food-recognition-benchmark-starter-kit VS TACO

ℹ️ What's unique? These are real images of real food - not a biased data set downloaded from food websites. The images were collected by participants in the foodandyou_ch study (and released with their consent 🙏). 🖼️ Dataset preview: https://i.imgur.com/BjH4ypx.png 😋 Download and know more about the dataset: https://www.aicrowd.com/challenges/food-recognition-benchmark-2022#datasets 🤖 Pre-trained MMdetection & Detectron2 models on this dataset: https://github.com/AIcrowd/food-recognition-benchmark-starter-kit 🏆 Open Benchmark (if you are interested in the ML part): https://www.aicrowd.com/challenges/food-recognition-benchmark-2022/leaderboards

🤖 Pre-trained MMdetection & Detectron2 models on this dataset: https://github.com/AIcrowd/food-recognition-benchmark-starter-kit

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.