Models and dataset for the work: "Advancing Compositional Awareness in CLIP with Efficient Fine-Tuning"
Naman Deep Singh
nmndeep
·
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
1 day ago
Robustness in Both Domains: CLIP Needs a Robust Text Encoder
upvoted
a
paper
4 days ago
RePOPE: Impact of Annotation Errors on the POPE Benchmark
updated
a model
8 days ago
nmndeep/CLIC-ViT-B-32-224-PixPr-RedCaps
Organizations
Collections
1
models
22
nmndeep/CLIC-ViT-B-32-224-PixPr-RedCaps
Updated
•
22
nmndeep/CLIC-ViT-L-14-224-PixPr-RedCaps
Updated
•
6
nmndeep/CLIC-CLIPA-ViT-L-14-224-PixPr-RedCaps
Updated
•
6
nmndeep/CLIC-CLIPS-ViT-L-14-224-PixPr-RedCaps
Updated
•
4
nmndeep/20250528T075420
Updated
•
1
nmndeep/20250527T133138
Updated
•
1
nmndeep/20250527T111637
Updated
nmndeep/20250527T081012
Updated
•
3
nmndeep/20250526T215524
Updated
•
1
nmndeep/20250526T194759
Updated
•
5