Related papers: Uncertainty-Aware ControlNet: Bridging Domain Gaps…

Though remarkable progress has been achieved in various vision tasks, deep neural networks still suffer obvious performance degradation when tested in out-of-distribution scenarios. We argue that the feature statistics (mean and standard…

Recent generative adversarial networks (GANs) are able to generate impressive photo-realistic images. However, controllable generation with GANs remains a challenging research problem. Achieving controllable generation requires semantically…

ControlNet has enabled detailed spatial control in text-to-image diffusion models by incorporating additional visual conditions such as depth or edge maps. However, its effectiveness heavily depends on the availability of visual conditions…

We present ControlNet, a neural network architecture to add spatial conditioning controls to large, pretrained text-to-image diffusion models. ControlNet locks the production-ready large diffusion models, and reuses their deep and robust…

Diffusion models are a powerful class of generative models capable of producing high-quality images from pure noise using a simple text prompt. While most methods which introduce additional spatial constraints into the generated images…

Anomaly awareness is an essential capability for safety-critical applications such as autonomous driving. While recent progress of robotics and computer vision has enabled anomaly detection for image classification, anomaly detection on…

Anomaly detection is a practical and challenging task due to the scarcity of anomaly samples in industrial inspection. Some existing anomaly detection methods address this issue by synthesizing anomalies with noise or external data.…

The usage of medical image data for the training of large-scale machine learning approaches is particularly challenging due to its scarce availability and the costly generation of data annotations, typically requiring the engagement of…

Coupling the high-fidelity generation capabilities of label-conditional image synthesis methods with the flexibility of unconditional generative models, we propose a semantic bottleneck GAN model for unconditional synthesis of complex…

In this paper, we propose a novel mutual consistency network (MC-Net+) to effectively exploit the unlabeled data for semi-supervised medical image segmentation. The MC-Net+ model is motivated by the observation that deep models trained with…

Deep learning has shown remarkable performance in medical image segmentation. However, despite its promise, deep learning has many challenges in practice due to its inability to effectively transition to unseen domains, caused by the…

Preparing training data for deep vision models is a labor-intensive task. To address this, generative models have emerged as an effective solution for generating synthetic data. While current generative models produce image-level category…

Our ability to sample realistic natural images, particularly faces, has advanced by leaps and bounds in recent years, yet our ability to exert fine-tuned control over the generative process has lagged behind. If this new technology is to…

The high cost of pixel-level annotations makes it appealing to train saliency detection models with weak supervision. However, a single weak supervision source usually does not contain enough information to train a well-performing model. To…

For semi-supervised learning with imbalance classes, the long-tailed distribution of data will increase the model prediction bias toward dominant classes, undermining performance on less frequent classes. Existing methods also face…

Most existing works in few-shot learning rely on meta-learning the network on a large base dataset which is typically from the same domain as the target dataset. We tackle the problem of cross-domain few-shot learning where there is a large…

Existing weakly or semi-supervised semantic segmentation methods utilize image or box-level supervision to generate pseudo-labels for weakly labeled images. However, due to the lack of strong supervision, the generated pseudo-labels are…

Recent remarkable advances in large-scale text-to-image diffusion models have inspired a significant breakthrough in text-to-3D generation, pursuing 3D content creation solely from a given text prompt. However, existing text-to-3D…

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…

We present a method for image-based crowd counting, one that can predict a crowd density map together with the uncertainty values pertaining to the predicted density map. To obtain prediction uncertainty, we model the crowd density values…