PyTorchKR Papers

최신 논문

총 3,796편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2308.09564공식 코드 · Papers with Code

Deep Equilibrium Object Detection

Query-based object detectors directly decode image features into object instances with a set of learnable queries. These query vectors are progressively refined to stable meaningful representations through a sequence of decoder layers, and then used to directly predict object locations and categories with simple FFN heads. In this paper, we present a new query-based object detector (DEQDet) by designing a deep equilibrium decoder. Our DEQ decoder models the query vector refinement as the fixed point solving of an {implicit} layer and is equivalent to applying {infinite} steps of refinement. To be more specific to object decoding, we use a two-step unrolled equilibrium equation to explicitly capture the query vector refinement. Accordingly, we are able to incorporate refinement awareness into the DEQ training with the inexact gradient back-propagation (RAG). In addition, to stabilize the training of our DEQDet and improve its generalization ability, we devise the deep supervision scheme on the optimization path of DEQ with refinement-aware perturbation~(RAP). Our experiments demonstrate DEQDet converges faster, consumes less memory, and achieves better results than the baseline counterpart (AdaMixer). In particular, our DEQDet with ResNet50 backbone and 300 queries achieves the $49.5$ mAP and $33.0$ AP$_s$ on the MS COCO benchmark under $2\times$ training scheme (24 epochs).

arXiv:2308.09534공식 코드 · Papers with Code

Small Object Detection via Coarse-to-fine Proposal Generation and Imitation Learning

The past few years have witnessed the immense success of object detection, while current excellent detectors struggle on tackling size-limited instances. Concretely, the well-known challenge of low overlaps between the priors and object regions leads to a constrained sample pool for optimization, and the paucity of discriminative information further aggravates the recognition. To alleviate the aforementioned issues, we propose CFINet, a two-stage framework tailored for small object detection based on the Coarse-to-fine pipeline and Feature Imitation learning. Firstly, we introduce Coarse-to-fine RPN (CRPN) to ensure sufficient and high-quality proposals for small objects through the dynamic anchor selection strategy and cascade regression. Then, we equip the conventional detection head with a Feature Imitation (FI) branch to facilitate the region representations of size-limited instances that perplex the model in an imitation manner. Moreover, an auxiliary imitation loss following supervised contrastive learning paradigm is devised to optimize this branch. When integrated with Faster RCNN, CFINet achieves state-of-the-art performance on the large-scale small object detection benchmarks, SODA-D and SODA-A, underscoring its superiority over baseline detector and other mainstream detection approaches.

arXiv:2308.09421공식 코드 · Papers with Code

MonoNeRD: NeRF-like Representations for Monocular 3D Object Detection

In the field of monocular 3D detection, it is common practice to utilize scene geometric clues to enhance the detector's performance. However, many existing works adopt these clues explicitly such as estimating a depth map and back-projecting it into 3D space. This explicit methodology induces sparsity in 3D representations due to the increased dimensionality from 2D to 3D, and leads to substantial information loss, especially for distant and occluded objects. To alleviate this issue, we propose MonoNeRD, a novel detection framework that can infer dense 3D geometry and occupancy. Specifically, we model scenes with Signed Distance Functions (SDF), facilitating the production of dense 3D representations. We treat these representations as Neural Radiance Fields (NeRF) and then employ volume rendering to recover RGB images and depth maps. To the best of our knowledge, this work is the first to introduce volume rendering for M3D, and demonstrates the potential of implicit reconstruction for image-based 3D perception. Extensive experiments conducted on the KITTI-3D benchmark and Waymo Open Dataset demonstrate the effectiveness of MonoNeRD. Codes are available at https://github.com/cskkxjk/MonoNeRD.

arXiv:2308.09351공식 코드 · Papers with Code

RLIPv2: Fast Scaling of Relational Language-Image Pre-training

Relational Language-Image Pre-training (RLIP) aims to align vision representations with relational texts, thereby advancing the capability of relational reasoning in computer vision tasks. However, hindered by the slow convergence of RLIPv1 architecture and the limited availability of existing scene graph data, scaling RLIPv1 is challenging. In this paper, we propose RLIPv2, a fast converging model that enables the scaling of relational pre-training to large-scale pseudo-labelled scene graph data. To enable fast scaling, RLIPv2 introduces Asymmetric Language-Image Fusion (ALIF), a mechanism that facilitates earlier and deeper gated cross-modal fusion with sparsified language encoding layers. ALIF leads to comparable or better performance than RLIPv1 in a fraction of the time for pre-training and fine-tuning. To obtain scene graph data at scale, we extend object detection datasets with free-form relation labels by introducing a captioner (e.g., BLIP) and a designed Relation Tagger. The Relation Tagger assigns BLIP-generated relation texts to region pairs, thus enabling larger-scale relational pre-training. Through extensive experiments conducted on Human-Object Interaction Detection and Scene Graph Generation, RLIPv2 shows state-of-the-art performance on three benchmarks under fully-finetuning, few-shot and zero-shot settings. Notably, the largest RLIPv2 achieves 23.29mAP on HICO-DET without any fine-tuning, yields 32.22mAP with just 1% data and yields 45.09mAP with 100% data. Code and models are publicly available at https://github.com/JacobYuan7/RLIPv2.

arXiv:2308.08529공식 코드 · Papers with Code

Diagnosing Human-object Interaction Detectors

We have witnessed significant progress in human-object interaction (HOI) detection. The reliance on mAP (mean Average Precision) scores as a summary metric, however, does not provide sufficient insight into the nuances of model performance (e.g., why one model is better than another), which can hinder further innovation in this field. To address this issue, in this paper, we introduce a diagnosis toolbox to provide detailed quantitative break-down analysis of HOI detection models, inspired by the success of object detection diagnosis toolboxes. We first conduct holistic investigations in the pipeline of HOI detection. By defining a set of errors and the oracles to fix each of them, we can have a quantitative analysis of the significance of different errors according to the mAP improvement obtained from fixing each error. We then delve into two sub-tasks of HOI detection: human-object pair detection and interaction classification, respectively. For the first detection task, we compute the coverage of ground-truth human-object pairs as well as the noisiness level in the detection results. For the second classification task, we measure a model's performance of differentiating positive and negative detection results and also classifying the actual interactions when the human-object pairs are correctly detected. We analyze eight state-of-the-art HOI detection models and provide valuable diagnosis insights to foster future research. For instance, our diagnosis shows that state-of-the-art model RLIPv2 outperforms others mainly because it significantly improves the multi-label interaction classification accuracy. Our toolbox is applicable for different methods across different datasets and available at https://github.com/neu-vi/Diag-HOI.

arXiv:2308.08140공식 코드 · Papers with Code

GPA-3D: Geometry-aware Prototype Alignment for Unsupervised Domain Adaptive 3D Object Detection from Point Clouds

LiDAR-based 3D detection has made great progress in recent years. However, the performance of 3D detectors is considerably limited when deployed in unseen environments, owing to the severe domain gap problem. Existing domain adaptive 3D detection methods do not adequately consider the problem of the distributional discrepancy in feature space, thereby hindering generalization of detectors across domains. In this work, we propose a novel unsupervised domain adaptive \textbf{3D} detection framework, namely \textbf{G}eometry-aware \textbf{P}rototype \textbf{A}lignment (\textbf{GPA-3D}), which explicitly leverages the intrinsic geometric relationship from point cloud objects to reduce the feature discrepancy, thus facilitating cross-domain transferring. Specifically, GPA-3D assigns a series of tailored and learnable prototypes to point cloud objects with distinct geometric structures. Each prototype aligns BEV (bird's-eye-view) features derived from corresponding point cloud objects on source and target domains, reducing the distributional discrepancy and achieving better adaptation. The evaluation results obtained on various benchmarks, including Waymo, nuScenes and KITTI, demonstrate the superiority of our GPA-3D over the state-of-the-art approaches for different adaptation scenarios. The MindSpore version code will be publicly available at \url{https://github.com/Liz66666/GPA3D}.

arXiv:2308.07737공식 코드 · Papers with Code

Identity-Consistent Aggregation for Video Object Detection

In Video Object Detection (VID), a common practice is to leverage the rich temporal contexts from the video to enhance the object representations in each frame. Existing methods treat the temporal contexts obtained from different objects indiscriminately and ignore their different identities. While intuitively, aggregating local views of the same object in different frames may facilitate a better understanding of the object. Thus, in this paper, we aim to enable the model to focus on the identity-consistent temporal contexts of each object to obtain more comprehensive object representations and handle the rapid object appearance variations such as occlusion, motion blur, etc. However, realizing this goal on top of existing VID models faces low-efficiency problems due to their redundant region proposals and nonparallel frame-wise prediction manner. To aid this, we propose ClipVID, a VID model equipped with Identity-Consistent Aggregation (ICA) layers specifically designed for mining fine-grained and identity-consistent temporal contexts. It effectively reduces the redundancies through the set prediction strategy, making the ICA layers very efficient and further allowing us to design an architecture that makes parallel clip-wise predictions for the whole video clip. Extensive experimental results demonstrate the superiority of our method: a state-of-the-art (SOTA) performance (84.7% mAP) on the ImageNet VID dataset while running at a speed about 7x faster (39.3 fps) than previous SOTAs.

arXiv:2308.07732공식 코드 · Papers with Code

UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representation

Jointly processing information from multiple sensors is crucial to achieving accurate and robust perception for reliable autonomous driving systems. However, current 3D perception research follows a modality-specific paradigm, leading to additional computation overheads and inefficient collaboration between different sensor data. In this paper, we present an efficient multi-modal backbone for outdoor 3D perception named UniTR, which processes a variety of modalities with unified modeling and shared parameters. Unlike previous works, UniTR introduces a modality-agnostic transformer encoder to handle these view-discrepant sensor data for parallel modal-wise representation learning and automatic cross-modal interaction without additional fusion steps. More importantly, to make full use of these complementary sensor types, we present a novel multi-modal integration strategy by both considering semantic-abundant 2D perspective and geometry-aware 3D sparse neighborhood relations. UniTR is also a fundamentally task-agnostic backbone that naturally supports different 3D perception tasks. It sets a new state-of-the-art performance on the nuScenes benchmark, achieving +1.1 NDS higher for 3D object detection and +12.0 higher mIoU for BEV map segmentation with lower inference latency. Code will be available at https://github.com/Haiyang-W/UniTR .

arXiv:2308.07717공식 코드 · Papers with Code

Real-time Automatic M-mode Echocardiography Measurement with Panel Attention from Local-to-Global Pixels

Motion mode (M-mode) recording is an essential part of echocardiography to measure cardiac dimension and function. However, the current diagnosis cannot build an automatic scheme, as there are three fundamental obstructs: Firstly, there is no open dataset available to build the automation for ensuring constant results and bridging M-mode echocardiography with real-time instance segmentation (RIS); Secondly, the examination is involving the time-consuming manual labelling upon M-mode echocardiograms; Thirdly, as objects in echocardiograms occupy a significant portion of pixels, the limited receptive field in existing backbones (e.g., ResNet) composed from multiple convolution layers are inefficient to cover the period of a valve movement. Existing non-local attentions (NL) compromise being unable real-time with a high computation overhead or losing information from a simplified version of the non-local block. Therefore, we proposed RAMEM, a real-time automatic M-mode echocardiography measurement scheme, contributes three aspects to answer the problems: 1) provide MEIS, a dataset of M-mode echocardiograms for instance segmentation, to enable consistent results and support the development of an automatic scheme; 2) propose panel attention, local-to-global efficient attention by pixel-unshuffling, embedding with updated UPANets V2 in a RIS scheme toward big object detection with global receptive field; 3) develop and implement AMEM, an efficient algorithm of automatic M-mode echocardiography measurement enabling fast and accurate automatic labelling among diagnosis. The experimental results show that RAMEM surpasses existing RIS backbones (with non-local attention) in PASCAL 2012 SBD and human performances in real-time MEIS tested. The code of MEIS and dataset are available at https://github.com/hanktseng131415go/RAME.

arXiv:2308.07535공식 코드 · Papers with Code

Improved Region Proposal Network for Enhanced Few-Shot Object Detection

Despite significant success of deep learning in object detection tasks, the standard training of deep neural networks requires access to a substantial quantity of annotated images across all classes. Data annotation is an arduous and time-consuming endeavor, particularly when dealing with infrequent objects. Few-shot object detection (FSOD) methods have emerged as a solution to the limitations of classic object detection approaches based on deep learning. FSOD methods demonstrate remarkable performance by achieving robust object detection using a significantly smaller amount of training data. A challenge for FSOD is that instances from novel classes that do not belong to the fixed set of training classes appear in the background and the base model may pick them up as potential objects. These objects behave similarly to label noise because they are classified as one of the training dataset classes, leading to FSOD performance degradation. We develop a semi-supervised algorithm to detect and then utilize these unlabeled novel objects as positive samples during the FSOD training stage to improve FSOD performance. Specifically, we develop a hierarchical ternary classification region proposal network (HTRPN) to localize the potential unlabeled novel objects and assign them new objectness labels to distinguish these objects from the base training dataset classes. Our improved hierarchical sampling strategy for the region proposal network (RPN) also boosts the perception ability of the object detection model for large objects. We test our approach and COCO and PASCAL VOC baselines that are commonly used in FSOD literature. Our experimental results indicate that our method is effective and outperforms the existing state-of-the-art (SOTA) FSOD methods. Our implementation is provided as a supplement to support reproducibility of the results.

arXiv:2308.07504공식 코드 · Papers with Code

ICAFusion: Iterative Cross-Attention Guided Feature Fusion for Multispectral Object Detection

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 sensitive to image misalignment due to the inherent deffciency in local-range feature interaction resulting in the performance degradation. To address this issue, a novel feature fusion framework of dual cross-attention transformers is proposed to model global feature interaction and capture complementary information across modalities simultaneously. This framework enhances the discriminability of object features through the query-guided cross-attention mechanism, leading to improved performance. However, stacking multiple transformer blocks for feature enhancement incurs a large number of parameters and high spatial complexity. To handle this, inspired by the human process of reviewing knowledge, an iterative interaction mechanism is proposed to share parameters among block-wise multimodal transformers, reducing model complexity and computation cost. The proposed method is general and effective to be integrated into different detection frameworks and used with different backbones. Experimental results on KAIST, FLIR, and VEDAI datasets show that the proposed method achieves superior performance and faster inference, making it suitable for various practical scenarios. Code will be available at https://github.com/chanchanchan97/ICAFusion.

arXiv:2308.06333공식 코드 · Papers with Code

Deep Learning-Based Open Source Toolkit for Eosinophil Detection in Pediatric Eosinophilic Esophagitis

Eosinophilic Esophagitis (EoE) is a chronic, immune/antigen-mediated esophageal disease, characterized by symptoms related to esophageal dysfunction and histological evidence of eosinophil-dominant inflammation. Owing to the intricate microscopic representation of EoE in imaging, current methodologies which depend on manual identification are not only labor-intensive but also prone to inaccuracies. In this study, we develop an open-source toolkit, named Open-EoE, to perform end-to-end whole slide image (WSI) level eosinophil (Eos) detection using one line of command via Docker. Specifically, the toolkit supports three state-of-the-art deep learning-based object detection models. Furthermore, Open-EoE further optimizes the performance by implementing an ensemble learning strategy, and enhancing the precision and reliability of our results. The experimental results demonstrated that the Open-EoE toolkit can efficiently detect Eos on a testing set with 289 WSIs. At the widely accepted threshold of >= 15 Eos per high power field (HPF) for diagnosing EoE, the Open-EoE achieved an accuracy of 91%, showing decent consistency with pathologist evaluations. This suggests a promising avenue for integrating machine learning methodologies into the diagnostic process for EoE. The docker and source code has been made publicly available at https://github.com/hrlblab/Open-EoE.

arXiv:2308.06635공식 코드 · Papers with Code

3DMOTFormer: Graph Transformer for Online 3D Multi-Object Tracking

Tracking 3D objects accurately and consistently is crucial for autonomous vehicles, enabling more reliable downstream tasks such as trajectory prediction and motion planning. Based on the substantial progress in object detection in recent years, the tracking-by-detection paradigm has become a popular choice due to its simplicity and efficiency. State-of-the-art 3D multi-object tracking (MOT) approaches typically rely on non-learned model-based algorithms such as Kalman Filter but require many manually tuned parameters. On the other hand, learning-based approaches face the problem of adapting the training to the online setting, leading to inevitable distribution mismatch between training and inference as well as suboptimal performance. In this work, we propose 3DMOTFormer, a learned geometry-based 3D MOT framework building upon the transformer architecture. We use an Edge-Augmented Graph Transformer to reason on the track-detection bipartite graph frame-by-frame and conduct data association via edge classification. To reduce the distribution mismatch between training and inference, we propose a novel online training strategy with an autoregressive and recurrent forward pass as well as sequential batch optimization. Using CenterPoint detections, our approach achieves 71.2% and 68.2% AMOTA on the nuScenes validation and test split, respectively. In addition, a trained 3DMOTFormer model generalizes well across different object detectors. Code is available at: https://github.com/dsx0511/3DMOTFormer.

arXiv:2308.06444공식 코드 · Papers with Code

TongueSAM: An Universal Tongue Segmentation Model Based on SAM with Zero-Shot

Tongue segmentation serves as the primary step in automated TCM tongue diagnosis, which plays a significant role in the diagnostic results. Currently, numerous deep learning based methods have achieved promising results. However, when confronted with tongue images that differ from the training set or possess challenging backgrounds, these methods demonstrate limited performance. To address this issue, this paper proposes a universal tongue segmentation model named TongueSAM based on SAM (Segment Anything Model). SAM is a large-scale pretrained interactive segmentation model known for its powerful zero-shot generalization capability. Applying SAM to tongue segmentation leverages its learned prior knowledge from natural images, enabling the achievement of zero-shot segmentation for various types of tongue images. In this study, a Prompt Generator based on object detection is integrated into SAM to enable an end-to-end automated tongue segmentation method. Experiments demonstrate that TongueSAM achieves exceptional performance across various of tongue segmentation datasets, particularly under zero-shot. Even when dealing with challenging background tongue images, TongueSAM achieves a mIoU of 95.23\% under zero-shot conditions, surpassing other segmentation methods. As far as we know, this is the first application of large-scale pretrained model for tongue segmentation. The project mentioned in this paper is currently publicly available.

arXiv:2308.06412공식 코드 · Papers with Code

Taming Self-Training for Open-Vocabulary Object Detection

Recent studies have shown promising performance in open-vocabulary object detection (OVD) by utilizing pseudo labels (PLs) from pretrained vision and language models (VLMs). However, teacher-student self-training, a powerful and widely used paradigm to leverage PLs, is rarely explored for OVD. This work identifies two challenges of using self-training in OVD: noisy PLs from VLMs and frequent distribution changes of PLs. To address these challenges, we propose SAS-Det that tames self-training for OVD from two key perspectives. First, we present a split-and-fusion (SAF) head that splits a standard detection into an open-branch and a closed-branch. This design can reduce noisy supervision from pseudo boxes. Moreover, the two branches learn complementary knowledge from different training data, significantly enhancing performance when fused together. Second, in our view, unlike in closed-set tasks, the PL distributions in OVD are solely determined by the teacher model. We introduce a periodic update strategy to decrease the number of updates to the teacher, thereby decreasing the frequency of changes in PL distributions, which stabilizes the training process. Extensive experiments demonstrate SAS-Det is both efficient and effective. SAS-Det outperforms recent models of the same scale by a clear margin and achieves 37.4 AP50 and 29.1 APr on novel categories of the COCO and LVIS benchmarks, respectively. Code is available at \url{https://github.com/xiaofeng94/SAS-Det}.

arXiv:2308.05991공식 코드 · Papers with Code

Cyclic-Bootstrap Labeling for Weakly Supervised Object Detection

Recent progress in weakly supervised object detection is featured by a combination of multiple instance detection networks (MIDN) and ordinal online refinement. However, with only image-level annotation, MIDN inevitably assigns high scores to some unexpected region proposals when generating pseudo labels. These inaccurate high-scoring region proposals will mislead the training of subsequent refinement modules and thus hamper the detection performance. In this work, we explore how to ameliorate the quality of pseudo-labeling in MIDN. Formally, we devise Cyclic-Bootstrap Labeling (CBL), a novel weakly supervised object detection pipeline, which optimizes MIDN with rank information from a reliable teacher network. Specifically, we obtain this teacher network by introducing a weighted exponential moving average strategy to take advantage of various refinement modules. A novel class-specific ranking distillation algorithm is proposed to leverage the output of weighted ensembled teacher network for distilling MIDN with rank information. As a result, MIDN is guided to assign higher scores to accurate proposals among their neighboring ones, thus benefiting the subsequent pseudo labeling. Extensive experiments on the prevalent PASCAL VOC 2007 \& 2012 and COCO datasets demonstrate the superior performance of our CBL framework. Code will be available at https://github.com/Yinyf0804/WSOD-CBL/.

arXiv:2308.05988공식 코드 · Papers with Code

MS3D++: Ensemble of Experts for Multi-Source Unsupervised Domain Adaption in 3D Object Detection

Deploying 3D detectors in unfamiliar domains has been demonstrated to result in a drastic drop of up to 70-90% in detection rate due to variations in lidar, geographical region, or weather conditions from their original training dataset. This domain gap leads to missing detections for densely observed objects, misaligned confidence scores, and increased high-confidence false positives, rendering the detector highly unreliable. To address this, we introduce MS3D++, a self-training framework for multi-source unsupervised domain adaptation in 3D object detection. MS3D++ provides a straightforward approach to domain adaptation by generating high-quality pseudo-labels, enabling the adaptation of 3D detectors to a diverse range of lidar types, regardless of their density. Our approach effectively fuses predictions of an ensemble of multi-frame pre-trained detectors from different source domains to improve domain generalization. We subsequently refine the predictions temporally to ensure temporal consistency in box localization and object classification. Furthermore, we present an in-depth study into the performance and idiosyncrasies of various 3D detector components in a cross-domain context, providing valuable insights for improved cross-domain detector ensembling. Experimental results on Waymo, nuScenes and Lyft demonstrate that detectors trained with MS3D++ pseudo-labels achieve state-of-the-art performance, comparable to training with human-annotated labels in Bird's Eye View (BEV) evaluation for both low and high density lidar.

arXiv:2308.05959공식 코드 · Papers with Code

Learned Point Cloud Compression for Classification

Deep learning is increasingly being used to perform machine vision tasks such as classification, object detection, and segmentation on 3D point cloud data. However, deep learning inference is computationally expensive. The limited computational capabilities of end devices thus necessitate a codec for transmitting point cloud data over the network for server-side processing. Such a codec must be lightweight and capable of achieving high compression ratios without sacrificing accuracy. Motivated by this, we present a novel point cloud codec that is highly specialized for the machine task of classification. Our codec, based on PointNet, achieves a significantly better rate-accuracy trade-off in comparison to alternative methods. In particular, it achieves a 94% reduction in BD-bitrate over non-specialized codecs on the ModelNet40 dataset. For low-resource end devices, we also propose two lightweight configurations of our encoder that achieve similar BD-bitrate reductions of 93% and 92% with 3% and 5% drops in top-1 accuracy, while consuming only 0.470 and 0.048 encoder-side kMACs/point, respectively. Our codec demonstrates the potential of specialized codecs for machine analysis of point clouds, and provides a basis for extension to more complex tasks and datasets in the future.

arXiv:2308.05820공식 코드 · Papers with Code

Recognizing Handwritten Mathematical Expressions of Vertical Addition and Subtraction

Handwritten Mathematical Expression Recognition (HMER) is a challenging task with many educational applications. Recent methods for HMER have been developed for complex mathematical expressions in standard horizontal format. However, solutions for elementary mathematical expression, such as vertical addition and subtraction, have not been explored in the literature. This work proposes a new handwritten elementary mathematical expression dataset composed of addition and subtraction expressions in a vertical format. We also extended the MNIST dataset to generate artificial images with this structure. Furthermore, we proposed a solution for offline HMER, able to recognize vertical addition and subtraction expressions. Our analysis evaluated the object detection algorithms YOLO v7, YOLO v8, YOLO-NAS, NanoDet and FCOS for identifying the mathematical symbols. We also proposed a transcription method to map the bounding boxes from the object detection stage to a mathematical expression in the LATEX markup sequence. Results show that our approach is efficient, achieving a high expression recognition rate. The code and dataset are available at https://github.com/Danielgol/HME-VAS

arXiv:2308.05480공식 코드 · Papers with Code

YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-time Object Detection

We aim at providing the object detection community with an efficient and performant object detector, termed YOLO-MS. The core design is based on a series of investigations on how convolutions with different kernel sizes affect the detection performance of objects at different scales. The outcome is a new strategy that can strongly enhance multi-scale feature representations of real-time object detectors. To verify the effectiveness of our strategy, we build a network architecture, termed YOLO-MS. We train our YOLO-MS on the MS COCO dataset from scratch without relying on any other large-scale datasets, like ImageNet, or pre-trained weights. Without bells and whistles, our YOLO-MS outperforms the recent state-of-the-art real-time object detectors, including YOLO-v7 and RTMDet, when using a comparable number of parameters and FLOPs. Taking the XS version of YOLO-MS as an example, with only 4.5M learnable parameters and 8.7G FLOPs, it can achieve an AP score of 43%+ on MS COCO, which is about 2%+ higher than RTMDet with the same model size. Moreover, our work can also be used as a plug-and-play module for other YOLO models. Typically, our method significantly improves the AP of YOLOv8 from 37%+ to 40%+ with even fewer parameters and FLOPs. Code is available at https://github.com/FishAndWasabi/YOLO-MS.