paper-with-me

Papers

RADIO Amplified: Improved Baselines for Agglomerative Vision Foundation Models

2024-12-10 · Greg Heinrich, Mike Ranzinger, Hongxu, Yin, Yao Lu, Jan Kautz, Andrew Tao, Bryan Catanzaro, Pavlo Molchanov

Agglomerative models have recently emerged as a powerful approach to training vision foundation models, leveraging multi-teacher distillation from existing models such as CLIP, DINO, and SAM. This strategy enables the efficient creation of robust models, combining the strengths of individual teachers while significantly reducing computational and resource demands. In this paper, we thoroughly analyze state-of-the-art agglomerative models, identifying critical challenges including resolution mode shifts, teacher imbalance, idiosyncratic teacher artifacts, and an excessive number of output tokens. To address these issues, we propose several novel solutions: multi-resolution training, mosaic augmentation, and improved balancing of teacher loss functions. Specifically, in the context of Vision Language Models, we introduce a token compression technique to maintain high-resolution information within a fixed token count. We release our top-performing models, available in multiple scales (-B, -L, -H, and -g), alongside inference code and pretrained weights.

📄 PDF Abstract BibTeX arXiv:2412.07679

Code (1)

nvlabs/radio 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Residual Connection 설명 없음
Multi-Head Attention 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Vision Transformer The Vision Transformer, or ViT, is a model for image classification that employs a Transformer-like architecture over…

Similar Papers 제목 키워드 기반

RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models

2025-01-01 · CVPR 2025 1 · Greg Heinrich, Mike Ranzinger, Hongxu Yin, Yao Lu 외

Agglomerative models have recently emerged as a powerful approach to training vision foundation models, leveraging multi-teacher distillation from existing models such as CLIP, DINO, and SAM. This strategy enables th…

RADSeg: Unleashing Parameter and Compute Efficient Zero-Shot Open-Vocabulary Segmentation Using Agglomerative Models

2025-11-24 · Omar Alama, Darshil Jariwala, Avigyan Bhattacharya, Seungchan Kim 외 arxiv

Open-vocabulary semantic segmentation (OVSS) underpins many vision and robotics tasks that require generalizable semantic understanding. Existing approaches either rely on limited segmentation training data, which hinder…

Semantic Segmentation

AM-RADIO: Agglomerative Vision Foundation Model -- Reduce All Domains Into One

2023-12-10 · Mike Ranzinger, Greg Heinrich, Jan Kautz, Pavlo Molchanov

A handful of visual foundation models (VFMs) have recently emerged as the backbones for numerous downstream tasks. VFMs like CLIP, DINOv2, SAM are trained with distinct objectives, exhibiting unique characteristics for v…

AllBenchmarkingobject-detectionObject Detection+1

AM-RADIO: Agglomerative Vision Foundation Model Reduce All Domains Into One

2024-01-01 · CVPR 2024 1 · Mike Ranzinger, Greg Heinrich, Jan Kautz, Pavlo Molchanov

A handful of visual foundation models (VFMs) have recently emerged as the backbones for numerous downstream tasks. VFMs like CLIP DINOv2 SAM are trained with distinct objectives exhibiting unique characteristics for …

AllBenchmarkingobject-detectionObject Detection+1

C-RADIOv4 (Tech Report)

2026-01-24 · Mike Ranzinger, Greg Heinrich, Collin McCarthy, Jan Kautz 외 arxiv

By leveraging multi-teacher distillation, agglomerative vision backbones provide a unified student model that retains and improves the distinct capabilities of multiple teachers. In this tech report, we describe the most…