Survey benchmarks SSL instance discrimination and masked image modeling for object detection, finding instance discrimination suits CNN encoders while MIM suits ViT encoders and custom pre-training, especially for small objects.
Unsupervised object-level representation learning from scene images,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Self-Supervised Learning for Real-World Object Detection: a Survey
Survey benchmarks SSL instance discrimination and masked image modeling for object detection, finding instance discrimination suits CNN encoders while MIM suits ViT encoders and custom pre-training, especially for small objects.