Login / Signup
SCNet: Enhancing Few-Shot Semantic Segmentation by Self-Contrastive Background Prototypes.
Jiacheng Chen
Bin-Bin Gao
Zongqing Lu
Jing-Hao Xue
Chengjie Wang
Qingmin Liao
Published in:
CoRR (2021)
Keyphrases
</>
semantic segmentation
street scenes
conditional random fields
superpixels
label transfer
scene classification
weakly supervised
bounding box
object categories
object classes
video sequences
image understanding
object class
pascal voc
multiscale
foreground objects
key frames
higher order
viewpoint
training set