Research map / Vision-language and multimodal / Multimodal LLMs
DnA: Denoising Attention for Visual Tasks
Ron Campos, Subhajit Maity, Xin Li, Srijan Das, Aritra Dutta
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| replace softmax attention with Denoising Attention (positive and negative query, two subspaces) | ViT-B · ImageNet-1K | accuracy: +0.8% | Improved |
| replace softmax attention with Denoising Attention | video transformers · video understanding | accuracy: 1.8% | Improved |
| replace softmax attention with Denoising Attention | video LLMs · video understanding | accuracy: 0.5% | Improved |
Closest papers by meaning
- Bridging the Divide: Reconsidering Softmax and Linear Attention (NeurIPS 2024 · similarity 0.86)
- Degrees of Freedom for Linear Attention: Distilling Softmax Attention with Optimal Feature Efficiency (NeurIPS 2025 · similarity 0.85)
- MimiQ: Low-Bit Data-Free Quantization of Vision Transformers with Encouraging Inter-Head Attention Similarity (AAAI 2025 · similarity 0.85)
- Rethinking Reconstruction and Denoising in the Dark: New Perspective, General Architecture and Beyond (CVPR 2025 · similarity 0.85)
- Attention-Only Transformers via Unrolled Subspace Denoising (ICML 2025 · similarity 0.85)
- In-Context Denoising with One-Layer Transformers: Connections between Attention and Associative Memory Retrieval (ICML 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
