Related papers: HIH: Towards More Accurate Face Alignment via Heat…
Biological systems often exhibit a heterogeneous arrangement of objects, such as assorted nuclear chromatin patterns in a tumor, assorted species of bacteria in biofilms, or assorted aggregates of subcellular particles. Principle Component…
Dataset Condensation (DC) aims to obtain a condensed dataset that allows models trained on the condensed dataset to achieve performance comparable to those trained on the full dataset. Recent DC approaches increasingly focus on encoding…
Wide Area Motion Imagery (WAMI) yields high-resolution images with a large number of extremely small objects. Target objects have large spatial displacements throughout consecutive frames. This nature of WAMI images makes object tracking…
Heterogeneous Face Recognition (HFR) aims at matching face images captured across different sensing modalities, such as thermal-to-visible or near-infrared-to-visible, enhancing the usability of face recognition systems in challenging…
In the field of human pose estimation, regression-based methods have been dominated in terms of speed, while heatmap-based methods are far ahead in terms of performance. How to take advantage of both schemes remains a challenging problem.…
The homography matrix is a key component in various vision-based robotic tasks. Traditionally, homography estimation algorithms are classified into feature- or intensity-based. The main advantages of the latter are their versatility,…
Heterogeneity of both the source and target objects is taken into account in a network-based algorithm for the directional resource transformation between objects. Based on a biased heat conduction recommendation method (BHC) which…
The volume-wise labeling of 3D medical images is expertise-demanded and time-consuming; hence semi-supervised learning (SSL) is highly desirable for training with limited labeled data. Imbalanced class distribution is a severe problem that…
In keypoint estimation tasks such as human pose estimation, heatmap-based regression is the dominant approach despite possessing notable drawbacks: heatmaps intrinsically suffer from quantization error and require excessive computation to…
Accurate identification and localization of the vertebrae in CT scans is a critical and standard preprocessing step for clinical spinal diagnosis and treatment. Existing methods are mainly based on the integration of multiple neural…
Deep learning has recently gained popularity in digital pathology due to its high prediction quality. However, the medical domain requires explanation and insight for a better understanding beyond standard quantitative performance…
Instance-level image classification tasks have traditionally relied on single-instance labels to train models, e.g., few-shot learning and transfer learning. However, set-level coarse-grained labels that capture relationships among…
Contemporary image generation systems have achieved high fidelity and superior aesthetic quality beyond basic text-image alignment. However, existing evaluation frameworks have failed to evolve in parallel. This study reveals that human…
Few-shot learning is an established topic in natural images for years, but few work is attended to histology images, which is of high clinical value since well-labeled datasets and rare abnormal samples are expensive to collect. Here, we…
The problem of counterfactual visual explanations is considered. A new family of discriminant explanations is introduced. These produce heatmaps that attribute high scores to image regions informative of a classifier prediction but not of a…
High-resolution remote sensing image semantic segmentation (HRSS) is a fundamental yet critical task in the field of Earth observation. However, it has long faced the challenges of high inter-class similarity and large intra-class…
Estimating homography from a single image remains a challenging yet practically valuable task, particularly in domains like retail, where only one viewpoint is typically available for shelf monitoring and product alignment. In this paper,…
The rapid development of large climate models has created the requirement of storing and transferring massive atmospheric data worldwide. Therefore, data compression is essential for meteorological research, but an efficient compression…
Due to their large sizes, volumetric scans and whole-slide pathology images (WSIs) are often processed by extracting embeddings from local regions and then an aggregator makes predictions from this set. However, current methods require…
In this paper, we propose an end-to-end trainable regression approach for human pose estimation from still images. We use the proposed Soft-argmax function to convert feature maps directly to joint coordinates, resulting in a fully…