paper-with-me

홈 › Papers

On Invariance in Hierarchical Models

2009-12-01 · NeurIPS 2009 12 · Jake Bouvrie, Lorenzo Rosasco, Tomaso Poggio

A goal of central importance in the study of hierarchical models for object recognition -- and indeed the visual cortex -- is that of understanding quantitatively the trade-off between invariance and selectivity, and how invariance and discrimination properties contribute towards providing an improved representation useful for learning from data. In this work we provide a general group-theoretic framework for characterizing and understanding invariance in a family of hierarchical models. We show that by taking an algebraic perspective, one can provide a concise set of conditions which must be met to establish invariance, as well as a constructive prescription for meeting those conditions. Analyses in specific cases of particular relevance to computer vision and text processing are given, yielding insight into how and when invariance can be achieved. We find that the minimal sets of transformations intrinsic to the hierarchical model needed to support a particular invariance can be clearly described, thereby encouraging efficient computational implementations.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Object Recognition

Similar Papers 제목 키워드 기반

Emergence of Selective Invariance in Hierarchical Feed Forward Networks

2017-01-30 · Dipan K. Pal, Vishnu Boddeti, Marios Savvides

Many theories have emerged which investigate how in- variance is generated in hierarchical networks through sim- ple schemes such as max and mean pooling. The restriction to max/mean pooling in theoretical and empirical …

Object Categorization

Hierarchical Invariance for Robust and Interpretable Vision Tasks at Larger Scales

2024-02-23 · Shuren Qi, Yushu Zhang, Chao Wang, Zhihua Xia 외

Developing robust and interpretable vision systems is a crucial step towards trustworthy artificial intelligence. In this regard, a promising paradigm considers embedding task-required invariant structures, e.g., geometr…

Neural Architecture Search

How ConvNets model Non-linear Transformations

2017-02-24 · Dipan K. Pal, Marios Savvides

In this paper, we theoretically address three fundamental problems involving deep convolutional networks regarding invariance, depth and hierarchy. We introduce the paradigm of Transformation Networks (TN) which are a di…

model

Hierarchically Decoupled Spatial-Temporal Contrast for Self-supervised Video Representation Learning

2020-11-23 · Zehua Zhang, David Crandall

We present a novel technique for self-supervised video representation learning by: (a) decoupling the learning objective into two contrastive subtasks respectively emphasizing spatial and temporal features, and (b) perfo…

Action RecognitionContrastive LearningRepresentation Learning

Bayesian Hierarchical Invariant Prediction

2025-05-16 · Francisco Madaleno, Pernille Julie Viuff Sand, Francisco C. Pereira, Sergio Hernan Garrido Mejia

We propose Bayesian Hierarchical Invariant Prediction (BHIP) reframing Invariant Causal Prediction (ICP) through the lens of Hierarchical Bayes. We leverage the hierarchical structure to explicitly test invariance of cau…

Prediction