From image directly output text labels and coordinates of detected objects
From image directly output text labels and coordinates of detected objects
Pix2seq: A Language Modeling Framework for Object Detection
arXiv paper abstract https://arxiv.org/abs/2109.10852
arXiv PDF paper https://arxiv.org/pdf/2109.10852.pdf
... presents Pix2Seq, a simple and generic framework for object detection.
Unlike existing approaches that explicitly integrate prior knowledge about the task, we simply cast object detection as a language modeling task conditioned on the observed pixel inputs.
Object descriptions (e.g., bounding boxes and class labels) are expressed as sequences of discrete tokens, and we train a neural net to perceive the image and generate the desired sequence.
... based mainly on the intuition that if a neural net knows about where and what the objects are, we just need to teach it how to read them out.
Beyond the use of task-specific data augmentations, our approach makes minimal assumptions about the task,
yet it achieves competitive results on the challenging COCO dataset, compared to highly specialized and well optimized detection algorithms.
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
Comments