Detr, or Detection Transformer, is a set-based object detector using a Transformer on top of a convolutional backbone. It uses a conventional CNN backbone to learn a 2D representation of an input image. The model flattens it and supplements it with a positional encoding before passing it into a transformer encoder. A transformer decoder then takes as input a small fixed number of learned positional embeddings, which we call object queries, and additionally attends to the encoder output. We pass each output embedding of the decoder to a shared feed forward network (FFN) that predicts either a detection (class and bounding box) or a “no object” class.
Source: End-to-End Object Detection with TransformersPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Object Detection | 108 | 34.73% |
Semantic Segmentation | 12 | 3.86% |
Instance Segmentation | 10 | 3.22% |
Image Classification | 7 | 2.25% |
2D Object Detection | 6 | 1.93% |
Few-Shot Object Detection | 6 | 1.93% |
Autonomous Driving | 5 | 1.61% |
Real-Time Object Detection | 5 | 1.61% |
Semi-Supervised Object Detection | 5 | 1.61% |
Component | Type |
|
---|---|---|
Convolution
|
Convolutions | |
Feedforward Network
|
Feedforward Networks | |
ResNet
|
Convolutional Neural Networks | (optional) |
Transformer
|
Transformers |