DSWoK — Data Science Well of Knowledge
Search
Search
Dark mode
Light mode
Explorer
#cv
3 notes
· co-occurs with
6 tags
· last updated
Jun 22, 2026
Co-tags
#
nlp
1
#
architecture
1
#
multimodal
1
#
pre-trained
1
#
loss
1
#
evaluation
1
Notes tagged
#cv
01
Contrastive Language-Image Pre-training
CLIP (Contrastive Language-Image Pre-training) is a neural net model developed by OpenAI that efficiently learns visual concepts from natural language supervision.
Jun 22, 2026
Deep Learning
02
Computer vision losses
Loss functions commonly used in computer vision tasks. For general losses (Cross-Entropy, MSE, KL Divergence), see General losses.
Jun 22, 2026
Metrics and losses
03
Computer vision metrics
Computer vision metrics evaluate models across detection, segmentation, generation, 3D, and pose estimation tasks.
Jun 22, 2026
Metrics and losses