GAN- vs. JPEG2000 Image Compression for Distributed Automotive Perception: Higher Peak SNR Does Not Mean Better Semantic Segmentation.
Jonas LöhdefinkAndreas BärNico M. SchmidtFabian HügerPeter SchlichtTim FingscheidtPublished in: CoRR (2019)
Keyphrases
- semantic segmentation
- street scenes
- superpixels
- conditional random fields
- label transfer
- weakly supervised
- scene classification
- jpeg image compression
- hidden markov models
- computer vision
- object categories
- object classes
- small number
- viewpoint
- training data
- generative model
- supervised learning
- object class
- object classification
- color images
- object recognition
- multiscale