| Nov 2025 |
Train Your Own Speech Recognition Model in 5 Simple Steps ↗ |
Gourav Bais |
Read |
Speech and audioDeveloper tools |
| Aug 2021 |
In defense of triplet loss for person re-identification ↗ |
Deval Shah |
Paper |
Re-identificationLoss functions |
| Mar 2021 |
Improving Illumination in Night-Time Images ↗ |
Vardan Agarwal |
Read |
Image enhancementDeveloper tools |
| Oct 2020 |
Insight on Style Attentional Networks (SANet) for Arbitrary Style Transfer ↗ |
dhwani mehta |
Paper |
Generative modelsAttention modules |
| Aug 2020 |
OpenAI’s GPT — Part 1: Unveiling the GPT Model ↗ |
Yesha R Shastri |
Paper |
Language modelsTransformersNatural language |
| Aug 2020 |
PAMTRI: Pose-Aware Multi-Task Learning for Vehicle Re-Identification
Using Highly Randomized Synthetic Data ↗ |
Deval Shah |
Paper |
Re-identificationKeypoints and poseTraffic analytics |
| Aug 2020 |
Protecting Privacy Using Fawkes Against Unauthorized Surveillance ↗ |
Vardan Agarwal |
Paper |
FacesImage classification |
| Aug 2020 |
LISA: An End-to-End Deep Framework for Instance Shadow Detection ↗ |
Devshree Patel |
Paper |
SegmentationObject detection |
| Aug 2020 |
SpinalNet: Deep Neural Network with Gradual Input ↗ |
Ratnam Parikh |
Paper |
Backbone designImage classification |
| Aug 2020 |
Text2SQL — Part 5: Final Insights · Text2SQL 5/5 ↗ |
Devshree Patel |
Read |
Natural languageLanguage modelsDeveloper tools |
| Aug 2020 |
Text2SQL — Part 4: State-Of-The-Art Models · Text2SQL 4/5 ↗ |
Devshree Patel |
Read |
Natural languageLanguage modelsTransformers |
| Jul 2020 |
Dynamic Convolution — An Exciting Innovation over Convolution Kernels from Microsoft Research ↗ |
Yesha R Shastri |
Paper |
ConvolutionsAttention modulesEfficient networks |
| Jul 2020 |
Face Spoofing Detection in Python ↗ |
Vardan Agarwal |
Read |
FacesDeveloper tools |
| Jul 2020 |
Assembled CNN: Trick-o-Tweaks ↗ |
Mahima Modi |
Paper |
Training recipesBackbone designData augmentation |
| Jul 2020 |
Text2SQL — Part 3: Baseline Models · Text2SQL 3/5 ↗ |
Devshree Patel |
Read |
Natural languageLanguage models |
| Jul 2020 |
DetectoRS — A Comprehensive Review |
Shreejal Trivedi |
Paper |
Feature pyramids and necksConvolutionsObject detection |
| Jul 2020 |
Text2SQL — Part 2: Datasets · Text2SQL 2/5 ↗ |
Devshree Patel |
Read |
Natural languageDatasets and labelling |
| Jul 2020 |
SpineNet: An Unconventional Backbone Architecture from Google Brain ↗ |
Yesha R Shastri |
Paper |
Backbone designObject detectionFeature pyramids and necks |
| Jul 2020 |
Text2SQL — Part 1: Introduction · Text2SQL 1/5 ↗ |
Devshree Patel |
Read |
Natural languageLanguage models |
| Jul 2020 |
DarkCovidNet: Automated detection of COVID-19 with X-ray images ↗ |
Ratnam Parikh |
Paper |
Medical imagingImage classification |
| Jul 2020 |
Weakly Supervised Object Detection — An End to End Training Pipeline ↗ |
Yesha R Shastri |
Paper |
Object detectionWeak supervision |
| Jul 2020 |
BoolGAN: DCGAN For Car Image Generation ↗ |
Ratnam Parikh |
Read |
Generative modelsDeveloper tools |
| Jul 2020 |
Self-Supervised Classification: Semantic Clustering by Adopting Nearest Neighbors ↗ |
Mahima Modi |
Paper |
Self-supervised learningImage classification |
| Jul 2020 |
SNIPER: Efficient Multi-Scale Training ↗ |
Devshree Patel |
Paper |
Object detectionTraining recipesEfficient networks |
| Jul 2020 |
Is ALBERT short for BERT? ↗ |
Marzieh Mehdizadeh |
Paper |
Language modelsTransformersNatural language |
| Jul 2020 |
Video Semantic Segmentation -A Novel Approach from NVIDIA ↗ |
Yesha R Shastri |
Paper |
SegmentationVideoData augmentation |
| Jun 2020 |
Facebook AI TransCoder ↗ |
Devshree Patel |
Paper |
Natural languageLanguage modelsTransformers |
| Jun 2020 |
Novel Visual Question Answering system on 360⁰ Images ↗ |
Ratnam Parikh |
Paper |
Vision and languageNatural language |
| Jun 2020 |
MixConv — Mixed Depthwise Convolutional Kernels from Google Brain |
Shreejal Trivedi |
Paper |
ConvolutionsEfficient networks |
| Jun 2020 |
Synthetic Bounding Box Generation ↗ |
Mahima Modi |
Read |
Datasets and labellingObject detectionData augmentation |
| Jun 2020 |
Simple, Powerful, and Fast— RegNet Architecture from Facebook AI |
Shreejal Trivedi |
Paper |
Backbone designImage classification |
| Jun 2020 |
Triplet Loss Demystified in 5 mins ↗ |
Deval Shah |
Read |
Loss functionsRe-identificationFaces |
| Jun 2020 |
Revolutionary Object Detection Algorithm from Facebook AI ↗ |
Deval Shah |
Paper |
Object detectionSet predictionTransformers |
| Jun 2020 |
YOLOv4 — Version 1: Bag of Freebies · YOLOv4 2/5 ↗ |
Deval Shah |
Paper |
Object detectionData augmentationTraining recipesLoss functions |
| Jun 2020 |
YOLOv4 — Version 3: Proposed Workflow · YOLOv4 4/5 ↗ |
Deval Shah |
Paper |
Object detectionBackbone designFeature pyramids and necks |
| Jun 2020 |
Understanding Attention Modules: CBAM and BAM — A Quick Read |
Shreejal Trivedi |
Paper |
Attention modulesBackbone design |
| May 2020 |
Understanding Focal Loss —A Quick Read |
Shreejal Trivedi |
Paper |
Loss functionsClass imbalanceObject detection |
| May 2020 |
Benchmark Datasets: Gas-station for CV ↗ |
Mahima Modi |
Read |
Datasets and labellingEvaluation and metricsObject detectionTracking |
| May 2020 |
YOLOv4 — Version 4: Final Verdict · YOLOv4 5/5 |
Shreejal Trivedi |
Paper |
Object detectionData augmentationTraining recipes |
| May 2020 |
Understanding DIoU Loss — A Quick Read ↗ |
Mahima Modi |
Paper |
Loss functionsObject detectionNon-maximum suppression |
| May 2020 |
YOLOv4 — Version 2: Bag of Specials · YOLOv4 3/5 |
Shreejal Trivedi |
Paper |
Object detectionAttention modulesActivation functionsFeature pyramids and necks |
| May 2020 |
EfficientDet — A Comprehensive Review ↗ |
Kanan Vyas |
Paper |
Object detectionFeature pyramids and necksEfficient networks |
| May 2020 |
YOLOv4 — Version 0: Introduction · YOLOv4 1/5 |
Shreejal Trivedi |
Paper |
Object detectionBackbone design |
| May 2020 |
CenterNet: Objects as Points — A Comprehensive Guide |
Shreejal Trivedi |
Paper |
Anchor-free detectionKeypoints and poseObject detection |
| Apr 2020 |
Object Detection — A Quick Read |
Shreejal Trivedi |
Read |
Object detectionLoss functions |
| Apr 2020 |
The Surveillance phenomenon you must know about : Multi Object Tracking ↗ |
Deval Shah |
Read |
TrackingVideoRe-identification |
| Apr 2020 |
Object Segmentation ↗ |
Kanan Vyas |
Read |
Segmentation |