Related papers: Improving Representation of High-frequency Compone…
Most image labeling problems such as segmentation and image reconstruction are fundamentally ill-posed and suffer from ambiguities and noise. Higher order image priors encode high level structural dependencies between pixels and are key to…
Many healthcare applications are inherently multimodal, involving several physiological signals. As sensors for these signals become more common, improving machine learning methods for multimodal healthcare data is crucial. Pretraining…
Magnetic resonance imaging (MRI) plays a vital role in clinical diagnostics, yet it remains hindered by long acquisition times and motion artifacts. Multi-contrast MRI reconstruction has emerged as a promising direction by leveraging…
Foundation models pre-trained on large-scale natural image datasets offer a powerful paradigm for medical image segmentation. However, effectively transferring their learned representations for precise clinical applications remains a…
Attention mechanisms have emerged as important tools that boost the performance of deep models by allowing them to focus on key parts of learned embeddings. However, current attention mechanisms used in speaker recognition tasks fail to…
Neural fields excel in computer vision and robotics due to their ability to understand the 3D visual world such as inferring semantics, geometry, and dynamics. Given the capabilities of neural fields in densely representing a 3D scene from…
In this paper, we introduce MaeFuse, a novel autoencoder model designed for Infrared and Visible Image Fusion (IVIF). The existing approaches for image fusion often rely on training combined with downstream tasks to obtain highlevel visual…
Accurate segmentation of tumors and adjacent normal tissues in medical images is essential for surgical planning and tumor staging. Although foundation models generally perform well in segmentation tasks, they often struggle to focus on…
Recent advances in the masked autoencoder (MAE) paradigm have significantly propelled self-supervised skeleton-based action recognition. However, most existing approaches limit reconstruction targets to raw joint coordinates or their simple…
We present an efficient frequency-based neural representation termed PREF: a shallow MLP augmented with a phasor volume that covers significant border spectra than previous Fourier feature mapping or Positional Encoding. At the core is our…
Existing X-ray based pre-trained vision models are usually conducted on a relatively small-scale dataset (less than 500k samples) with limited resolution (e.g., 224 $\times$ 224). However, the key to the success of self-supervised…
Transformer-based foundation models (FMs) have recently demonstrated remarkable performance in medical image segmentation. However, scaling these models is challenging due to the limited size of medical image datasets within isolated…
Visual generative models (e.g., diffusion models) typically operate in compressed latent spaces to balance training efficiency and sample quality. In parallel, there has been growing interest in leveraging high-quality pre-trained visual…
The primary challenge in accelerating image super-resolution lies in reducing computation while maintaining performance and adaptability. Motivated by the observation that high-frequency regions (e.g., edges and textures) are most critical…
Detecting 3D objects accurately from multi-view 2D images is a challenging yet essential task in the field of autonomous driving. Current methods resort to integrating depth prediction to recover the spatial information for object query…
Implicit Neural Representations (INRs) have recently gained attention as a powerful approach for continuously representing signals such as images, videos, and 3D shapes using multilayer perceptrons (MLPs). However, MLPs are known to exhibit…
Masked Image Modeling (MIM) has garnered significant attention in self-supervised learning, thanks to its impressive capacity to learn scalable visual representations tailored for downstream tasks. However, images inherently contain…
Multimodal pretraining is effective for building general-purpose representations, but in many practical deployments, only one modality is heavily used during downstream fine-tuning. Standard pretraining strategies treat all modalities…
We study universal deepfake detection. Our goal is to detect synthetic images from a range of generative AI approaches, particularly from emerging ones which are unseen during training of the deepfake detector. Universal deepfake detection…
The recently developed and publicly available synthetic image generation methods and services make it possible to create extremely realistic imagery on demand, raising great risks for the integrity and safety of online information.…