Related papers: DEYOv2: Rank Feature with Greedy Matching for End-…

Recently, end-to-end object detectors have gained significant attention from the research community due to their outstanding performance. However, DETR typically relies on supervised pretraining of the backbone on ImageNet, which limits the…

The training paradigm of DETRs is heavily contingent upon pre-training their backbone on the ImageNet dataset. However, the limited supervisory signals provided by the image classification task and one-to-one matching strategy result in an…

Object detection is an important topic in computer vision, with post-processing, an essential part of the typical object detection pipeline, posing a significant bottleneck affecting the performance of traditional object detection models.…

Driven by the simple and effective Dense O2O, DEIM demonstrates faster convergence and enhanced performance. In this work, we extend it with DINOv3 features, resulting in DEIMv2. DEIMv2 spans eight model sizes from X to Atto, covering GPU,…

We introduce DEIM, an innovative and efficient training framework designed to accelerate convergence in real-time object detection with Transformer-based architectures (DETR). To mitigate the sparse supervision inherent in one-to-one (O2O)…

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…

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…

Over the past years, YOLOs have emerged as the predominant paradigm in the field of real-time object detection owing to their effective balance between computational cost and detection performance. Researchers have explored the…

The recently proposed end-to-end transformer detectors, such as DETR and Deformable DETR, have a cascade structure of stacking 6 decoder layers to update object queries iteratively, without which their performance degrades seriously. In…

Modern object detectors are static, fixed-depth networks optimized for a single operating point, requiring separate models for different deployment scenarios. We present an any-depth detection framework that enables a single network to span…

The YOLO series has become the most popular framework for real-time object detection due to its reasonable trade-off between speed and accuracy. However, we observe that the speed and accuracy of YOLOs are negatively affected by the NMS.…

One-to-one label assignment in object detection has successfully obviated the need for non-maximum suppression (NMS) as postprocessing and makes the pipeline end-to-end. However, it triggers a new dilemma as the widely used sparse queries…

Dynamic neural network is an emerging research topic in deep learning. With adaptive inference, dynamic models can achieve remarkable accuracy and computational efficiency. However, it is challenging to design a powerful dynamic detector,…

Dense object detection is widely used in automatic driving, video surveillance, and other fields. This paper focuses on the challenging task of dense object detection. Currently, detection methods based on greedy algorithms, such as…

Object detection is considered one of the most challenging problems in this field of computer vision, as it involves the combination of object classification and object localization within a scene. Recently, deep neural networks (DNNs) have…

One-to-one set matching is a key design for DETR to establish its end-to-end capability, so that object detection does not require a hand-crafted NMS (non-maximum suppression) to remove duplicate detections. This end-to-end signature is…

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…

Model efficiency has become increasingly important in computer vision. In this paper, we systematically study neural network architecture design choices for object detection and propose several key optimizations to improve efficiency.…

Being effective and efficient is essential to an object detector for practical use. To meet these two concerns, we comprehensively evaluate a collection of existing refinements to improve the performance of PP-YOLO while almost keep the…

DETR is the first end-to-end object detector using a transformer encoder-decoder architecture and demonstrates competitive performance but low computational efficiency on high resolution feature maps. The subsequent work, Deformable DETR,…