Rosetta Neurons: Mining the Common Units in a Model Zoo

2023-06-15 · ICCV 2023 1 · Amil Dravid, Yossi Gandelsman, Alexei A. Efros, Assaf Shocher

Do different neural networks, trained for various vision tasks, share some common representations? In this paper, we demonstrate the existence of common features we call "Rosetta Neurons" across a range of models with different architectures, different tasks (generative and discriminative), and different types of supervision (class-supervised, text-supervised, self-supervised). We present an algorithm for mining a dictionary of Rosetta Neurons across several popular vision models: Class Supervised-ResNet50, DINO-ResNet50, DINO-ViT, MAE, CLIP-ResNet50, BigGAN, StyleGAN-2, StyleGAN-XL. Our findings suggest that certain visual concepts and structures are inherently embedded in the natural world and can be learned by different models regardless of the specific task or architecture, and without the use of semantic labels. We can visualize shared concepts directly due to generative models included in our analysis. The Rosetta Neurons facilitate model-to-model translation enabling various inversion-based manipulations, including cross-class alignments, shifting, zooming, and more, without the need for specialized training.

📄 PDF Abstract BibTeX arXiv:2306.09346

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Six Ways To Communicate To Someone At Expedia Via Phone And Email's. To communicate or get human at Expedia, the quickest option is typically to call their customer service at ＋１－８８８－８２９－０８８１　ｏｒ　＋１（８０５）　３３０　（４０５６）. You can also use the live chat…

BigGAN BigGAN is a type of generative adversarial network that was designed for scaling generation to high-resolution, high-fidelity images. It includes a number of incremental…

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…

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…

Residual Connection 설명 없음

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 $x$…

Adam 설명 없음

Neuron Populations Exhibit Divergent Selectivity with Scale

2026-06-02 · Amil Dravid, Yasaman Bahri, Alexei A. Efros, Yossi Gandelsman arxiv

We investigate whether neuron populations within neural networks evolve predictably with scale, extending scaling laws beyond macroscopic observables such as loss. To probe this question, we study Rosetta Neurons, a prev…

From Rosetta to Match-Up: A Paired Corpus of Linguistic Puzzles with Human and LLM Benchmarks

2026-05-13 · Neh Majmudar, Anne Huang, Jinfan Frank Hu, Elena Filatova arxiv

In this paper, we examine linguistic puzzles used in high school linguistics competitions, focusing on two common formats: Rosetta Stone and Match-Up. We propose a systematic procedure for converting existing Rosetta Sto…

Simple End-to-end Deep Learning Model for CDR-H3 Loop Structure Prediction

2021-11-20 · Natalia Zenkova, Ekaterina Sedykh, Tatiana Shugaeva, Vladislav Strashko 외

Predicting a structure of an antibody from its sequence is important since it allows for a better design process of synthetic antibodies that play a vital role in the health industry. Most of the structure of an antibody…

The Rosetta Paradox: Domain-Specific Performance Inversions in Large Language Models

2024-12-09 · Basab Jha, Ujjwal Puri

While large language models, such as GPT and BERT, have already demonstrated unprecedented skills in everything from natural language processing to domain-specific applications, there came an unexplored phenomenon we ter…

Common Sense Reasoning Specificity

Compete to Compute

2013-12-01 · NeurIPS 2013 12 · Rupesh K. Srivastava, Jonathan Masci, Sohrob Kazerounian, Faustino Gomez 외

Local competition among neighboring neurons is common in biological neural networks (NNs). We apply the concept to gradient-based, backprop-trained artificial multilayer NNs. NNs with competing linear units tend to outpe…