Related papers: Regularized Training with Generated Datasets for N…

Recently there has been an interest in the potential of learning generative models from a single image, as opposed to from a large dataset. This task is of practical significance, as it means that generative models can be used in domains…

Face presentation attacks have become an increasingly critical concern when face recognition is widely applied. Many face anti-spoofing methods have been proposed, but most of them ignore the generalization ability to unseen attacks. To…

High-quality open-source text-to-image models have lowered the threshold for obtaining photorealistic images significantly, but also face potential risks of misuse. Specifically, suspects may use synthetic data generated by these generative…

Data augmentation is widely used to enhance generalization in visual classification tasks. However, traditional methods struggle when source and target domains differ, as in domain adaptation, due to their inability to address domain gaps.…

Data augmentation is widely used in vision to introduce variation and mitigate overfitting, by enabling models to learn invariant properties. However, augmentation only indirectly captures these properties and does not explicitly constrain…

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…

Vision Transformers (ViTs) often degrade under distribution shifts because they rely on spurious correlations, such as background cues, rather than semantically meaningful features. Existing regularization methods, typically relying on…

Training models to high-end performance requires availability of large labeled datasets, which are expensive to get. The goal of our work is to automatically synthesize labeled datasets that are relevant for a downstream task. We propose…

Deep neural networks often suffer performance drops when test data distribution differs from training data. Domain Generalization (DG) aims to address this by focusing on domain-invariant features or augmenting data for greater diversity.…

While image-text representation learning has become very popular in recent years, existing models tend to lack spatial awareness and have limited direct applicability for dense understanding tasks. For this reason, self-supervised…

Prompt tuning, a recently emerging paradigm, enables the powerful vision-language pre-training models to adapt to downstream tasks in a parameter -- and data -- efficient way, by learning the ``soft prompts'' to condition frozen…

The quality of the latent space in visual tokenizers (e.g., VAEs) is crucial for modern generative models. However, the standard reconstruction-based training paradigm produces a latent space that is biased towards low-level information,…

Single-domain generalized object detection aims to enhance a model's generalizability to multiple unseen target domains using only data from a single source domain during training. This is a practical yet challenging task as it requires the…

Large language models such as BERT and the GPT series started a paradigm shift that calls for building general-purpose models via pre-training on large datasets, followed by fine-tuning on task-specific datasets. There is now a plethora of…

The absence of well-structured large datasets in medical computer vision results in decreased performance of automated systems and, especially, of deep learning models. Domain generalization techniques aim to approach unknown domains from a…

Recent advances in image tokenizers, such as VQ-VAE, have enabled text-to-image generation using auto-regressive methods, similar to language modeling. However, these methods have yet to leverage pre-trained language models, despite their…

Models trained on synthetic images often face degraded generalization to real data. As a convention, these models are often initialized with ImageNet pre-trained representation. Yet the role of ImageNet knowledge is seldom discussed despite…

Foundational vision-language models such as CLIP are becoming a new paradigm in vision, due to their excellent generalization abilities. However, adapting these models for downstream tasks while maintaining their generalization remains a…

This work concerns video-language pre-training and representation learning. In this now ubiquitous training scheme, a model first performs pre-training on paired videos and text (e.g., video clips and accompanied subtitles) from a large…

We introduce LaGTran, a novel framework that utilizes text supervision to guide robust transfer of discriminative knowledge from labeled source to unlabeled target data with domain gaps. While unsupervised adaptation methods have been…