Representational Similarity via Interpretable Visual Concepts
How do two deep neural networks differ in how they arrive at a decision? Measuring the similarity of deep networks has been a long-standing open question. Most existing methods provide a single number to measure the similarity of two networks at a given layer, but give no insight into what makes them similar or dissimilar. We introduce an interpretable representational similarity method (RSVC) to compare two networks. We use RSVC to discover shared and unique visual concepts between two models. We show that some aspects of model differences can be attributed to unique concepts discovered by one model that are not well represented in the other. Finally, we conduct extensive evaluation across different vision model architectures and training protocols to demonstrate its effectiveness.
Code (1)
Similar Papers 제목 키워드 기반
Logit Distance Bounds Representational Similarity
For a broad family of discriminative models that includes autoregressive language models, identifiability results imply that if two models induce the same conditional distributions, then their internal representations ar…
Comparing Deep Neural Nets with UMAP Tour
Neural networks should be interpretable to humans. In particular, there is a growing interest in concepts learned in a layer and similarity between layers. In this work, a tool, UMAP Tour, is built to visually inspect an…
CoCoG: Controllable Visual Stimuli Generation based on Human Concept Representations
A central question for cognitive science is to understand how humans process visual objects, i.e, to uncover human low-dimensional concept representation space from high-dimensional visual stimuli. Generating visual stim…
AI AgentDecision MakingBridging Functional and Representational Similarity via Usable Information
We present a unified framework for quantifying the similarity between representations through the lens of \textit{usable} information, offering a rigorous theoretical and empirical synthesis across three key dimensions. …
On the Complexity of Bayesian Generalization
We consider concept generalization at a large scale in the diverse and natural visual spectrum. Established computational modes (i.e., rule-based or similarity-based) are primarily studied isolated and focus on confined …
Attribute