paper-with-me

Papers

Deep Networks With Large Output Spaces

2014-12-23 · Sudheendra Vijayanarasimhan, Jonathon Shlens, Rajat Monga, Jay Yagnik

Deep neural networks have been extremely successful at various image, speech, video recognition tasks because of their ability to model deep structures within the data. However, they are still prohibitively expensive to train and apply for problems containing millions of classes in the output layer. Based on the observation that the key computation common to most neural network layers is a vector/matrix product, we propose a fast locality-sensitive hashing technique to approximate the actual dot product enabling us to scale up the training and inference to millions of output classes. We evaluate our technique on three diverse large-scale recognition tasks and show that our approach can train large-scale models at a faster rate (in terms of steps/total time) compared to baseline methods.

📄 PDF Abstract BibTeX arXiv:1412.7479

Code (0)

등록된 구현이 없습니다.

Tasks

Video Recognition

Similar Papers 제목 키워드 기반

A General Framework for Consistent Structured Prediction with Implicit Loss Embeddings

2020-02-13 · Carlo Ciliberto, Lorenzo Rosasco, Alessandro Rudi

We propose and analyze a novel theoretical and algorithmic framework for structured prediction. While so far the term has referred to discrete output spaces, here we consider more general settings, such as manifolds or s…

Structured Prediction

PECOS: Prediction for Enormous and Correlated Output Spaces

2020-10-12 · Hsiang-Fu Yu, Kai Zhong, Jiong Zhang, Wei-Cheng Chang 외

Many large-scale applications amount to finding relevant results from an enormous output space of potential candidates. For example, finding the best matching product from a large catalog or suggesting related search phr…

Prediction

Learning Representation in Colour Conversion

2021-01-01 · Arash Akbarinia, Raquel Gil-Rodriguez, Alban Flachot, Matteo Toscani

Colours can be represented in an infinite set of spaces highlighting distinct features. In this work, we study the structure of colour representation in variational autoencoders (VAEs) and investigate whether a specific …

image-classificationImage ClassificationScene Segmentation

Neural networks in non-metric spaces

2024-06-13 · Luca Galimberti

Leveraging the infinite dimensional neural network architecture we proposed in arXiv:2109.13512v4 and which can process inputs from Fr\'echet spaces, and using the universal approximation property shown therein, we now l…

Fast Label Embeddings for Extremely Large Output Spaces

2015-03-30 · Paul Mineiro, Nikos Karampatziakis

Many modern multiclass and multilabel problems are characterized by increasingly large output spaces. For these problems, label embeddings have been shown to be a useful primitive that can improve computational and stati…