Related papers: End-to-End Object Detection with Transformers
RT-DETR is the first real-time end-to-end transformer-based object detector. Its efficiency comes from the framework design and the Hungarian matching. However, compared to dense supervision detectors like the YOLO series, the Hungarian…
Convolutional Neural networks (CNN) have been the first choice of paradigm in many computer vision applications. The convolution operation however has a significant weakness which is it only operates on a local neighborhood of pixels, thus…
Efficient and accurate object detection is an important topic in the development of computer vision systems. With the advent of deep learning techniques, the accuracy of object detection has increased significantly. The project aims to…
DETR is the first fully end-to-end detector that predicts a final set of predictions without post-processing. However, it suffers from problems such as low performance and slow convergence. A series of works aim to tackle these issues in…
In this paper, we present a light-weight detection transformer, LW-DETR, which outperforms YOLOs for real-time object detection. The architecture is a simple stack of a ViT encoder, a projector, and a shallow DETR decoder. Our approach…
Transformers have revolutionized the object detection landscape by introducing DETRs, acclaimed for their simplicity and efficacy. Despite their advantages, the substantial size of these models poses significant challenges for practical…
In this paper, we present a joint end-to-end line segment detection algorithm using Transformers that is post-processing and heuristics-guided intermediate processing (edge/junction/region detection) free. Our method, named LinE segment…
Temporal modeling of objects is a key challenge in multiple object tracking (MOT). Existing methods track by associating detections through motion-based and appearance-based similarity heuristics. The post-processing nature of association…
Transformer and its variants have shown great potential for various vision tasks in recent years, including image classification, object detection and segmentation. Meanwhile, recent studies also reveal that with proper architecture design,…
The recently-developed DETR approach applies the transformer encoder and decoder architecture to object detection and achieves promising performance. In this paper, we handle the critical issue, slow training convergence, and present a…
Existing methods enhance the training of detection transformers by incorporating an auxiliary one-to-many assignment. In this work, we treat the model as a multi-task framework, simultaneously performing one-to-one and one-to-many…
Monocular 3D object detection has long been a challenging task in autonomous driving. Most existing methods follow conventional 2D detectors to first localize object centers, and then predict 3D attributes by neighboring features. However,…
We consider the problem of omni-supervised object detection, which can use unlabeled, fully labeled and weakly labeled annotations, such as image tags, counts, points, etc., for object detection. This is enabled by a unified architecture,…
Transformer-based multi-object tracking (MOT) methods have captured the attention of many researchers in recent years. However, these models often suffer from slow inference speeds due to their structure or other issues. To address this…
The introduction of DETR represents a new paradigm for object detection. However, its decoder conducts classification and box localization using shared queries and cross-attention layers, leading to suboptimal results. We observe that…
End-to-end transformer architectures have driven significant progress in multi-object tracking by unifying detection and association into a single, heuristic-free framework. Despite these benefits, poor detection performance and the…
The recent detection transformer (DETR) simplifies the object detection pipeline by removing hand-crafted designs and hyperparameters as employed in conventional two-stage object detectors. However, how to leverage the simple yet effective…
This paper is on Few-Shot Object Detection (FSOD), where given a few templates (examples) depicting a novel class (not seen during training), the goal is to detect all of its occurrences within a set of images. From a practical perspective,…
Pretraining on large-scale datasets can boost the performance of object detectors while the annotated datasets for object detection are hard to scale up due to the high labor cost. What we possess are numerous isolated filed-specific…
This paper is concerned with the matching stability problem across different decoder layers in DEtection TRansformers (DETR). We point out that the unstable matching in DETR is caused by a multi-optimization path problem, which is…