paper-with-me

홈 › Papers

Unpaired Image Translation via Vector Symbolic Architectures

2022-09-06 · Justin Theiss, Jay Leverett, Daeil Kim, Aayush Prakash

Image-to-image translation has played an important role in enabling synthetic data for computer vision. However, if the source and target domains have a large semantic mismatch, existing techniques often suffer from source content corruption aka semantic flipping. To address this problem, we propose a new paradigm for image-to-image translation using Vector Symbolic Architectures (VSA), a theoretical framework which defines algebraic operations in a high-dimensional vector (hypervector) space. We introduce VSA-based constraints on adversarial learning for source-to-target translations by learning a hypervector mapping that inverts the translation to ensure consistency with source content. We show both qualitatively and quantitatively that our method improves over other state-of-the-art techniques.

📄 PDF Abstract BibTeX arXiv:2209.02686

Code (1)

facebookresearch/vsait 공식 구현 pytorch

Tasks

Image-to-Image TranslationTranslation

Similar Papers 제목 키워드 기반

Show, Attend and Translate: Unpaired Multi-Domain Image-to-Image Translation with Visual Attention

2018-11-19 · Honglun Zhang, Wenqing Chen, Jidong Tian, Yongkun Wang 외

Recently unpaired multi-domain image-to-image translation has attracted great interests and obtained remarkable progress, where a label vector is utilized to indicate multi-domain information. In this paper, we propose S…

AttributeGenerative Adversarial NetworkImage-to-Image TranslationTranslation

Paired and Unpaired Image to Image Translation using Generative Adversarial Networks

2025-05-22 · Gaurav Kumar, Soham Satyadharma, Harpreet Singh

Image to image translation is an active area of research in the field of computer vision, enabling the generation of new images with different styles, textures, or resolutions while preserving their characteristic proper…

Image-to-Image TranslationTranslation

CrossNet: Latent Cross-Consistency for Unpaired Image Translation

2019-01-14 · Omry Sendik, Dani Lischinski, Daniel Cohen-Or

Recent GAN-based architectures have been able to deliver impressive performance on the general task of image-to-image translation. In particular, it was shown that a wide variety of image translation operators may be lea…

Image-to-Image TranslationTranslation

DSI2I: Dense Style for Unpaired Image-to-Image Translation

2022-12-26 · Baran Ozaydin, Tong Zhang, Sabine Süsstrunk, Mathieu Salzmann

Unpaired exemplar-based image-to-image (UEI2I) translation aims to translate a source image to a target image domain with the style of a target image exemplar, without ground-truth input-translation pairs. Existing UEI2I…

Image-to-Image TranslationTranslation

Music Transcription with (Almost) No Supervision

2026-05-22 · Saebyeol Shin, Chao Wan, Zhenzhen Liu, Justin Lovelace 외 arxiv

Competitive music transcription models require large amounts of paired audio-score data, which is scarce due to collection costs, alignment difficulty, and copyright restrictions. Meanwhile, vast quantities of unpaired a…

Music Transcription