Related papers: Generalized Mask-aware IoU for Anchor Assignment f…
Loss functions is a crucial factor that affecting the detection precision in object detection task. In this paper, we optimize both two loss functions for classification and localization simultaneously. Firstly, by multiplying an IoU-based…
Accurate pedestrian classification and localization have received considerable attention due to their wide applications such as security monitoring, autonomous driving, etc. Although pedestrian detectors have made great progress in recent…
Instance segmentation requires a large number of training samples to achieve satisfactory performance and benefits from proper data augmentation. To enlarge the training set and increase the diversity, previous methods have investigated…
Modeling temporal information for both detection and tracking in a unified framework has been proved a promising solution to video instance segmentation (VIS). However, how to effectively incorporate the temporal information into an online…
Intraoperative ultrasound (ioUS) is a valuable tool in brain tumor surgery due to its versatility, affordability, and seamless integration into the surgical workflow. However, its adoption remains limited, primarily because of the…
Prompt tuning adapts Vision-Language Models like CLIP to open-world tasks with minimal training costs. In this direction, one typical paradigm evaluates model performance separately on known classes (i.e., base domain) and unseen classes…
In recent years, zero-shot and few-shot learning in visual grounding have garnered considerable attention, largely due to the success of large-scale vision-language pre-training on expansive datasets such as LAION-5B and DataComp-1B.…
Successful execution of dexterous robotic manipulation tasks in new environments, such as grasping, depends on the ability to proficiently segment unseen objects from the background and other objects. Previous works in unseen object…
In object detection, the intersection over union (IoU) threshold is frequently used to define positives/negatives. The threshold used to train a detector defines its \textit{quality}. While the commonly used threshold of 0.5 leads to noisy…
Bounding box regression (BBR) is fundamental to object detection, where the regression loss is crucial for accurate localization. Existing IoU-based losses often incorporate handcrafted geometric penalties to address IoU's…
Recent segmentation models have demonstrated promising efficiency by aggressively reducing parameter counts and computational complexity. However, these models often struggle to accurately delineate fine lesion boundaries and texture…
Instance segmentation is a form of image detection which has a range of applications, such as object refinement, medical image analysis, and image/video editing, all of which demand a high degree of accuracy. However, this precision is…
End-to-end paradigms significantly improve the accuracy of various deep-learning-based computer vision models. To this end, tasks like object detection have been upgraded by replacing non-end-to-end components, such as removing non-maximum…
Intracranial aneurysms (IAs) are generally asymptomatic and thus often discovered incidentally on angiographic scans like 3D DSA, CTA and MRA. Skilled radiologists achieved a sensitivity of 88% by means of visual detection, which seems…
Most object detection methods use bounding boxes to encode and represent the object shape and location. In this work, we explore a fuzzy representation of object regions using Gaussian distributions, which provides an implicit binary…
We propose a simple yet effective instance segmentation framework, termed CondInst (conditional convolutions for instance segmentation). Top-performing instance segmentation methods such as Mask R-CNN rely on ROI operations (typically…
Gait recognition is one of the most promising video-based biometric technologies. The edge of silhouettes and motion are the most informative feature and previous studies have explored them separately and achieved notable results. However,…
Multi-modal methods based on camera and LiDAR sensors have garnered significant attention in the field of 3D detection. However, many prevalent works focus on single or partial stage fusion, leading to insufficient feature extraction and…
The localization quality of automatic object detectors is typically evaluated by the Intersection over Union (IoU) score. In this work, we show that humans have a different view on localization quality. To evaluate this, we conduct a survey…
Instance-level object segmentation across disparate egocentric and exocentric views is a fundamental challenge in visual understanding, critical for applications in embodied AI and remote collaboration. This task is exceptionally difficult…