Related papers: Learning Common and Salient Generative Factors Bet…
Real-world datasets are often biased with respect to key demographic factors such as race and gender. Due to the latent nature of the underlying factors, detecting and mitigating bias is especially challenging for unsupervised machine…
A good metric, which promises a reliable comparison between solutions, is essential for any well-defined task. Unlike most vision tasks that have per-sample ground-truth, image synthesis tasks target generating unseen data and hence are…
We study how to generate captions that are not only accurate in describing an image but also discriminative across different images. The problem is both fundamental and interesting, as most machine-generated captions, despite phenomenal…
We propose a novel ECGAN for the challenging semantic image synthesis task. Although considerable improvements have been achieved by the community in the recent period, the quality of synthesized images is far from satisfactory due to three…
A powerful simulator highly decreases the need for real-world tests when training and evaluating autonomous vehicles. Data-driven simulators flourished with the recent advancement of conditional Generative Adversarial Networks (cGANs),…
Saliency prediction models are constrained by the limited diversity and quantity of labeled data. Standard data augmentation techniques such as rotating and cropping alter scene composition, affecting saliency. We propose a novel data…
Image matting and image harmonization are two important tasks in image composition. Image matting, aiming to achieve foreground boundary details, and image harmonization, aiming to make the background compatible with the foreground, are…
Generative Adversarial Networks (GANs) have recently achieved significant improvement on paired/unpaired image-to-image translation, such as photo$\rightarrow$ sketch and artist painting style transfer. However, existing models can only be…
The rapid advancement of generative models has increased the demand for generated image detectors capable of generalizing across diverse and evolving generation techniques. However, existing methods, including those leveraging pre-trained…
Generating photo-realistic images from a text description is a challenging problem in computer vision. Previous works have shown promising performance to generate synthetic images conditional on text by Generative Adversarial Networks…
Semantic image synthesis, i.e., generating images from user-provided semantic label maps, is an important conditional image generation task as it allows to control both the content as well as the spatial layout of generated images. Although…
Modern vision models excel at general purpose downstream tasks. It is unclear, however, how they may be used for personalized vision tasks, which are both fine-grained and data-scarce. Recent works have successfully applied synthetic data…
In the image classification task, deep neural networks frequently rely on bias attributes that are spuriously correlated with a target class in the presence of dataset bias, resulting in degraded performance when applied to data without…
Recent diagnostic datasets on compositional generalization, such as SCAN (Lake and Baroni, 2018) and COGS (Kim and Linzen, 2020), expose severe problems in models trained from scratch on these datasets. However, in contrast to this poor…
Suffering from the extreme training data imbalance between seen and unseen classes, most of existing state-of-the-art approaches fail to achieve satisfactory results for the challenging generalized zero-shot learning task. To circumvent the…
Deep learning has brought an unprecedented progress in computer vision and significant advances have been made in predicting subjective properties inherent to visual data (e.g., memorability, aesthetic quality, evoked emotions, etc.).…
In medical imaging, image synthesis is the estimation process of one image (sequence, modality) from another image (sequence, modality). Since images with different modalities provide diverse biomarkers and capture various features,…
Difference features obtained by comparing the images of two periods play an indispensable role in the change detection (CD) task. However, a pair of bi-temporal images can exhibit diverse changes, which may cause various difference…
Variational autoencoders are powerful algorithms for identifying dominant latent structure in a single dataset. In many applications, however, we are interested in modeling latent structure and variation that are enriched in a target…
Noise synthesis is a challenging low-level vision task aiming to generate realistic noise given a clean image along with the camera settings. To this end, we propose an effective generative model which utilizes clean features as guidance…