Related papers: Gaussian Guided IoU: A Better Metric for Balanced …
State-of-the-art object detectors rely on regressing and classifying an extensive list of possible anchors, which are divided into positive and negative samples based on their intersection-over-union (IoU) with corresponding groundtruth…
Recently, many arbitrary-oriented object detection (AOOD) methods have been proposed and attracted widespread attention in many fields. However, most of them are based on anchor-boxes or standard Gaussian heatmaps. Such label assignment…
Most existing object detectors suffer from class imbalance problems that hinder balanced performance. In particular, anchor free object detectors have to solve the background imbalance problem due to detection in a per-pixel prediction…
Detecting tiny objects is one of the main obstacles hindering the development of object detection. The performance of generic object detectors tends to drastically deteriorate on tiny object detection tasks. In this paper, we point out that…
The Jaccard index, also known as Intersection-over-Union (IoU), is one of the most critical evaluation metrics in image semantic segmentation. However, direct optimization of IoU score is very difficult because the learning objective is…
We address the task of open-world class-agnostic object detection, i.e., detecting every object in an image by learning from a limited number of base object classes. State-of-the-art RGB-based models suffer from overfitting the training…
In one-stage multi-object detection tasks, various intersection over union (IoU)-based solutions aim at smooth and stable convergence near the targets during training. However, IoU-based losses fail to correctly update the gradient of small…
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…
We introduce a novel Interval Bound Propagation (IBP) approach for the formal verification of object detection models, specifically targeting the Intersection over Union (IoU) metric. The approach has been implemented in an open source…
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…
Non-maximum suppression (NMS) is widely used in object detection pipelines for removing duplicated bounding boxes. The inconsistency between the confidence for NMS and the real localization confidence seriously affects detection…
Object detection is one of the most fundamental yet challenging research topics in the domain of computer vision. Recently, the study on this topic in aerial images has made tremendous progress. However, complex background and worse imaging…
After DETR was proposed, this novel transformer-based detection paradigm which performs several cross-attentions between object queries and feature maps for predictions has subsequently derived a series of transformer-based detection heads.…
Region Proposal Network (RPN) is the cornerstone of two-stage object detectors, it generates a sparse set of object proposals and alleviates the extrem foregroundbackground class imbalance problem during training. However, we find that the…
Deep learning-based object detection and instance segmentation have achieved unprecedented progress. In this paper, we propose Complete-IoU (CIoU) loss and Cluster-NMS for enhancing geometric factors in both bounding box regression and…
Semantic segmentation datasets often exhibit two types of imbalance: \textit{class imbalance}, where some classes appear more frequently than others and \textit{size imbalance}, where some objects occupy more pixels than others. This causes…
Cameras are essential vision instruments to capture images for pattern detection and measurement. Human-object interaction (HOI) detection is one of the most popular pattern detection approaches for captured human-centric visual scenes.…
In the CNN based object detectors, feature pyramids are widely exploited to alleviate the problem of scale variation across object instances. These object detectors, which strengthen features via a top-down pathway and lateral connections,…
The CenterTrack tracking algorithm achieves state-of-the-art tracking performance using a simple detection model and single-frame spatial offsets to localize objects and predict their associations in a single network. However, this joint…
Camouflaged object detection (COD) aims to segment objects visually embedded in their surroundings, which is a very challenging task due to the high similarity between the objects and the background. To address it, most methods often…