Related papers: Metric-aligned Sample Selection and Critical Featu…
Object pose refinement is essential for robust object pose estimation. Previous work has made significant progress towards instance-level object pose refinement. Yet, category-level pose refinement is a more challenging problem due to large…
This study proposes an attention-based statistical distance-guided unsupervised domain adaptation model for multi-class cardiovascular magnetic resonance (CMR) image quality assessment. The proposed model consists of a feature extractor, a…
Reducing the annotation cost of oriented object detection in remote sensing remains a major challenge. Recently, sparse annotation has gained attention for effectively reducing annotation redundancy in densely remote sensing scenes.…
Rotated object detection aims to identify and locate objects in images with arbitrary orientation. In this scenario, the oriented directions of objects vary considerably across different images, while multiple orientations of objects exist…
Oriented object detection has been developed rapidly in the past few years, where rotation equivariance is crucial for detectors to predict rotated boxes. It is expected that the prediction can maintain the corresponding rotation when…
Tiny object detection is becoming one of the most challenging tasks in computer vision because of the limited object size and lack of information. The label assignment strategy is a key factor affecting the accuracy of object detection.…
The uncertainty quantification and error control of classifiers are crucial in many high-consequence decision-making scenarios. We propose a selective classification framework that provides an indecision option for any observations that…
Unsupervised domain adaptation for object detection is a challenging problem with many real-world applications. Unfortunately, it has received much less attention than supervised object detection. Models that try to address this task tend…
Machine learning algorithms have grown in sophistication over the years and are increasingly deployed for real-life applications. However, when using machine learning techniques in practical settings, particularly in high-risk applications…
Despite the great promise of machine-learning algorithms to classify and predict astrophysical parameters for the vast numbers of astrophysical sources and transients observed in large-scale surveys, the peculiarities of the training data…
Object recognition is a key enabler across industry and defense. As technology changes, algorithms must keep pace with new requirements and data. New modalities and higher resolution sensors should allow for increased algorithm robustness.…
Obtaining gold standard annotated data for object detection is often costly, involving human-level effort. Semi-supervised object detection algorithms solve the problem with a small amount of gold-standard labels and a large unlabelled…
Region search is widely used for object localization. Typically, the region search methods project the score of a classifier into an image plane, and then search the region with the maximal score. The recently proposed region search…
Object detection models often struggle with class imbalance, where rare categories appear significantly less frequently than common ones. Existing sampling-based rebalancing strategies, such as Repeat Factor Sampling (RFS) and…
Modern deep neural networks can easily overfit to biased training data containing corrupted labels or class imbalance. Sample re-weighting methods are popularly used to alleviate this data bias issue. Most current methods, however, require…
In recent years, deep learning methods bring incredible progress to the field of object detection. However, in the field of remote sensing image processing, existing methods neglect the relationship between imaging configuration and…
This paper delves into the task of arbitrary modality salient object detection (AM SOD), aiming to detect salient objects from arbitrary modalities, eg RGB images, RGB-D images, and RGB-D-T images. A novel modality-adaptive Transformer…
In remote sensing rotated object detection, mainstream methods suffer from two bottlenecks, directional incoherence at detector neck and task conflict at detecting head. Ulitising fourier rotation equivariance, we introduce Fourier Angle…
Recent real-time detection transformers have gained popularity due to their simplicity and efficiency. However, these detectors do not explicitly model object rotation, especially in remote sensing imagery where objects appear at arbitrary…
Medical image analysis requires substantial labeled data for model training, yet expert annotation is expensive and time-consuming. Active learning (AL) addresses this challenge by strategically selecting the most informative samples for…