Papers

One paper, explained end to end: the idea, every equation, the numbers, and where it sits among the others.

Date	Paper	Explanation	Tags
Oct 2026	DETRs Beat YOLOs on Real-time Object Detection Zhao, Lv, Xu, Wei, Wang, Dang, Liu, Chen, 2024	RT-DETR — DETRs Beat YOLOs, Encoder by Encoder · RT-DETR 1/5	Object detection Set prediction Efficient attention Non-maximum suppression
Oct 2026	RT-DETRv2: Improved Baseline with Bag-of-Freebies for Real-Time Detection Transformer Lv, Zhao, Chang, Huang, Wang, Liu, 2024	RT-DETRv2 — A Bag of Freebies for the Decoder · RT-DETR 2/5	Object detection Efficient attention Training recipes Edge deployment
Oct 2026	RT-DETRv3: Real-time End-to-End Object Detection with Hierarchical Dense Positive Supervision Wang, Xia, Lv, Shi, 2024	RT-DETRv3 — More Positives Without Paying at Inference · RT-DETR 3/5	Object detection Set prediction Training recipes
Oct 2026	RT-DETRv4: Painlessly Furthering Real-Time Object Detection with Vision Foundation Models Liao et al., 2025	RT-DETRv4 — Borrowing a Foundation Model's Eyes · RT-DETR 4/5	Object detection Knowledge distillation Training recipes
Oct 2026	RT-DETR-World: Transferring Rich LLM Semantics to Real-Time Open-Vocabulary Detection Zhang et al., 2026	RT-DETR-World — Naming Any Object in Real Time · RT-DETR 5/5	Object detection Vision and language Contrastive learning Knowledge distillation
Oct 2026	Attention Is All You Need Vaswani, Shazeer, Parmar, Uszkoreit, Jones, Gomez, Kaiser, Polosukhin, 2017	Attention Is All You Need — The Transformer, Block by Block · Transformers in Vision 3/12	Transformers Positional encoding Self-attention
Oct 2026	End-to-End Object Detection with Transformers Carion et al., 2020	DETR — Detection as Set Prediction, No Anchors and No NMS · Transformers in Vision 5/12	Object detection Set prediction Transformers
Oct 2026	An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale Dosovitskiy et al., 2020	An Image Is Worth 16×16 Words — ViT, Patch by Patch · Transformers in Vision 6/12	Vision transformers Image classification Pretraining at scale
Oct 2026	Training data-efficient image transformers & distillation through attention Touvron, Cord, Douze, Massa, Sablayrolles, Jégou, 2021	DeiT — Training a Vision Transformer on ImageNet Alone · Transformers in Vision 7/12	Vision transformers Knowledge distillation Data augmentation Training recipes
Oct 2026	Swin Transformer: Hierarchical Vision Transformer using Shifted Windows Liu et al., 2021	Swin Transformer — Windows, Shifts and a Pyramid for Dense Prediction · Transformers in Vision 8/12	Vision transformers Efficient attention Feature pyramids and necks
Oct 2026	Masked Autoencoders Are Scalable Vision Learners He, Chen, Xie, Li, Dollár, Girshick, 2021	Masked Autoencoders — Hide 75 %, Encode the Rest · Transformers in Vision 10/12	Self-supervised learning Vision transformers
Oct 2026	Learning Transferable Visual Models From Natural Language Supervision Radford et al., 2021	CLIP — Learning Pictures From the Words Next to Them · Transformers in Vision 11/12	Vision and language Contrastive learning Pretraining at scale
Aug 2021	In Defense of the Triplet Loss for Person Re-Identification Hermans, Beyer, Leibe, 2017	In defense of triplet loss for person re-identification by Deval Shah, on VisionWizard ↗	Re-identification Loss functions
Oct 2020	Arbitrary Style Transfer with Style-Attentional Networks Park, Lee, 2018	Insight on Style Attentional Networks (SANet) for Arbitrary Style Transfer by dhwani mehta, on VisionWizard ↗	Generative models Attention modules
Aug 2020	Improving Language Understanding by Generative Pre-Training Radford, Narasimhan, Salimans, Sutskever, 2018	OpenAI’s GPT — Part 1: Unveiling the GPT Model by Yesha R Shastri, on VisionWizard ↗	Language models Transformers Natural language
Aug 2020	PAMTRI: Pose-Aware Multi-Task Learning for Vehicle Re-Identification Using Highly Randomized Synthetic Data Tang et al., 2020	PAMTRI: Pose-Aware Multi-Task Learning for Vehicle Re-Identification Using Highly Randomized Synthetic Data by Deval Shah, on VisionWizard ↗	Re-identification Keypoints and pose Traffic analytics
Aug 2020	Fawkes: Protecting Privacy against Unauthorized Deep Learning Models Shan et al., 2020	Protecting Privacy Using Fawkes Against Unauthorized Surveillance by Vardan Agarwal, on VisionWizard ↗	Faces Image classification
Aug 2020	Instance Shadow Detection Wang, Hu, Wang, Heng, Fu, 2019	LISA: An End-to-End Deep Framework for Instance Shadow Detection by Devshree Patel, on VisionWizard ↗	Segmentation Object detection
Aug 2020	SpinalNet: Deep Neural Network with Gradual Input Kabir et al., 2020	SpinalNet: Deep Neural Network with Gradual Input by Ratnam Parikh, on VisionWizard ↗	Backbone design Image classification
Jul 2020	Dynamic Convolution: Attention over Convolution Kernels Chen et al., 2019	Dynamic Convolution — An Exciting Innovation over Convolution Kernels from Microsoft Research by Yesha R Shastri, on VisionWizard ↗	Convolutions Attention modules Efficient networks
Jul 2020	Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network Lee et al., 2020	Assembled CNN: Trick-o-Tweaks by Mahima Modi, on VisionWizard ↗	Training recipes Backbone design Data augmentation
Jul 2020	DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution Qiao, Chen, Yuille, 2020	DetectoRS — A Comprehensive Review	Feature pyramids and necks Convolutions Object detection
Jul 2020	SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization Du et al., 2019	SpineNet: An Unconventional Backbone Architecture from Google Brain by Yesha R Shastri, on VisionWizard ↗	Backbone design Object detection Feature pyramids and necks
Jul 2020	Automated detection of COVID-19 cases using deep neural networks with X-ray images Ozturk, Talo, Yildirim, Baloglu, Yildirim, Acharya, 2020	DarkCovidNet: Automated detection of COVID-19 with X-ray images by Ratnam Parikh, on VisionWizard ↗	Medical imaging Image classification
Jul 2020	PCL: Proposal Cluster Learning for Weakly Supervised Object Detection Tang et al., 2018	Weakly Supervised Object Detection — An End to End Training Pipeline by Yesha R Shastri, on VisionWizard ↗	Object detection Weak supervision
Jul 2020	SCAN: Learning to Classify Images without Labels Van Gansbeke, Vandenhende, Georgoulis, Proesmans, Van Gool, 2020	Self-Supervised Classification: Semantic Clustering by Adopting Nearest Neighbors by Mahima Modi, on VisionWizard ↗	Self-supervised learning Image classification
Jul 2020	SNIPER: Efficient Multi-Scale Training Singh, Najibi, Davis, 2018	SNIPER: Efficient Multi-Scale Training by Devshree Patel, on VisionWizard ↗	Object detection Training recipes Efficient networks
Jul 2020	ALBERT: A Lite BERT for Self-supervised Learning of Language Representations Lan et al., 2019	Is ALBERT short for BERT? by Marzieh Mehdizadeh, on VisionWizard ↗	Language models Transformers Natural language
Jul 2020	Improving Semantic Segmentation via Video Propagation and Label Relaxation Zhu et al., 2018	Video Semantic Segmentation -A Novel Approach from NVIDIA by Yesha R Shastri, on VisionWizard ↗	Segmentation Video Data augmentation
Jun 2020	Unsupervised Translation of Programming Languages Lachaux, Roziere, Chanussot, Lample, 2020	Facebook AI TransCoder by Devshree Patel, on VisionWizard ↗	Natural language Language models Transformers
Jun 2020	Visual Question Answering on 360{\deg} Images Chou, Chao, Lai, Sun, Yang, 2020	Novel Visual Question Answering system on 360⁰ Images by Ratnam Parikh, on VisionWizard ↗	Vision and language Natural language
Jun 2020	MixConv: Mixed Depthwise Convolutional Kernels Tan, Le, 2019	MixConv — Mixed Depthwise Convolutional Kernels from Google Brain	Convolutions Efficient networks
Jun 2020	Designing Network Design Spaces Radosavovic, Kosaraju, Girshick, He, Dollár, 2020	Simple, Powerful, and Fast— RegNet Architecture from Facebook AI	Backbone design Image classification
Jun 2020	End-to-End Object Detection with Transformers Carion et al., 2020	Revolutionary Object Detection Algorithm from Facebook AI by Deval Shah, on VisionWizard ↗	Object detection Set prediction Transformers
Jun 2020	YOLOv4: Optimal Speed and Accuracy of Object Detection Bochkovskiy, Wang, Liao, 2020	YOLOv4 — Version 1: Bag of Freebies · YOLOv4 2/5 by Deval Shah, on VisionWizard ↗	Object detection Data augmentation Training recipes Loss functions
Jun 2020	YOLOv4: Optimal Speed and Accuracy of Object Detection Bochkovskiy, Wang, Liao, 2020	YOLOv4 — Version 3: Proposed Workflow · YOLOv4 4/5 by Deval Shah, on VisionWizard ↗	Object detection Backbone design Feature pyramids and necks
Jun 2020	CBAM: Convolutional Block Attention Module Woo, Park, Lee, Kweon, 2018 BAM: Bottleneck Attention Module Park, Woo, Lee, Kweon, 2018	Understanding Attention Modules: CBAM and BAM — A Quick Read	Attention modules Backbone design
May 2020	Focal Loss for Dense Object Detection Lin, Goyal, Girshick, He, Dollár, 2017	Understanding Focal Loss —A Quick Read	Loss functions Class imbalance Object detection
May 2020	YOLOv4: Optimal Speed and Accuracy of Object Detection Bochkovskiy, Wang, Liao, 2020	YOLOv4 — Version 4: Final Verdict · YOLOv4 5/5	Object detection Data augmentation Training recipes
May 2020	Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression Zheng et al., 2019	Understanding DIoU Loss — A Quick Read by Mahima Modi, on VisionWizard ↗	Loss functions Object detection Non-maximum suppression
May 2020	YOLOv4: Optimal Speed and Accuracy of Object Detection Bochkovskiy, Wang, Liao, 2020	YOLOv4 — Version 2: Bag of Specials · YOLOv4 3/5	Object detection Attention modules Activation functions Feature pyramids and necks
May 2020	EfficientDet: Scalable and Efficient Object Detection Tan, Pang, Le, 2019	EfficientDet — A Comprehensive Review by Kanan Vyas, on VisionWizard ↗	Object detection Feature pyramids and necks Efficient networks
May 2020	YOLOv4: Optimal Speed and Accuracy of Object Detection Bochkovskiy, Wang, Liao, 2020	YOLOv4 — Version 0: Introduction · YOLOv4 1/5	Object detection Backbone design
May 2020	Objects as Points Zhou, Wang, Krähenbühl, 2019	CenterNet: Objects as Points — A Comprehensive Guide	Anchor-free detection Keypoints and pose Object detection

44 papers, newest first.

Entries marked “on VisionWizard” are by other writers of the publication I ran; they open on Medium under the author's name. The VisionWizard tab lists all of them.

Series

Transformers in Vision · 12 parts, in order

YOLOv4 · 5 parts, in order

RT-DETR · 5 parts, in order