paper-with-me

Papers

Deep Matching Autoencoders

2017-11-16 · Tanmoy Mukherjee, Makoto Yamada, Timothy M. Hospedales

Increasingly many real world tasks involve data in multiple modalities or views. This has motivated the development of many effective algorithms for learning a common latent space to relate multiple domains. However, most existing cross-view learning algorithms assume access to paired data for training. Their applicability is thus limited as the paired data assumption is often violated in practice: many tasks have only a small subset of data available with pairing annotation, or even no paired data at all. In this paper we introduce Deep Matching Autoencoders (DMAE), which learn a common latent space and pairing from unpaired multi-modal data. Specifically we formulate this as a cross-domain representation learning and object matching problem. We simultaneously optimise parameters of representation learning auto-encoders and the pairing of unpaired multi-modal data. This framework elegantly spans the full regime from fully supervised, semi-supervised, and unsupervised (no paired data) multi-modal learning. We show promising results in image captioning, and on a new task that is uniquely enabled by our methodology: unsupervised classifier learning.

📄 PDF Abstract BibTeX arXiv:1711.06047

Code (0)

등록된 구현이 없습니다.

Tasks

Image CaptioningRepresentation Learning

Similar Papers 제목 키워드 기반

Manifold-Matching Autoencoders

2026-03-17 · Laurent Cheret, Vincent Létourneau, Isar Nejadgholi, Chris Drummond 외 arxiv

We study a simple unsupervised regularization scheme for autoencoders called Manifold-Matching (MMAE): we align the pairwise distances in the latent space to those of the input data space by minimizing mean squared error…

An Unsupervised Model with Attention Autoencoders for Question Retrieval

2018-03-09 · Minghua Zhang, Yunfang Wu

Question retrieval is a crucial subtask for community question answering. Previous research focus on supervised models which depend heavily on training data and manual feature engineering. In this paper, we propose a nov…

Community Question AnsweringFeature EngineeringQuestion AnsweringRetrieval

Theoretical Insights into the Use of Structural Similarity Index In Generative Models and Inferential Autoencoders

2020-04-04 · Benyamin Ghojogh, Fakhri Karray, Mark Crowley

Generative models and inferential autoencoders mostly make use of $\ell_2$ norm in their optimization objectives. In order to generate perceptually better images, this short paper theoretically discusses how to use Struc…

Dimensionality ReductionImage GenerationImage Quality AssessmentSSIM

Information Theoretic-Learning Auto-Encoder

2016-03-22 · Eder Santana, Matthew Emigh, Jose C. Principe

We propose Information Theoretic-Learning (ITL) divergence measures for variational regularization of neural networks. We also explore ITL-regularized autoencoders as an alternative to variational autoencoding bayes, adv…

Evaluating Sparse Autoencoders: From Shallow Design to Matching Pursuit

2025-06-05 · Valérie Costa, Thomas Fel, Ekdeep Singh Lubana, Bahareh Tolooshams 외

Sparse autoencoders (SAEs) have recently become central tools for interpretability, leveraging dictionary learning principles to extract sparse, interpretable features from neural representations whose underlying structu…

Dictionary Learning