Top Research Papers on Object Detection

A baseline is proposed that largely improves REC methods by reconstructing the training data and introducing a binary classification sub-task, outperforming existing methods.

The first systematic study on concealed object detection (COD), which aims to identify objects that are visually embedded in their background, is presented, and rich annotations including object categories, object boundaries, challenging attributes, object-level labels, and instance-level annotations are provided.

This paper conducts research on applying the transformer networks for salient object detection (SOD) and investigates the contributions of two strategies to provide stronger spatial supervision through the transformer layers within a unified framework, namely deep supervision and dif ficulty-aware learning.

This paper proposes a ContinuaL DEtection TRansformer (CL-DETR), a new method for transformer-based IOD which enables effective usage of KD and ER in this context and introduces a Detector Knowledge Distillation (DKD) loss, focusing on the most informative and reliable predictions from old versions of the model.

This work proposes a novel training strategy, called UNKAD, able to predict unknown objects without requiring any annotation of them, exploiting non annotated objects that are already present in the background of training images.

A flexible framework for monocular 3D object detection which explicitly decouples the truncated objects and adaptively combines multiple approaches for object depth estimation, which outperforms the state-of-the-art method.

It is demonstrated that bottom-up approaches show competitive performance compared with top-down approaches and have higher recall rates and a real-time CenterNet model, an anchor-free detector that achieves a good trade-off between accuracy and speed.

An Object-Aware Distillation Pyramid (OADP) framework, including an Object- aware Knowledge Extraction (OAKE) module and adistillation Pyramid mechanism, is proposed, which introduces global and block distillation for more comprehensive knowledge transfer to compensate for the missing relation information in object distillation.

The OWLv2 model and OWL-ST self-training recipe, which surpasses the performance of previous state-of-the-art open-vocabulary detectors already at comparable training scales and unlocks Web-scale training for open-world localization, similar to what has been seen for image classification and language modelling.

Compared to the best class identification frameworks, YOLO makes many limitations yet very different to expect misleading sides on the basis, and overcomes other local techniques, including SSD and R-CNN, while summarizing from conventional images to as diverse as art.

This paper proposes an algorithm to perform the real-time object detection typically leverage machine learning, deep learning to produce effective results and presents a fast and accurate object detection method with higher performance, YOLO version3 (YOLOv3).

This work proposes an object-aware domain generalization (OA-DG) method for single-domain generalization in object detection that outperforms state-of-the-art works on standard benchmarks.

The extensive experiments show that DiffusionDet achieves favorable performance compared to previous well-established detectors, and possesses an appealing property of flexibility, which enables the dynamic number of boxes and iterative evaluation.

This paper dives into both the foundational modules of DETR and its recent enhancements, such as modifications to the backbone structure, query design strategies, and refinements to attention mechanisms, and conducts a comparative analysis across various detection transformers, evaluating their performance and network architectures.

A novel probabilistic framework for objectness estimation is introduced, where it alternate between probability distribution estimation and objectness likelihood maximization of known objects in the embedded feature space - ultimately allowing to estimate the objectness probability of different proposals.

This paper presents a generalized model for real-time detection of flying objects that can be used for transfer learning and further research, as well as a refined model that achieves state-of-the-art results for flying object detection. We achieve this by training our first (generalized) model on a data set containing 40 different classes of flying objects, forcing the model to extract abstract feature representations. We then perform transfer learning with these learned parameters on a data set more representative of real world environments (i.e. higher frequency of occlusion, very small spa...

A novel approach called Multiple Enhancement Network (MENet) is proposed that adopts the boundary sensibility, content integrity, iterative refinement, and frequency decomposition mechanisms of HVS to identify and segment salient objects.

A new generation of YOLO series for real-time end-to-end object detection, dubbed YOLOv10, is presented and the holistic efficiency-accuracy driven model design strategy for YOLOs is introduced, which greatly reduces the computational overhead and enhances the capability.

This paper presents a novel localization distillation (LD) method which can efficiently transfer the localization knowledge from the teacher to the student and introduces the concept of valuable localization region that can aid to selectively distill the classification and localization knowledge for a certain region.

The experimental result of PASCALVOC show that the copy-pastemethod model can be used to improve the performance of deep learning models in many vision tasks such as objectdetection, by responding to reasonable generationfortraining examples byannotatinggroundtruth onfreespace according to the placementrules.

A method designed to detect and localize brain cancer by proposing an automated approach for the detection and localization of brain cancer using the YOLO model, which utilizes magnetic resonance imaging analysis.

The proposed system makes training over different kinds of samples and allows noting the statistics of each kind of object, which could be useful in many real-time applications where the count of objects is needed as well as other applications where specific detail is considered important.

UniDetector is proposed, a universal object detector that has the ability to recognize enormous categories in the open world, and surpasses the traditional supervised baselines by more than 4% on average without seeing any corresponding images.

This work proposes an effective and simple oriented object detection framework, termed Oriented R-CNN, which is a general two-stage oriented detector with promising accuracy and efficiency, and an oriented Region Proposal Network (oriented RPN) that directly generates high-quality oriented proposals in a nearly cost-free manner.

This paper proposes a paradigm of lever-aging the contradictory information to enhance the detection ability of both salient object detection and camouflaged object detection, and introduces a "similarity measure" module to explicitly model the contradicting attributes of these two tasks.

This paper proposes a novel open-vocabulary object detection framework directly learning from image-text pair data as a set matching problem between a set of image region features and aSet of word embeddings, which enables us to train an open- Vocabulary object detector on image- Text pairs in a much simple and effective way.

A refined YOLOv8 object detection model is proposed, emphasizing motion-specific detections in varied visual contexts, through tailored preprocessing and architectural adjustments, to heighten the model’s sensitivity to object movements.

The final model architecture proposed is more accurate and provides the fast result of object detection with voice as compared to previous researches.

This work proposes a novel computer vision problem called ORE: Open World Object Detector, which is based on contrastive clustering and energy based unknown identification, and finds that identifying and characterising unknown instances helps to reduce confusion in an incremental object detection setting.

Voxel Transformer is presented, a novel and effective voxel-based Transformer backbone for 3D object detection from point clouds that shows consistent improvement over the convolutional baselines while maintaining computational efficiency on the KITTI dataset and the Waymo Open dataset.

The study explores the underlying architecture of CNNs, elucidating how convolution, pooling, and flattening layers enable efficient image processing and object identification.

This application's main purpose is to act as a surveillance system that can identify persons, recognise faces, and display user information, which lowers the possibility of future system penetration by people and improves social stability.

The analysis shows that the proposed AAF-Faster RCNN model has higher efficiency than state-of-art Pay Attention to Them (PAT) model in object detection.

In this work, the object-based hyperspectral detection problem is formulated, and a convolutional neural network is designed based on the specific characteristics of this problem based on its superior performance in experimental results.

The problem of referring camouflaged object detection (Ref-COD), a new task that aims to segment specified camouflaged objects based on a small set of referring images with salient target objects, is considered, with a simple but strong dual-branch framework.

This paper proposes an effective approximate SkewIoU loss based on Gaussian modeling and Gaussian product, which mainly consists of two items, and extends the technique to the 3-D case which also suffers from the same issues as 2-D.

This paper proposes a novel boundary-guided network (BGNet) for camouflaged object detection, which significantly outperforms the existing 18 state-of-the-art methods under four widely-used evaluation metrics.

The goal of COD task is not just to mimic the human visual ability in a single RGB domain, but to go beyond the human biological vision, and the proposed method significantly outperforms other state-of-the-art methods by a large margin.

This method models 3D object detection as message passing on a dynamic graph, generalizing the DGCNN framework to predict a set of objects and achieves state-of-the-art performance on autonomous driving benchmarks.

This paper proposes the Real-Time DEtection TRansformer (RT-DETR), the first real-time end-to-end object detector to the best knowledge that addresses the above dilemma and designs an efficient hybrid encoder to expeditiously process multi-scale features by decoupling intra-scale interaction and cross-scale fusion to improve speed.

This work provides the first attempt and implements Oriented Object DEtection with TRansformer based on an end-to-end network and provides a new insight into oriented object detection by applying Transformer to directly and efficiently localize objects without a tedious process of rotated anchors.

This paper proposes an effective adaptive points learning approach to aerial object detection by taking advantage of the adaptive points representation, which is able to capture the geometric information of the arbitrary-oriented instances.

A Centralized Feature Pyramid (CFP) network for object detection, which is based on a globally explicit centralized feature regulation, which not only has the ability to capture the global long-range dependencies but also efficiently obtain an all-round yet discriminative feature representation.

A fully sparse object detector termed FSD, built upon the general sparse voxel encoder and a novel sparse instance recognition (SIR) module, and a super sparse detector named FSD++, which first generates residual points, which indicate the point changes between consecutive frames.

This review paper will focus on the existing techniques that are present in the community and how each technique is different from the other techniques and perform comparative analyses of these techniques to draw meaningful conclusions.

This research discusses the importance of enhancing real-time object detection on mobile devices by introducing a new multi-object detection system that uses the quantified YOLOv7 model and develops object detection techniques theoretically, offering valuable insights that can be applied across various domains.

This work proposes a new instance of joint MOT approach based on Graph Neural Networks (GNNs), which can model relations between variablesized objects in both the spatial and temporal domains, which is essential for learning discriminative features for detection and data association.

This work proposes a novel distillation method for detection tasks based on discriminative instances without considering the positive or negative distinguished by GT, which is called general instance distillation (GID).

This paper explores the potential of curriculum learning in LiDAR-based 3D object detection by proposing a curricular object manipulation (COM) framework. The framework embeds the curricular training strategy into both the loss design and the augmentation process. For the loss design, we propose the COMLoss to dynamically predict object-level difficulties and emphasize objects of different difficulties based on training stages. On top of the widely-used augmentation technique called GT-Aug in Li-DAR detection tasks, we propose a novel COMAug strategy which first clusters objects in ground-trut...

This paper draws on the idea of mutual-assistance (MA) learning and accordingly proposes a robust one-stage detector, referred as MADet, to address weaknesses in object detection, and meticulously devise a quality assessment mechanism to facilitate adaptive sample selection and loss term reweighting.