arXiv (All)
open access
Breaking the Geometric Bottleneck: Contrastive Expansion in Asymmetric Cross-Modal Distillation
Knowledge distillation between asymmetric architectures often induces severe geometric constraints on the learned representation space. We investigate dimensional collapse when distilling global Vision Transformers into capacity-constrained, local-receptive-field CNNs (0.5M-8.0M parameters). Using s
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Robust Knowledge Distillation for Resource-Constrained Applications: Evaluating Offline KD Techniques for Large–Compact Heterogeneous CNNs#448476
- Disentangling Representation Evolution in Transformers through Directional Decomposition#1110000
- Learning reshapes power-law anisotropy in internal representations#612658
- Learning reshapes power-law anisotropy in internal representations#611181
- TOWARDS DATA-EFFICIENT DEEP LEARNING#254778
Record · ID 821804
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive