Related papers: Focaler-IoU: More Focused Intersection over Union …
Label assignment plays a significant role in modern object detection models. Detection models may yield totally different performances with different label assignment strategies. For anchor-based detection models, the IoU (Intersection over…
Bounding box regression (BBR) has been widely used in object detection and instance segmentation, which is an important step in object localization. However, most of the existing loss functions for bounding box regression cannot be…
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…
Bounding boxes uniquely characterize object detection, where a good detector gives accurate bounding boxes of categories of interest. However, in the real-world where test ground truths are not provided, it is non-trivial to find out…
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…
Locating an object in a sequence of frames, given its appearance in the first frame of the sequence, is a hard problem that involves many stages. Usually, state-of-the-art methods focus on bringing novel ideas in the visual encoding or…
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…
Existing detection methods commonly use a parameterized bounding box (BBox) to model and detect (horizontal) objects and an additional rotation angle parameter is used for rotated objects. We argue that such a mechanism has fundamental…
Few-shot object detection has gained significant attention in recent years as it has the potential to greatly reduce the reliance on large amounts of manually annotated bounding boxes. While most existing few-shot object detection…
Four-variable-independent-regression localization losses, such as Smooth-$\ell_1$ Loss, are used by default in modern detectors. Nevertheless, this kind of loss is oversimplified so that it is inconsistent with the final evaluation metric,…
Effective feature fusion of multispectral images plays a crucial role in multi-spectral object detection. Previous studies have demonstrated the effectiveness of feature fusion using convolutional neural networks, but these methods are…
Inadequate bounding box modeling in regression tasks constrains the performance of one-stage 3D object detection. Our study reveals that the primary reason lies in two aspects: (1) The limited center-offset prediction seriously impairs the…
Two-stage deep object detectors generate a set of regions-of-interest (RoI) in the first stage, then, in the second stage, identify objects among the proposed RoIs that sufficiently overlap with a ground truth (GT) box. The second stage is…
Monocular 3D object detection is a challenging task because depth information is difficult to obtain from 2D images. A subset of viewpoint-agnostic monocular 3D detection methods also do not explicitly leverage scene homography or geometry…
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…
Classification and regression are two pillars of object detectors. In most CNN-based detectors, these two pillars are optimized independently. Without direct interactions between them, the classification loss and the regression loss can not…
Without densely tiled anchor boxes or grid points in the image, sparse R-CNN achieves promising results through a set of object queries and proposal boxes updated in the cascaded training manner. However, due to the sparse nature and the…
Region sampling or weighting is significantly important to the success of modern region-based object detectors. Unlike some previous works, which only focus on "hard" samples when optimizing the objective function, we argue that sample…
Bounding boxes are often used to communicate automatic object detection results to humans, aiding humans in a multitude of tasks. We investigate the relationship between bounding box localization errors and human task performance. We use…
Cross-domain object detection is more challenging than object classification since multiple objects exist in an image and the location of each object is unknown in the unlabeled target domain. As a result, when we adapt features of…