Related papers: LapNet : Automatic Balanced Loss and Optimal Assig…
Existing anchor-based and anchor-free object detectors in multi-stage or one-stage pipelines have achieved very promising detection performance. However, they still encounter the design difficulty in hand-crafted 2D anchor definition and…
The highest accuracy object detectors to date are based on a two-stage approach popularized by R-CNN, where a classifier is applied to a sparse set of candidate object locations. In contrast, one-stage detectors that are applied over a…
Object detection is a basic but challenging task in computer vision, which plays a key role in a variety of industrial applications. However, object detectors based on deep learning usually require greater storage requirements and longer…
One-stage object detectors are trained by optimizing classification-loss and localization-loss simultaneously, with the former suffering much from extreme foreground-background class imbalance issue due to the large number of anchors. This…
Automated driving object detection has always been a challenging task in computer vision due to environmental uncertainties. These uncertainties include significant differences in object sizes and encountering the class unseen. It may…
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…
The recent advances of compressing high-accuracy convolution neural networks (CNNs) have witnessed remarkable progress for real-time object detection. To accelerate detection speed, lightweight detectors always have few convolution layers…
Object detection has been vigorously investigated for years but fast accurate detection for real-world scenes remains a very challenging problem. Overcoming drawbacks of single-stage detectors, we take aim at precisely detecting objects for…
Despite significant progress of deep learning in recent years, state-of-the-art semantic matching methods still rely on legacy features such as SIFT or HoG. We argue that the strong invariance properties that are key to the success of…
One-stage object detectors are trained by optimizing classification-loss and localization-loss simultaneously, with the former suffering much from extreme foreground-background class imbalance issue due to the large number of anchors. This…
A standard one-stage detector is comprised of two tasks: classification and regression. Anchors of different shapes are introduced for each location in the feature map to mitigate the challenge of regression for multi-scale objects.…
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…
Dense object tracking, the ability to localize specific object points with pixel-level accuracy, is an important computer vision task with numerous downstream applications in robotics. Existing approaches either compute dense keypoint…
Object occlusion boundary detection is a fundamental and crucial research problem in computer vision. This is challenging to solve as encountering the extreme boundary/non-boundary class imbalance during training an object occlusion…
Recently, anchor-free detection methods have been through great progress. The major two families, anchor-point detection and key-point detection, are at opposite edges of the speed-accuracy trade-off, with anchor-point detectors having the…
In object detection, determining which anchors to assign as positive or negative samples, known as anchor assignment, has been revealed as a core procedure that can significantly affect a model's performance. In this paper we propose a…
Recent one-stage object detectors follow a per-pixel prediction approach that predicts both the object category scores and boundary positions from every single grid location. However, the most suitable positions for inferring different…
Deep learning based object detectors are commonly deployed on mobile devices to solve a variety of tasks. For maximum accuracy, each detector is usually trained to solve one single specific task, and comes with a completely independent set…
Object detection often costs a considerable amount of computation to get satisfied performance, which is unfriendly to be deployed in edge devices. To address the trade-off between computational cost and detection accuracy, this paper…
Object detection has been one of the most active topics in computer vision for the past years. Recent works have mainly focused on pushing the state-of-the-art in the general-purpose COCO benchmark. However, the use of such detection…