paper-with-me

Papers

Back-Modality: Leveraging Modal Transformation for Data Augmentation

2023-09-21 · NeurIPS 2023 11

We introduce Back-Modality, a novel data augmentation schema predicated on modal transformation. Data from an initial modality undergoes transformation to an intermediate modality, followed by a reverse transformation. This framework serves dual roles. On one hand, it operates as a general data augmentation strategy. On the other hand, it allows for other augmentation techniques, suitable for the intermediate modality, to enhance the initial modality. For instance, data augmentation methods applicable to pure text can be employed to augment images, thereby facilitating the cross-modality of data augmentation techniques. To validate the viability and efficacy of our framework, we proffer three instantiations of Back-Modality: back-captioning, back-imagination, and back-speech. Comprehensive evaluations across tasks such as image classification, sentiment classification, and textual entailment demonstrate that our methods consistently enhance performance under data-scarce circumstances.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

CaReFlow: Cyclic Adaptive Rectified Flow for Multimodal Fusion

2026-02-22 · Sijie Mai, Shiqin Han arxiv

Modality gap significantly restricts the effectiveness of multimodal fusion. Previous methods often use techniques such as diffusion models and adversarial learning to reduce the modality gap, but they typically focus on…

Diff$^2$I2P: Differentiable Image-to-Point Cloud Registration with Diffusion Prior

2025-07-09 · Juncheng Mu, Chengwei Ren, Weixiang Zhang, Liang Pan 외 arxiv

Learning cross-modal correspondences is essential for image-to-point cloud (I2P) registration. Existing methods achieve this mostly by utilizing metric learning to enforce feature alignment across modalities, disregardin…

Point Cloud RegistrationMetric Learning

FIRE: Unsupervised bi-directional inter-modality registration using deep networks

2019-07-11 · Chengjia Wang, Giorgos Papanastasiou, Agisilaos Chartsias, Grzegorz Jacenkow 외

Inter-modality image registration is an critical preprocessing step for many applications within the routine clinical pathway. This paper presents an unsupervised deep inter-modality registration network that can learn t…

Image Registration

How Image Generation Helps Visible-to-Infrared Person Re-Identification?

2022-10-04 · Honghu Pan, Yongyong Chen, Yunqi He, Xin Li 외

Compared to visible-to-visible (V2V) person re-identification (ReID), the visible-to-infrared (V2I) person ReID task is more challenging due to the lack of sufficient training samples and the large cross-modality discrep…

Image GenerationPerson Re-Identification

Generalizable Cross-modality Medical Image Segmentation via Style Augmentation and Dual Normalization

2021-12-21 · CVPR 2022 1 · Ziqi Zhou, Lei Qi, Xin Yang, Dong Ni 외

For medical image segmentation, imagine if a model was only trained using MR images in source domain, how about its performance to directly segment CT images in target domain? This setting, namely generalizable cross-mod…

Domain AdaptationDomain GeneralizationImage SegmentationMedical Image Segmentation+2