Related papers: Few-Shot Generative Model Adaption via Identity In…

Few-shot image generation aims to generate images of high quality and great diversity with limited data. However, it is difficult for modern GANs to avoid overfitting when trained on only a few images. The discriminator can easily remember…

Multi-person identity-preserving generation requires binding multiple reference faces to specified locations under a text prompt. Strong identity/layout conditions often trigger copy-paste shortcuts and weaken prompt-driven controllability.…

Denoising diffusion probabilistic models (DDPMs) have been proven capable of synthesizing high-quality images with remarkable diversity when trained on large amounts of data. However, to our knowledge, few-shot image generation tasks have…

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, disregarding the inherent…

In this study, we delve into the task of few-shot Generative Domain Adaptation (GDA), which involves transferring a pre-trained generator from one domain to a new domain using only a few reference images. Inspired by the way human brains…

Existing image-to-image transformation approaches primarily focus on synthesizing visually pleasing data. Generating images with correct identity labels is challenging yet much less explored. It is even more challenging to deal with image…

Few-shot image generation, which aims to produce plausible and diverse images for one category given a few images from this category, has drawn extensive attention. Existing approaches either globally interpolate different images or fuse…

This paper considers the domain adaptive person re-identification (re-ID) problem: learning a re-ID model from a labeled source domain and an unlabeled target domain. Conventional methods are mainly to reduce feature distribution gap…

Few-shot object detection (FSOD) has thrived in recent years to learn novel object classes with limited data by transferring knowledge gained on abundant base classes. FSOD approaches commonly assume that both the scarcely provided examples…

Deep neural networks often encounter significant performance drops while facing with domain shifts between training (source) and test (target) data. To address this issue, Test Time Adaptation (TTA) methods have been proposed to adapt…

In this work, we address the challenging task of few-shot and zero-shot 3D point cloud semantic segmentation. The success of few-shot semantic segmentation in 2D computer vision is mainly driven by the pre-training on large-scale datasets…

Adapting pre-trained representations has become the go-to recipe for learning new downstream tasks with limited examples. While literature has demonstrated great successes via representation learning, in this work, we show that substantial…

Cross-domain object detection is challenging, and it involves aligning labeled source and unlabeled target domains. Previous approaches have used adversarial training to align features at both image-level and instance-level. At the instance…

Unsupervised domain adaptation in person re-identification resorts to labeled source data to promote the model training on target domain, facing the dilemmas caused by large domain shift and large camera variations. The non-overlapping…

Few-shot learning aims to recognize novel queries with limited support samples by learning from base knowledge. Recent progress in this setting assumes that the base knowledge and novel query samples are distributed in the same domains,…

Training generative models, such as GANs, on a target domain containing limited examples (e.g., 10) can easily result in overfitting. In this work, we seek to utilize a large source domain for pretraining and transfer the diversity…

Identity-consistent generation has become an important focus in text-to-image research, with recent models achieving notable success in producing images aligned with a reference identity. Yet, the scarcity of large-scale paired datasets…

Drawing on recent advancements in diffusion models for text-to-image generation, identity-preserved personalization has made significant progress in accurately capturing specific identities with just a single reference image. However,…

Cross-domain few-shot segmentation (CD-FSS) aims to segment objects of novel classes in new domains, which is often challenging due to the diverse characteristics of target domains and the limited availability of support data. Most CD-FSS…

Generative data augmentation has demonstrated gains in several vision tasks, but its impact on object re-identification - where preserving fine-grained visual details is essential - remains largely unexplored. In this work, we assess the…