Paper Review

Reading time ~3 minutes

General Purpose

Supervised Learning

Convolutional Neural Network

Classification

  • [LeNet] Gradient-Based Learning Applied to Document Recognition, 1998 [paper]
  • [AlexNet] ImageNet Classification with Deep Convolutional Neural Networks, 2012 [paper]
  • [ZFNet] Visualizing and Understanding Convolutional Networks, 2014 [paper]
  • [VGGNet] Very Deep Convolutional Networks for Large-Scale Image Recognition, 2014 [paper]
  • [GoogLeNet(inception)] Going Deeper with Convolutions, 2015 [paper]
  • [ResNet] Deep Residual Learning for Image Recognition, 2016 [paper]
  • [DenseNet] Densely Connected Convolutional Networks, 2017 [paper]
  • [XceptionNet] Xception: Deep Learning with Depthwise Separable Convolutions, 2017 [paper]

Object Detection

  • [OverFeat] OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks, 2013 [paper]
  • [R-CNN] Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation, 2014 [paper]
  • [YOLO] You Only Look Once: Unified, Real-Time Object Detection, 2015 [paper]
  • [SPP-Net] Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition, 2015 [paper]
  • [Fast R-CNN] Fast r-cnn, 2015 [paper]
  • [Faster R-CNN] Faster R-CNN: towards real-time object detection with region proposal networks, 2015 [paper]
  • [SSD] SSD: Single Shot MultiBox Detector, 2015 [paper]
  • [R-FCN] R-FCN: Object Detection via Region-based Fully Convolutional Networks, 2016 [paper]
  • [FPN] Feature Pyramid Networks for Object Detection, 2016 [paper]
  • [YOLOv2, YOLO9000] YOLO9000: Better, Faster, Stronger, 2016 [paper]
  • [Mask R-CNN] Mask R-CNN, 2017 [paper]
  • [RetinaNet] Focal Loss for Dense Object Detection, 2017 [paper]
  • [YOLOv3] YOLOv3: An Incremental Improvement, 2018 [paper]

Semantic Segmantation

-

CNN visualization

  • Deep inside convolutional networks: Visualising image classification models and saliency maps, 2013 [paper]
  • [ZFNet] Visualizing and Understanding Convolutional Networks, 2014 [paper]
  • do convnets learn correspondence?, 2014 [paper]
  • Object Detectors Emerge in Deep Scene CNNs, 2014 [paper]
  • Rich feature hierarchies for accurate object detection and semantic segmentation, 2014 [paper]
  • Striving for simplicity: The all convolutional net, 2014 [paper] [review]
  • Deep neural networks are easily fooled: High confidence predictions for unrecognizable images, 2015 [paper]
  • explaining and harnessing adversarial examples, 2015 [paper]
  • Understanding deep image representations by inverting them, 2015 [paper]
  • [CAM] Learning Deep Features for Discriminative Localization, 2016 [paper] [review]
  • Inverting visual representations with convolutional networks, 2016 [paper]
  • [Grad-CAM] Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization, 2017 [paper] [review]

Recurrent/Recursive Neural Network

- -

Both CNN & RNN

Unsupervised Learning

Deep Belief Network

Auto Encoder

Generative adversarial Network

Reinforcement Learning

DQN

Meta Learning

Siamese Network

  • Learning a Similarity Metric Discriminatively with Application to Face Verification, 2005 [paper]
  • Learning Fine-grained Image Similarity with Deep Ranking, 2014 [paper] [review]
  • Siamese Neural Networks for One-shot Image Recognition, 2015 [paper]
  • DEEP METRIC LEARNING USING TRIPLET NETWORK, 2015 [paper] [review]
  • FaceNet: A Unified Embedding for Face Recognition and Clustering, 2015 [paper] [review]
  • In Defense of the Triplet Loss for Person Re-Identification, 2017 [paper]

Curriculum learning

Domain

image restoration/reconstruction (super-resolution)

Fire Detection

Image Forensics

Financial Analysis

Sound Recognition

[GMM-UBM]

  • Speaker Verification Using Adapted Gaussian, 2000 [paper]

[GSV-SVM, JFA]

  • SVM based speaker verification using a GMM supervector kernel and NAP variability compensation, 2006 [paper]
  • Speaker and session variability in GMM-based speaker verification, 2007 [paper]

[i-vector/CSS]

  • Discriminative and generative approaches for long-and short-term speaker characteristics modeling: application to speaker verification, 2009 [paper]

[i-vector/PLDA]

  • Bayesian speaker verification with heavy-tailed priors., 2010 [pdf]
  • Front-end factor analysis for speaker verification, 2011 [paper]
  • Supervised domain adaptation for i-vector based speaker recognition, 2014 [paper]

[i-vector/DNN]

  • A novel scheme for speaker recognition using a phonetically-aware deep neural network, 2014 [paper]
  • Speaker verification using kernel-based binary classifiers with binary operation derived features, 2014 [paper]
  • Denoising autoencoder-based speaker feature restoration for utterances of short duration, 2015 [paper]
  • Discriminative autoencoders for speaker verification, 2017 [paper]
  • Advanced b-vector system based deep neural network as classifier for speaker verification, 2016 [paper]

[DNN]

  • Deep neural networks for small footprint text-dependent speaker verification., 2014 [paper]
  • End-to-end text-dependent speaker verification, 2016 [paper]
  • End-to-end attention based text-dependent speaker verification, 2016 [paper]
  • [Deep speaker]: an end-to-end neural speaker embedding system, 2017 [paper]
  • A complete end-to-end speaker verification system using deep neural networks: From raw signals to verification result, 2018 [paper] [review]
  • Generalised Discriminative Transform via Curriculum Learning for Speaker Recognition, 2018 [paper]
  • Generalized end-to-end loss for speaker verification, 2018 [paper]

  • [DATASET] VoxCeleb: a large-scale speaker identification dataset, 2018 [paper] [review]

Agriculture

  • Evaluation of Features for Leaf Classification in Challenging Conditions, 2015 [paper] [review]
  • Deep Neural Networks Based Recognition of Plant Diseases by Leaf Image Classification, 2016 [paper] [review]
  • Using Deep Learning for Image-Based Plant Disease Detection, 2016 [paper]
  • A Deep Learning-based Approach for Banana Leaf Diseases Classification, 2017 [paper] [review]

  • Deep learning in agriculture: A survey, 2018 [paper]

  • [DATASET] University of Arcansas, Plants Dataset [site1] [site2]
  • [DATASET] EPEL, Plant Village Dataset [site]
    • currently not available!
  • [DATASET] Leafsnap Dataset [site]
  • [DATASET] LifeCLEF Dataset [site]
  • [DATASET] Africa Soil Information Service(AFSIS) Dataset [site]
  • [DATASET] UC Merced Land Use Dataset [site]
  • [DATASET] MalayaKew Dataset [site]
  • [DATASET] Crop/Weed Field Image Dataset [paper] [site]
  • [DATASET] University of Bonn Photogrammetry, IGG [site]
  • [DATASET] Flavia leaf Dataset [site]
  • [DATASET] Syngenta Crop Challenge 2017 [site]
  • [DATASET] Plant Image Analysis [site]
  • [DATASET] PlantVillage Disease Classification Challenge - Color Images [site]