Related papers: Enhancing Your Trained DETRs with Box Refinement

In this paper, we present a novel training scheme, namely Teach-DETR, to learn better DETR-based detectors from versatile teacher detectors. We show that the predicted boxes from teacher detectors are effective medium to transfer knowledge…

In this paper, we are interested in Detection Transformer (DETR), an end-to-end object detection approach based on a transformer encoder-decoder architecture without hand-crafted postprocessing, such as NMS. Inspired by Conditional DETR, an…

It has been established that training a box-based detector network can enhance the localization performance of weakly supervised and unsupervised methods. Moreover, we extend this understanding by demonstrating that these detectors can be…

We present in this paper a novel query formulation using dynamic anchor boxes for DETR (DEtection TRansformer) and offer a deeper understanding of the role of queries in DETR. This new formulation directly uses box coordinates as queries in…

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…

We present in this paper a novel denoising training method to speedup DETR (DEtection TRansformer) training and offer a deepened understanding of the slow convergence issue of DETR-like methods. We show that the slow convergence results…

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…

This paper investigates the problem of object detection with a focus on improving both the localization accuracy of bounding boxes and explicitly modeling prediction uncertainty. Conventional detectors rely on deterministic bounding box…

Ensuring robust 3D object detection and localization is crucial for many applications in robotics and autonomous driving. Recent models, however, face difficulties in maintaining high performance when applied to domains with differing…

This paper presents an improved DETR detector that maintains a "plain" nature: using a single-scale feature map and global cross-attention calculations without specific locality constraints, in contrast to previous leading DETR-based…

We perform fast vehicle detection from traffic surveillance cameras. A novel deep learning framework, namely Evolving Boxes, is developed that proposes and refines the object boxes under different feature representations. Specifically, our…

We present DINO (\textbf{D}ETR with \textbf{I}mproved de\textbf{N}oising anch\textbf{O}r boxes), a state-of-the-art end-to-end object detector. % in this paper. DINO improves over previous DETR-like models in performance and efficiency by…

Modern detection transformers (DETRs) use a set of object queries to predict a list of bounding boxes, sort them by their classification confidence scores, and select the top-ranked predictions as the final detection results for the given…

The paradigm of large-scale pre-training followed by downstream fine-tuning has been widely employed in various object detection algorithms. In this paper, we reveal discrepancies in data, model, and task between the pre-training and…

The DEtection TRansformer (DETR) algorithm has received considerable attention in the research community and is gradually emerging as a mainstream approach for object detection and other perception tasks. However, the current field lacks a…

Person search aims at localizing and identifying a query person from a gallery of uncropped scene images. Different from person re-identification (re-ID), its performance also depends on the localization accuracy of a pedestrian detector.…

DETR-like models have significantly boosted the performance of detectors and even outperformed classical convolutional models. However, all tokens are treated equally without discrimination brings a redundant computational burden in the…

Implicit layer deep learning techniques, like Neural Differential Equations, have become an important modeling framework due to their ability to adapt to new problems automatically. Training a neural differential equation is effectively a…

Despite the promising results, existing oriented object detection methods usually involve heuristically designed rules, e.g., RRoI generation, rotated NMS. In this paper, we propose an end-to-end framework for oriented object detection,…

Recent self-training techniques have shown notable improvements in unsupervised domain adaptation for 3D object detection (3D UDA). These techniques typically select pseudo labels, i.e., 3D boxes, to supervise models for the target domain.…