BranchConnect: Image Categorization with Learned Branch Connections
Karim Ahmed Lorenzo Torresani Department of Computer Science, Dartmouth College
Abstract
We introduce an architecture for image categorization that enables the end-to-end learning of separate visual features for the different classes to distinguish. The proposed model consists of a deep CNN shaped like a tree. The stem of the tree includes a sequence of convolutional layers common to all classes. The stem then splits into multiple branches implementing parallel feature extractors, which are ultimately connected to the final classification layer via learned gated connections. These learned gates determine for each individual class the subset of features to use. Such a scheme naturally encourages the learning of a heterogeneous set of specialized features through the separate branches and it allows each class to use the subset of features that are optimal for its recognition. We show the generality of our proposed method by reshaping several popular CNNs from the literature into our proposed architecture. Our experiments on the CIFAR100, CIFAR10, ImageNet, and Synth datasets show that in each case our resulting model yields a substantial improvement in accuracy over the original CNN. Our empirical analysis also suggests that our scheme acts as a form of beneficial regula
中文速览
大规模图像分类任务中，传统CNN让所有类别共用同一套特征表示，既忽略了不同类别之间难易程度的差异，也难以为相似类别学出有针对性的区分特征。本文提出了一种名为BranchConnect的树状多分支CNN架构：网络前段共享一个卷积主干（stem），随后分叉出多条并行的特征提取分支，每个类别通过可学习的门控连接（gated connections）自动选择最适合自己的分支子集，从而为不同类别量身定制专属特征，整个过程以端到端的方式在单一优化目标下完成，无需分阶段预训练。实验在CIFAR10、CIFAR100、ImageNet和Synth四个数据集上将多种主流CNN改造为BranchConnect结构，均取得了显著的精度提升，同时分析表明门控机制还起到了正则化的作用，改善了模型的泛化能力。这项工作的意义在于，它以与训练普通CNN相当的计算代价，让模型同时兼顾"共享底层特征"与"类别专属高层特征"，为处理类别数量庞大、类间难易不均的视觉识别问题提供了一条实用且通用的新思路。
原文 arXiv:1704.06010;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1704.06010v3