   - [Video & Image Captioning]  
   - [Biomedical Imaging] [SOTA](https://paperswithcode.com/area/med)
   - [Remote Sensing] 
   - [Video Analysis]
   - [3D Vision]
   - [CNNs for NLP]
   - [CNNs for Speech Processing]
   - [Adversarial Attacks on CNN] [SOTA](https://paperswithcode.com/area/adversarial)

------------

#### Object Detection

[Back to top](#applications)

- [R-CNN(2013)] [[paper](https://arxiv.org/pdf/1311.2524.pdf)]
- [Overfeat(2014)] [[paper](https://arxiv.org/pdf/1312.6229.pdf)]
- [Multibox(2014)] [[paper](https://arxiv.org/pdf/1412.1441.pdf)]
- [SPPNet(2014)] [[paper](https://arxiv.org/pdf/1406.4729.pdf)]
- [MR-CNN(2015)] [[paper](https://ieeexplore.ieee.org/document/7900179)]
- [Deepbox(2015)] [[paper](https://arxiv.org/pdf/1505.02146.pdf)]
- [AttentionNet(2015)] [[paper](https://arxiv.org/pdf/1506.07704.pdf)]
- [Fast R-CNN(2015)] [[paper](https://arxiv.org/abs/1504.08083)] 
- [DeepProposal(2015)] [[paper](https://arxiv.org/pdf/1510.04445.pdf)]
- [RPN(2015)] [[paper]]
- [Faster R-CNN(2015)] [[paper](https://arxiv.org/abs/1506.01497)]
- [YOLOv1(2016)] [[paper](https://arxiv.org/pdf/1506.02640v1.pdf)]
- [GCNN(2016)] [[paper](https://arxiv.org/abs/1501.06297)]
- [AZNet(2016)] [[paper](https://arxiv.org/pdf/1512.07711.pdf)]
- [ION(2016)] [[paper](https://arxiv.org/pdf/1512.04143.pdf)]
- [HyperNet(2016)] [[paper](https://arxiv.org/pdf/1604.00600.pdf)]
- [OHEM(2016)] [[paper](https://arxiv.org/pdf/1604.03540.pdf)]
- [CRAFT(2016)] [[paper](https://arxiv.org/pdf/1804.10871.pdf)]
- [MultipathNet(2016)] [[paper](https://arxiv.org/pdf/1604.02135.pdf)]
- [SSD(2016)] [[paper](https://arxiv.org/pdf/1512.02325.pdf)]
- [GBDNet(2016)] [[paper](https://arxiv.org/pdf/1610.02579.pdf)]
- [CPF(2016)] [[paper]]
- [MS-CNN(2016)] [[paper](https://arxiv.org/pdf/1607.07155.pdf)]
- [R-FCN(2016)] [[paper](https://arxiv.org/pdf/1605.06409.pdf)]
- [PVANET(2016)] [[paper](https://arxiv.org/pdf/1608.08021.pdf)]
- [DeepIDNet(2016)] [[paper](https://arxiv.org/abs/1409.3505)]
- [NoC(2016)] [[paper](https://arxiv.org/pdf/1504.06066.pdf)]
- [DSSD(2017)] [[paper](https://arxiv.org/abs/1701.06659)]
- [TDM(2017)] [[paper](https://arxiv.org/pdf/1802.09081.pdf)]
- [Feature Pyramid Net(2017)] [[paper](https://arxiv.org/pdf/1612.03144.pdf)]
- [YOLOv2(2017)] [[paper](https://arxiv.org/abs/1612.08242)]
- [RON(2017)] [[paper](https://arxiv.org/pdf/1707.01691.pdf)]
- [DCN(2017)] [[paper]]
- [DeNet(2017)] [[paper](https://arxiv.org/pdf/1703.10295.pdf)]
- [CoupleNet(2017)] [[paper](https://arxiv.org/pdf/1708.02863.pdf)]
- [RetinaNet(2017)] [[paper](https://arxiv.org/pdf/1708.02002.pdf)]
- [Mask R-CNN(2017)] [[paper](https://arxiv.org/pdf/1703.06870.pdf)]
- [DSOD(2017)] [[paper](https://arxiv.org/pdf/1708.01241.pdf)]
- [SMN(2017)] [[paper](https://arxiv.org/pdf/1704.04224.pdf)]
- [YOLOv3(2018)] [[paper](https://arxiv.org/pdf/1804.02767.pdf)]
- [SIN(2018)] [[paper](https://arxiv.org/pdf/1807.00119.pdf)]
- [STDN(2018)] [[paper](https://arxiv.org/pdf/1805.09512.pdf)]
- [RefineDet(2018)] [[paper](https://arxiv.org/pdf/1711.06897.pdf)]
- [RFBNet(2018)] [[paper](https://arxiv.org/pdf/1711.07767.pdf)]
 ------- 
- [Light-Head R-CNN(2017)] [[paper](https://arxiv.org/pdf/1711.07264.pdf)]
- [Cascade R-CNN(2017)]  [[paper](https://arxiv.org/pdf/1712.00726.pdf)]
- [YOLT(2018)] [[paper](https://arxiv.org/pdf/1805.09512.pdf)]
- [FSSD(2018)] [[paper](https://arxiv.org/pdf/1712.00960.pdf)]
- [ESSD] [[paper](https://arxiv.org/ftp/arxiv/papers/1801/1801.05918.pdf)]
- [MDSSD(2018)] [[paper](https://arxiv.org/pdf/1805.07009.pdf)]
- [Pelee(2018)] [[paper](https://arxiv.org/pdf/1804.06882.pdf)]
- [Fire SSD(2018)] [[paper](https://arxiv.org/pdf/1806.05363.pdf)]
- [MegNet(2018)] [[paper](https://arxiv.org/pdf/1803.08009.pdf)]
- [DetNet(2018)] [[paper](https://arxiv.org/abs/1804.06215)]
- [SSOD(2018)] [[paper](https://arxiv.org/pdf/1806.03370.pdf)]
- [CornerNet(2018)] [[paper](https://arxiv.org/abs/1808.01244)]
- [3D Object Detection(2018)] [[paper](https://arxiv.org/pdf/1805.01195.pdf)]
- [ZSD（Zero-Shot Object Detection）(2018)] [[paper](https://arxiv.org/pdf/1804.04340.pdf)]
- [OSD（One-Shot object Detection）(2018)] [[paper](https://arxiv.org/pdf/1807.05857.pdf)]
- [Weakly Supervised Object Detection(2018)] [[paper](https://arxiv.org/pdf/1810.02569.pdf)]
- [Softer-NMS (2018)] [[paper](https://arxiv.org/pdf/1809.08545.pdf)]
- [VideoCapsuleNet(2018)]   [[paper](https://arxiv.org/pdf/1805.08162v1.pdf)]
- [YOLO3D(2018)]   [[paper](https://arxiv.org/pdf/1808.02350v1.pdf)]
--------------

#### Semantic Segmentation

[Back to top](#applications)

- U-Net [[arxiv](https://arxiv.org/pdf/1505.04597.pdf)][[Pytorch](https://github.com/tangzhenyu/SemanticSegmentation_DL/tree/master/U-net)]
- SegNet [[arxiv](https://arxiv.org/pdf/1511.00561.pdf)][[Caffe](https://github.com/alexgkendall/caffe-segnet)]
- DeepLab [[arxiv](https://arxiv.org/pdf/1606.00915.pdf)][[Caffe](https://bitbucket.org/deeplab/deeplab-public/)]
- FCN [[arxiv](https://arxiv.org/pdf/1605.06211.pdf)][[tensorflow](https://github.com/tangzhenyu/SemanticSegmentation_DL/tree/master/FCN)]
- ENet [[arxiv](https://arxiv.org/pdf/1606.02147.pdf)][[Caffe](https://github.com/TimoSaemann/ENet)]
- LinkNet [[arxiv](https://arxiv.org/pdf/1707.03718.pdf)][[Torch](https://github.com/e-lab/LinkNet)]
- DenseNet [[arxiv](https://arxiv.org/pdf/1608.06993.pdf)[]
- Tiramisu [[arxiv](https://arxiv.org/pdf/1611.09326.pdf)]
- DilatedNet [[arxiv](https://arxiv.org/pdf/1511.07122.pdf)]
- PixelNet [[arxiv](https://arxiv.org/pdf/1609.06694.pdf)][[Caffe](https://github.com/aayushbansal/PixelNet)]
- ICNet [[arxiv](https://arxiv.org/pdf/1704.08545.pdf)][[Caffe](https://github.com/hszhao/ICNet )]
- ERFNet [[arxiv](http://www.robesafe.uah.es/personal/eduardo.romera/pdfs/Romera17iv.pdf)][[Torch](https://github.com/Eromera/erfnet )]
- RefineNet [[arxiv](https://arxiv.org/pdf/1611.06612.pdf)][[tensorflow](https://github.com/tangzhenyu/SemanticSegmentation_DL/tree/master/RefineNet)]
- PSPNet [[arxiv](https://arxiv.org/pdf/1612.01105.pdf),[pspnet](https://hszhao.github.io/projects/pspnet/)][[Caffe](https://github.com/hszhao/PSPNet )]
- Dilated convolution [[arxiv](https://arxiv.org/pdf/1511.07122.pdf)][[Caffe](https://github.com/fyu/dilation )]
- DeconvNet [[arxiv](https://arxiv.org/pdf/1505.04366.pdf)][[Caffe](http://cvlab.postech.ac.kr/research/deconvnet/ )]
- FRRN [[arxiv](https://arxiv.org/pdf/1611.08323.pdf)][[Lasagne](https://github.com/TobyPDE/FRRN )]
- GCN [[arxiv](https://arxiv.org/pdf/1703.02719.pdf)][[PyTorch](https://github.com/ZijunDeng/pytorch-semantic-segmentation )]
- LRR [[arxiv](https://arxiv.org/pdf/1605.02264.pdf)][[Matconvnet](https://github.com/golnazghiasi/LRR )]
- DUC, HDC [[arxiv](https://arxiv.org/pdf/1702.08502.pdf)][[PyTorch](https://github.com/ZijunDeng/pytorch-semantic-segmentation )]
- MultiNet [[arxiv](https://arxiv.org/pdf/1612.07695.pdf)] [[tensorflow1](https://github.com/MarvinTeichmann/MultiNet)[tensorflow2](https://github.com/MarvinTeichmann/KittiSeg)]
- Segaware [[arxiv](https://arxiv.org/pdf/1708.04607.pdf)][[Caffe](https://github.com/aharley/segaware )]
- Semantic Segmentation using Adversarial Networks [[arxiv](https://arxiv.org/pdf/1611.08408.pdf)] [[Chainer](https://github.com/oyam/Semantic-Segmentation-using-Adversarial-Networks )]
- In-Place Activated BatchNorm:obtain #1 positions [[arxiv](https://arxiv.org/abs/1712.02616)] [[Pytorch](https://github.com/mapillary/inplace_abn)]
- [SegCaps(2018)]  [[arxiv](https://arxiv.org/abs/1804.04241v1)]
- [SegFinNet(2018)] [[arxiv](https://arxiv.org/abs/1804.09650v1)]
- [SUNets(2018)]   [[arxiv](https://arxiv.org/abs/1804.10343v1)]

--------------

#### References

- [Computer Vision SOTA](https://paperswithcode.com/area/cv)
- [neural-network-papers](https://github.com/robertsdionne/neural-network-papers)
- [ref-implementations](https://github.com/gopala-kr/CNNs/blob/master/ref-implementations.md)
- [ConvNet](https://github.com/gopala-kr/CNNs/blob/master/cnn.md)
- [image-video-classification](https://github.com/gopala-kr/CNNs/blob/master/image-video-classification.md)
- [object-detection](https://github.com/gopala-kr/CNNs/blob/master/object-detection.md)
- [object-tracking-and-recognition](https://github.com/gopala-kr/CNNs/blob/master/object-tracking-and-recognition.md)
- [semantic-segmentation](https://github.com/gopala-kr/CNNs/blob/master/semantic-segmentation.md)
- [image-generation](https://github.com/gopala-kr/CNNs/blob/master/image-generation.md)
- [human-pose-estimation](https://github.com/gopala-kr/CNNs/blob/master/human-pose-estimation.md)
- [low-level-vision](https://github.com/gopala-kr/CNNs/blob/master/low-level-vision.md)
- [vision-and-nlp](https://github.com/gopala-kr/CNNs/blob/master/vision-and-nlp.md)
- [other](https://github.com/gopala-kr/CNNs/blob/master/other.md)
- [face-recognition](https://github.com/gopala-kr/CNNs/blob/master/face-recognition.md)
- [cv-datasets](https://github.com/gopala-kr/ConvNets/blob/master/cv-datasets.md)

------------
- First paper on Memorization in DNNs: https://arxiv.org/abs/1611.03530
- A closer look at memorization in Deep Networks: https://arxiv.org/abs/1706.05394
- Opening the Black Box of Deep Neural Networks via Information: https://arxiv.org/abs/1703.00810
- [Understanding Deep Convolutional Networks](https://arxiv.org/pdf/1601.04920.pdf)
- [A Survey: Time Travel in Deep Learning Space: An Introduction to Deep Learning Models and How Deep Learning Models Evolved from the Initial Ideas](https://arxiv.org/abs/1510.04781)
- [Survey on the attention based RNN model and its applications in computer vision](https://arxiv.org/pdf/1601.06823.pdf)
- [Automatic Description Generation from Images: A Survey of Models, Datasets, and Evaluation Measures](https://arxiv.org/pdf/1601.03896.pdf)
- [Best Practices for Applying Deep Learning to Novel Applications](https://arxiv.org/ftp/arxiv/papers/1704/1704.01568.pdf)
- [Adversarial Examples: Attacks and Defenses for Deep Learning](https://arxiv.org/pdf/1712.07107.pdf)
- [Adversarial Examples that Fool both Human and Computer Vision](https://arxiv.org/pdf/1802.08195v2.pdf)
- [Deep Learning:
A Critical Appraisal ](https://arxiv.org/ftp/arxiv/papers/1801/1801.00631.pdf)
- [A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay](https://arxiv.org/pdf/1803.09820v1.pdf)
- [Multi-objective Architecture Search for CNNs](https://arxiv.org/abs/1804.09081v1)
- [Deep Learning for Generic Object Detection: A Survey](https://arxiv.org/pdf/1809.02165v1.pdf)
- [What I learned from competing against a ConvNet on ImageNet](http://karpathy.github.io/2014/09/02/what-i-learned-from-competing-against-a-convnet-on-imagenet/)
- [neural-network-architectures](https://towardsdatascience.com/neural-network-architectures-156e5bad51ba)
- [Real-time Object Detection with YOLO, YOLOv2 and now YOLOv3](https://medium.com/@jonathan_hui/real-time-object-detection-with-yolo-yolov2-28b1b93e2088)
- [Recognition, Detection, Segmentation and Tracking](https://handong1587.github.io/computer_vision/2015/10/09/recognition-detection-segmentation-tracking.html)
- [Computer Vision: Algorithms and Applications](http://szeliski.org/Book/drafts/SzeliskiBook_20100903_draft.pdf)
- [Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks](https://arxiv.org/abs/1806.05393v1)
- [Adversarial Attacks and Defences: A Survey](https://arxiv.org/pdf/1810.00069v1.pdf)
- [Secure Deep Learning Engineering:
A Software Quality Assurance Perspective](https://arxiv.org/pdf/1810.04538v1.pdf)
- [Face Recognition: From Traditional to Deep
Learning Methods](https://arxiv.org/pdf/1811.00116v1.pdf)
- [Security for Machine Learning-based Systems: Attacks and Challenges during Training and Inference](https://arxiv.org/abs/1811.01463v1)
- [Deep Learning For Computer Vision Tasks: A review](https://arxiv.org/ftp/arxiv/papers/1804/1804.03928.pdf)
- [Mini-batch Serialization: CNN Training with Inter-layer Data Reuse](https://arxiv.org/abs/1810.00307v3)

----------
![cnn](https://github.com/gopala-kr/CNNs/blob/master/resources/img/cnn.PNG)
-------
![1542368857926](https://www.mathworks.com/content/mathworks/www/en/discovery/deep-learning/jcr:content/mainParsys/band_2123350969_copy_1983242569/mainParsys/columns_1635259577/1/image_2128876021_cop.adapt.full.low.svg/1542368857926.svg)
----------------
![img72](https://github.com/gopala-kr/ConvNets/blob/master/resources/img/img72.jpg)
------------------
![cnn_4](https://github.com/gopala-kr/ConvNets/blob/master/resources/img/cnn_4.PNG)
----------
![cnn_5](https://github.com/gopala-kr/ConvNets/blob/master/resources/img/cnn_5.PNG)
----------
![cnn_6](https://github.com/gopala-kr/ConvNets/blob/master/resources/img/cnn_6.PNG)

----------
![cnn_11](https://github.com/gopala-kr/ConvNets/blob/master/resources/img/cnn_11.PNG)
---------------
![cnn21](https://github.com/gopala-kr/ConvNets/blob/master/resources/img/cnn21.PNG)
![cnn22](https://github.com/gopala-kr/ConvNets/blob/master/resources/img/cnn22.PNG)
![cnn23](https://github.com/gopala-kr/ConvNets/blob/master/resources/img/cnn23.PNG)

----------
![obj_det](https://github.com/gopala-kr/ConvNets/blob/master/resources/img/obj_det.png)

-----------

_**Maintainer**_

Gopala KR / @gopala-kr

--------------

ConvNets

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README