arXiv (All)
open access
SAGE: Saliency-Annealed Gated Encoder for Universal Vision Recognition
When adapting self-supervised Vision Transformers (ViTs) to dense prediction, existing methods often treat the ViT as a passive feature extractor and may underuse the rich priors encoded in its representations, including saliency, global context, and high-frequency details. We propose SAGE (Saliency
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
- Learning to Discriminate Scene Structures Makes Self-Supervised Depth Learning Scalable#1387865
- Decoding the Functional Roles of Register and High-Norm Patch Tokens in Vision Transformers#1188409
- CODI: Improving Self-Supervised Vision Transformers with Cross Distillation#1423431
- GTR: Gated Token Recurrence for Efficient Dense Prediction#1063007
- GTR: Gated Token Recurrence for Efficient Dense Prediction#1043097
Record · ID 1468043
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