paper-with-me

홈 › Papers

Improving OOD Generalization of Pre-trained Encoders via Aligned Embedding-Space Ensembles

2024-11-20 · Shuman Peng, Arash Khoeini, Sharan Vaswani, Martin Ester

The quality of self-supervised pre-trained embeddings on out-of-distribution (OOD) data is poor without fine-tuning. A straightforward and simple approach to improving the generalization of pre-trained representation to OOD data is the use of deep ensembles. However, obtaining an effective ensemble in the embedding space with only unlabeled data remains an unsolved problem. We first perform a theoretical analysis that reveals the relationship between individual hyperspherical embedding spaces in an ensemble. We then design a principled method to align these embedding spaces in an unsupervised manner. Experimental results on the MNIST dataset show that our embedding-space ensemble method improves pre-trained embedding quality on in-distribution and OOD data compared to single encoders.

📄 PDF Abstract BibTeX arXiv:2411.13073

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

A Mechanism for Producing Aligned Latent Spaces with Autoencoders

2021-06-29 · Saachi Jain, Adityanarayanan Radhakrishnan, Caroline Uhler

Aligned latent spaces, where meaningful semantic shifts in the input space correspond to a translation in the embedding space, play an important role in the success of downstream tasks such as unsupervised clustering and…

ClusteringImputationTranslation

jina-embeddings-v5-omni: Geometry-preserving Embeddings via Locked Aligned Towers

2026-05-08 · Florian Hönicke, Michael Günther, Andreas Koukounas, Mohammad Kalim Akram 외 arxiv

In this work, we introduce GELATO (Geometry-preserving Embeddings via Locked Aligned TOwers), a novel approach to multimodal embedding models. We build on the VLM-style architecture, in which non-text encoders are adapte…

Relating graph auto-encoders to linear models

2022-11-03 · Solveig Klepper, Ulrike Von Luxburg

Graph auto-encoders are widely used to construct graph representations in Euclidean vector spaces. However, it has already been pointed out empirically that linear models on many tasks can outperform graph auto-encoders.…

Inductive Bias

Cross-Linked Variational Autoencoders for Generalized Zero-Shot Learning

2019-03-24 · ICLR Workshop LLD 2019 · Edgar Schönfeld, Sayna Ebrahimi, Samarth Sinha, Trevor Darrell 외

Most approaches in generalized zero-shot learning rely on cross-modal mapping between an image feature space and a class embedding space or on generating artificial image features. However, learning a shared cross-modal …

Few-Shot LearningGeneralized Zero-Shot LearningZero-Shot Learning

Kernel Affine Hull Machines as Compute-Efficient Encoders for Frozen Semantic Spaces

2026-05-01 · Mohit Kumar, Somayeh Kargaran, Bernhard A. Moser, Manuela Geiß arxiv

Transformer-based semantic encoders are effective for retrieval, but in many deployments the recurring bottleneck is online query encoding rather than offline corpus indexing. This paper studies whether, once a strong te…