DCLIP fine-tunes a CLIP student's image encoder to match a YOLO-region, bidirectional cross-attention teacher, improving retrieval while retaining most zero-shot accuracy.
Inverse problems of inhomogeneous fracture toughness using phase-field models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We propose inverse problems of crack propagation using the phase-field models. First, we study the crack propagation in an inhomogeneous media in which fracture toughness varies in space. Using the two phase-field models based on different surface energy functionals, we perform simulations of the crack propagation and show that the $J$-integral reflects the effective inhomogeneous toughness. Then, we formulate regression problems to estimate space-dependent fracture toughness from the crack path. Our method successfully estimates the positions and magnitude of tougher regions. We also demonstrate that our method works for different geometry of inhomogeneity.
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Distill CLIP (DCLIP): Enhancing Image-Text Retrieval via Cross-Modal Transformer Distillation
DCLIP fine-tunes a CLIP student's image encoder to match a YOLO-region, bidirectional cross-attention teacher, improving retrieval while retaining most zero-shot accuracy.