paper-with-me

Papers

Bootstrapping Parallel Anchors for Relative Representations

2023-03-01 · Irene Cannistraci, Luca Moschella, Valentino Maiorca, Marco Fumero, Antonio Norelli, Emanuele Rodolà

The use of relative representations for latent embeddings has shown potential in enabling latent space communication and zero-shot model stitching across a wide range of applications. Nevertheless, relative representations rely on a certain amount of parallel anchors to be given as input, which can be impractical to obtain in certain scenarios. To overcome this limitation, we propose an optimization-based method to discover new parallel anchors from a limited known set (seed). Our approach can be used to find semantic correspondence between different domains, align their relative spaces, and achieve competitive results in several tasks.

📄 PDF Abstract BibTeX arXiv:2303.00721

Code (1)

icannistraci/bootstrapping-ao 공식 구현 pytorch

Tasks

Semantic correspondence

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

AnchDrive: Bootstrapping Diffusion Policies with Hybrid Trajectory Anchors for End-to-End Driving

2025-09-24 · Jinhao Chai, Anqing Jiang, Hao Jiang, Shiyi Mu 외 arxiv

End-to-end multi-modal planning has become a transformative paradigm in autonomous driving, effectively addressing behavioral multi-modality and the generalization challenge in long-tail scenarios. We propose AnchDrive, …

Autonomous Driving

Weakly Supervised Vision-and-Language Pre-training with Relative Representations

2023-05-24 · Chi Chen, Peng Li, Maosong Sun, Yang Liu

Weakly supervised vision-and-language pre-training (WVLP), which learns cross-modal representations with limited cross-modal supervision, has been shown to effectively reduce the data cost of pre-training while maintaini…

Retrieval

Improving Relative Representations with Learned Anchors and Whitened Inner Products

2026-05-28 · Oscar Thorsted Svendsen, Nikolaj Holst Jakobsen, Fabian Mager, Hiba Nassar arxiv

Independently trained neural models typically converge to incompatible latent representations, creating a fundamental barrier to highly modular AI systems. While Relative Representations (RR) address this by mapping abso…

Relative Representations of Latent Spaces enable Efficient Semantic Channel Equalization

2024-11-29 · Tomás Hüttebräucker, Simone Fiorellino, Mohamed Sana, Paolo Di Lorenzo 외

In multi-user semantic communication, language mismatche poses a significant challenge when independently trained agents interact. We present a novel semantic equalization algorithm that enables communication between age…

Semantic Communication

Instant Learning: Parallel Deep Neural Networks and Convolutional Bootstrapping

2015-05-22 · Andrew J. R. Simpson

Although deep neural networks (DNN) are able to scale with direct advances in computational power (e.g., memory and processing speed), they are not well suited to exploit the recent trends for parallel architectures. In …