Related papers: IoU-balanced Loss Functions for Single-stage Objec…
Training a robust classifier and an accurate box regressor are difficult for occluded pedestrian detection. Traditionally adopted Intersection over Union (IoU) measurement does not consider the occluded region of the object and leads to…
Weakly supervised localization aims at finding target object regions using only image-level supervision. However, localization maps extracted from classification networks are often not accurate due to the lack of fine pixel-level…
Loss functions play an important role in training deep-network-based object detectors. The most widely used evaluation metric for object detection is Average Precision (AP), which captures the performance of localization and classification…
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…
The accuracy of object detectors and trackers is most commonly evaluated by the Intersection over Union (IoU) criterion. To date, most approaches are restricted to axis-aligned or oriented boxes and, as a consequence, many datasets are only…
Designing proper loss functions for vision tasks has been a long-standing research direction to advance the capability of existing models. For object detection, the well-established classification and regression loss functions have been…
Fully supervised object detection requires training images in which all instances are annotated. This is actually impractical due to the high labor and time costs and the unavoidable missing annotations. As a result, the incomplete…
We propose average Localisation-Recall-Precision (aLRP), a unified, bounded, balanced and ranking-based loss function for both classification and localisation tasks in object detection. aLRP extends the Localisation-Recall-Precision (LRP)…
Modern CNN-based object detectors rely on bounding box regression and non-maximum suppression to localize objects. While the probabilities for class labels naturally reflect classification confidence, localization confidence is absent. This…
Underwater optical images inevitably suffer from various degradation factors such as blurring, low contrast, and color distortion, which hinder the accuracy of object detection tasks. Due to the lack of paired underwater/clean images, most…
One-stage object detectors such as SSD or YOLO already have shown promising accuracy with small memory footprint and fast speed. However, it is widely recognized that one-stage detectors have difficulty in detecting small objects while they…
In Few-Shot Object Detection (FSOD), detecting small objects is extremely difficult. The limited supervision cripples the localization capabilities of the models and a few pixels shift can dramatically reduce the Intersection over Union…
Single-stage detectors suffer from extreme foreground-background class imbalance, while two-stage detectors do not. Therefore, in semi-supervised object detection, two-stage detectors can deliver remarkable performance by only selecting…
Current state-of-the-art one-stage object detectors are limited by treating each image region separately without considering possible relations of the objects. This causes dependency solely on high-quality convolutional feature…
Object detection has seen remarkable progress in recent years with the introduction of Convolutional Neural Networks (CNN). Object detection is a multi-task learning problem where both the position of the objects in the images as well as…
Bounding box (bbox) regression is a fundamental task in computer vision. So far, the most commonly used loss functions for bbox regression are the Intersection over Union (IoU) loss and its variants. In this paper, we generalize existing…
Most existing point cloud based 3D object detectors focus on the tasks of classification and box regression. However, another bottleneck in this area is achieving an accurate detection confidence for the Non-Maximum Suppression (NMS)…
Prior work on 6-DoF object pose estimation has largely focused on instance-level processing, in which a textured CAD model is available for each object being detected. Category-level 6-DoF pose estimation represents an important step toward…
Numerous improvements for feedback mechanisms have contributed to the great progress in object detection. In this paper, we first present an evaluation-feedback module, which is proposed to consist of evaluation system and feedback…
With basic Semi-Supervised Object Detection (SSOD) techniques, one-stage detectors generally obtain limited promotions compared with two-stage clusters. We experimentally find that the root lies in two kinds of ambiguities: (1) Selection…