TACO VS YOLOX

http://tacodataset.org/ <- Open source dataset if you want to train a classifier, I like this one

Hi, So my project is to do with object detection on trash in the wild on this fairly obscure dataset: http://tacodataset.org/ and I was thinking of applying vision transformers to it for feature extraction. I was thinking of taking the YOLOX implementation and swapping out the backbone with swin transformers and perform bunch of comparisons/experiments for the write up. Sort of like how they applied swin transformers to mask R-CNN here but I am struggling to understand where to begin.

I was wondering if anyone had a script or could point me to one that would be able to convert polygons from image segmentation to bounding boxes for object detection. I am looking to create a trash detector to run on my trash picking up robot. I found the TACO dataset, but it uses segmentation and I just want to start with bounding boxes. Any help would be appreciated.

So I am trying to do my best and train YOLOX for an object detection case using Google Colab.

https://github.com/Megvii-BaseDetection/YOLOX I have only tried the pretrained yolo X nano. I get corner responses even if the inference image is padded with a large margin which is unexpected

* Nice implemention of Yolo that is BSD license (not GPL) https://github.com/Megvii-BaseDetection/YOLOX

I wanted to have a few choices getting localization into image search (index and search time). I immediately thought of using a region proposal network (rpn) from mask-rcnn to create patches that can also be indexed and searched (and add the localisation). I figured it might be somewhat agnostic to classes. I did not want to use mmdetection or detectron2 due to their dependencies and just getting the rpn was not worth it. I was encouraged by the PyTorch native implementations of detection/segmentation models but ended up finding yolox the best.

Megvii-BaseDetection/YOLOX

Modern video can be broken into a series of still problems. AI vision models can make these types of classification in as fast as video. Here is a particularly there is a controversial company from China that does this very well on faces in video and they have open sourced the models: https://github.com/Megvii-BaseDetection/YOLOX

Not really a problem, see results here. Just use yolox_x. Thank you for your attention.

From what I understand the swin transformer outputs a single dimension feature vector and the yolo head takes inputs from 3 different layers from the backbone?? and I think I will need to write the backbone implementation here.