Related papers: SOMA: Feature Gradient Enhanced Affine-Flow Matchi…

Few-shot fine-grained recognition (FS-FGR) aims to recognize novel fine-grained categories with the help of limited available samples. Undoubtedly, this task inherits the main challenges from both few-shot learning and fine-grained…

Image registration is a fundamental medical image analysis task. Ideally, registration should focus on aligning semantically corresponding voxels, i.e., the same anatomical locations. However, existing methods often optimize similarity…

We propose FlowReg, a deep learning-based framework for unsupervised image registration for neuroimaging applications. The system is composed of two architectures that are trained sequentially: FlowReg-A which affinely corrects for gross…

Segment Anything (SAM) has recently pushed the boundaries of segmentation by demonstrating zero-shot generalization and flexible prompting after training on over one billion masks. Despite this, its mask prediction accuracy often falls…

In this work, we propose a novel method to improve the generalization ability of CNN-based face forgery detectors. Our method considers the feature anomalies of forged faces caused by the prevalent blending operations in face forgery…

The primary challenge in video super-resolution (VSR) is to handle large motions in the input frames, which makes it difficult to accurately aggregate information from multiple frames. Existing works either adopt deformable convolutions or…

Video semantic segmentation aims to generate accurate semantic maps for each video frame. To this end, many works dedicate to integrate diverse information from consecutive frames to enhance the features for prediction, where a feature…

In this work, we introduce a fast and accurate method for unsupervised 3D medical image registration. This work is built on top of a recent algorithm SAM, which is capable of computing dense anatomical/semantic correspondences between two…

Deep learning has revolutionized medical image registration by achieving unprecedented speeds, yet its clinical application is hindered by a limited ability to generalize beyond the training domain, a critical weakness given the typically…

Due to the rising awareness of privacy protection and the voluminous scale of speech data, it is becoming infeasible for Automatic Speech Recognition (ASR) system developers to train the acoustic model with complete data as before. For…

The paper investigates the fundamental convergence properties of Sharpness-Aware Minimization (SAM), a recently proposed gradient-based optimization method [Foret et al., 2021] that significantly improves the generalization of deep neural…

Previous deep image registration methods that employ single homography, multi-grid homography, or thin-plate spline often struggle with real scenes containing depth disparities due to their inherent limitations. To address this, we propose…

Medical image registration is a fundamental task in medical image analysis, aiming to establish spatial correspondences between paired images. However, existing unsupervised deformable registration methods rely solely on intensity-based…

Despite the promise of Vision-Language-Action (VLA) models as generalist robotic controllers, their robustness against perceptual noise and environmental variations in out-of-distribution (OOD) tasks remains fundamentally limited by the…

Medical imaging provides many valuable clues involving anatomical structure and pathological characteristics. However, image degradation is a common issue in clinical practice, which can adversely impact the observation and diagnosis by…

Optical and Synthetic Aperture Radar (SAR) image registration is crucial for multi-modal image fusion and applications. However, several challenges limit the performance of existing deep learning-based methods in cross-modal image…

It is commonly believed that gradient compression in federated learning (FL) enjoys significant improvement in communication efficiency with negligible performance degradation. In this paper, we find that gradient compression induces…

Despite its flexibility to learn diverse inductive biases in machine learning programs, meta learning (i.e., learning to learn) has long been recognized to suffer from poor scalability due to its tremendous compute/memory costs, training…

Salient Object Detection (SOD) methods can locate objects that stand out in an image, assign higher values to their pixels in a saliency map, and binarize the map outputting a predicted segmentation mask. A recent tendency is to investigate…

Deep learning-based deformable registration methods have been widely investigated in diverse medical applications. Learning-based deformable registration relies on weighted objective functions trading off registration accuracy and…