End To End Training For Object Detection

via “end-to-end transformer-based object detection with resnet-101 backbone”

object-detection model by undefined. 63,737 downloads.

Unique: Uses transformer encoder-decoder with bipartite matching loss instead of anchor-based region proposals or sliding windows, eliminating hand-crafted NMS and enabling direct set prediction of objects as a sequence-to-sequence problem

vs others: Simpler pipeline than Faster R-CNN (no RPN, no NMS) and more interpretable than YOLO, but slower inference due to transformer quadratic complexity compared to single-stage detectors

via “end-to-end training for object detection”

object-detection model by undefined. 38,839 downloads.

Unique: Facilitates a streamlined training process by integrating classification and localization into a single loss function, enhancing efficiency.

vs others: More efficient than traditional multi-stage training processes that require separate training for classification and localization.

via “object detection and instance segmentation with convolutional architectures”


Unique: Provides fastai wrappers around Faster R-CNN and Mask R-CNN that simplify the two-stage detection pipeline, handling region proposal generation, anchor matching, and loss computation automatically. Includes utilities for converting between annotation formats and visualizing predictions with bounding boxes and masks.

vs others: Faster to prototype object detection systems than implementing Faster R-CNN from scratch in PyTorch; includes pre-trained backbones (ResNet, EfficientNet) for transfer learning on custom datasets.