Adder神经网络（Addernets）在图像分类上表现出令人印象深刻的性能，只有加法操作，比使用乘法建立的传统卷积神经网络更节能。与分类相比，对通过Addernets降低现代对象探测器的能耗的强烈需求，例如自主驾驶和面部检测。在本文中，我们提出了对物体检测的addernets的实证研究。我们首先揭示了预先训练的加法器骨架中的批量归一化统计，不应冻结，因为Addernets的相对较大的特征方差。此外，我们在颈部中插入更多的快捷方式连接，并设计一个新的特征融合架构，以避免加法器层的稀疏功能。我们展示了广泛的消融研究，探讨了加法器探测器的几种设计选择。与最先进的比较在Coco和Pascal VOC基准上进行。具体而言，所提出的加法器FCOS在Coco Val集上实现了37.8 \％AP，展示了卷积对应物的相当性能，具有约1.4倍的能量减少。

在传统的对象检测框架中，从图像识别模型继承的骨干体提取了深层特征，然后颈部模块融合了这些潜在特征，以在不同的尺度上捕获信息。由于对象检测的分辨率比图像识别大得多，因此骨干的计算成本通常主导了总推断成本。这种沉重的背部设计范式主要是由于历史遗产将图像识别模型传输到对象检测时，而不是端到端的优化设计以进行对象检测。在这项工作中，我们表明这种范式确实导致了亚最佳对象检测模型。为此，我们提出了一种新型的重颈范式，长颈鹿，这是一个类似长颈鹿的网络，用于有效的对象检测。长颈鹿使用极轻的骨干和非常深的颈部模块，可同时同时在不同的空间尺度以及不同级别的潜在语义之间进行密集的信息交换。该设计范式允许检测器即使在网络的早期阶段，也可以在相同的优先级处理高级语义信息和低级空间信息，从而使其在检测任务中更有效。对多个流行对象检测基准的数值评估表明，长颈鹿在广泛的资源约束中始终优于先前的SOTA模型。源代码可在https://github.com/jyqi/giraffedet上获得。

We report competitive results on object detection and instance segmentation on the COCO dataset using standard models trained from random initialization. The results are no worse than their ImageNet pre-training counterparts even when using the hyper-parameters of the baseline system (Mask R-CNN) that were optimized for fine-tuning pretrained models, with the sole exception of increasing the number of training iterations so the randomly initialized models may converge. Training from random initialization is surprisingly robust; our results hold even when: (i) using only 10% of the training data, (ii) for deeper and wider models, and (iii) for multiple tasks and metrics. Experiments show that ImageNet pre-training speeds up convergence early in training, but does not necessarily provide regularization or improve final target task accuracy. To push the envelope we demonstrate 50.9 AP on COCO object detection without using any external data-a result on par with the top COCO 2017 competition results that used ImageNet pre-training. These observations challenge the conventional wisdom of ImageNet pre-training for dependent tasks and we expect these discoveries will encourage people to rethink the current de facto paradigm of 'pretraining and fine-tuning' in computer vision.

ous vision tasks without convolutions, where it can be used as a direct replacement for CNN backbones. (3) We validate PVT through extensive experiments, showing that it boosts the performance of many downstream tasks, including object detection, instance and semantic segmentation. For example, with a comparable number of parameters, PVT+RetinaNet achieves 40.4 AP on the COCO dataset, surpassing ResNet50+RetinNet (36.3 AP) by 4.1 absolute AP (see Figure 2). We hope that PVT could serve as an alternative and useful backbone for pixel-level predictions and facilitate future research.

由于存储器和计算资源有限，部署在移动设备上的卷积神经网络（CNNS）是困难的。我们的目标是通过利用特征图中的冗余来设计包括CPU和GPU的异构设备的高效神经网络，这很少在神经结构设计中进行了研究。对于类似CPU的设备，我们提出了一种新颖的CPU高效的Ghost（C-Ghost）模块，以生成从廉价操作的更多特征映射。基于一组内在的特征映射，我们使用廉价的成本应用一系列线性变换，以生成许多幽灵特征图，可以完全揭示内在特征的信息。所提出的C-Ghost模块可以作为即插即用组件，以升级现有的卷积神经网络。 C-Ghost瓶颈旨在堆叠C-Ghost模块，然后可以轻松建立轻量级的C-Ghostnet。我们进一步考虑GPU设备的有效网络。在建筑阶段的情况下，不涉及太多的GPU效率（例如，深度明智的卷积），我们建议利用阶段明智的特征冗余来制定GPU高效的幽灵（G-GHOST）阶段结构。舞台中的特征被分成两个部分，其中使用具有较少输出通道的原始块处理第一部分，用于生成内在特征，另一个通过利用阶段明智的冗余来生成廉价的操作。在基准测试上进行的实验证明了所提出的C-Ghost模块和G-Ghost阶段的有效性。 C-Ghostnet和G-Ghostnet分别可以分别实现CPU和GPU的准确性和延迟的最佳权衡。代码可在https://github.com/huawei-noah/cv-backbones获得。

压缩高准确性卷积神经网络（CNN）的最新进展已经见证了实时对象检测的显着进步。为了加速检测速度，轻质检测器总是使用单路主链几乎没有卷积层。但是，单路径架构涉及连续的合并和下采样操作，始终导致粗糙和不准确的特征图，这些图形不利，无法找到对象。另一方面，由于网络容量有限，最近的轻质网络在表示大规模的视觉数据方面通常很弱。为了解决这些问题，本文提出了一个名为DPNET的双路径网络，并采用了实时对象检测的轻巧注意方案。双路径体系结构使我们能够与提取物相对于高级语义特征和低级对象详细信息。尽管DPNET相对于单路检测器几乎具有重复的形状，但计算成本和模型大小并未显着增加。为了增强表示能力，轻巧的自相关模块（LSCM）旨在捕获全局交互，只有很少的计算开销和网络参数。在颈部，LSCM扩展到轻质互相关模块（LCCM），从而捕获相邻尺度特征之间的相互依赖性。我们已经对Coco和Pascal VOC 2007数据集进行了详尽的实验。实验结果表明，DPNET在检测准确性和实施效率之间实现了最新的权衡。具体而言，DPNET在MS COCO Test-DEV上可实现30.5％的AP，Pascal VOC 2007测试集上的81.5％地图，MWITH近250万型号，1.04 GFLOPS，1.04 GFLOPS和164 fps和196 fps和196 fps，320 x 320输入图像的320 x 320输入图像。

In this report, we present a fast and accurate object detection method dubbed DAMO-YOLO, which achieves higher performance than the state-of-the-art YOLO series. DAMO-YOLO is extended from YOLO with some new technologies, including Neural Architecture Search (NAS), efficient Reparameterized Generalized-FPN (RepGFPN), a lightweight head with AlignedOTA label assignment, and distillation enhancement. In particular, we use MAE-NAS, a method guided by the principle of maximum entropy, to search our detection backbone under the constraints of low latency and high performance, producing ResNet-like / CSP-like structures with spatial pyramid pooling and focus modules. In the design of necks and heads, we follow the rule of "large neck, small head". We import Generalized-FPN with accelerated queen-fusion to build the detector neck and upgrade its CSPNet with efficient layer aggregation networks (ELAN) and reparameterization. Then we investigate how detector head size affects detection performance and find that a heavy neck with only one task projection layer would yield better results. In addition, AlignedOTA is proposed to solve the misalignment problem in label assignment. And a distillation schema is introduced to improve performance to a higher level. Based on these new techs, we build a suite of models at various scales to meet the needs of different scenarios, i.e., DAMO-YOLO-Tiny/Small/Medium. They can achieve 43.0/46.8/50.0 mAPs on COCO with the latency of 2.78/3.83/5.62 ms on T4 GPUs respectively. The code is available at https://github.com/tinyvision/damo-yolo.

Deploying convolutional neural networks (CNNs) on embedded devices is difficult due to the limited memory and computation resources. The redundancy in feature maps is an important characteristic of those successful CNNs, but has rarely been investigated in neural architecture design. This paper proposes a novel Ghost module to generate more feature maps from cheap operations. Based on a set of intrinsic feature maps, we apply a series of linear transformations with cheap cost to generate many ghost feature maps that could fully reveal information underlying intrinsic features. The proposed Ghost module can be taken as a plug-and-play component to upgrade existing convolutional neural networks. Ghost bottlenecks are designed to stack Ghost modules, and then the lightweight Ghost-Net can be easily established. Experiments conducted on benchmarks demonstrate that the proposed Ghost module is an impressive alternative of convolution layers in baseline models, and our GhostNet can achieve higher recognition performance (e.g. 75.7% top-1 accuracy) than MobileNetV3 with similar computational cost on the ImageNet ILSVRC-2012 classification dataset. Code is available at https: //github.com/huawei-noah/ghostnet.

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. First, we propose a weighted bi-directional feature pyramid network (BiFPN), which allows easy and fast multiscale feature fusion; Second, we propose a compound scaling method that uniformly scales the resolution, depth, and width for all backbone, feature network, and box/class prediction networks at the same time. Based on these optimizations and better backbones, we have developed a new family of object detectors, called EfficientDet, which consistently achieve much better efficiency than prior art across a wide spectrum of resource constraints. In particular, with singlemodel and single-scale, our EfficientDet-D7 achieves stateof-the-art 55.1 AP on COCO test-dev with 77M parameters and 410B FLOPs 1 , being 4x -9x smaller and using 13x -42x fewer FLOPs than previous detectors. Code is available at https://github.com/google/automl/tree/ master/efficientdet.

在对象检测模型中，检测骨干机消耗超过一半的整体推理成本。最近的研究试图通过在神经结构搜索（NAS）的帮助下优化骨干架构来降低这一成本。然而，对象检测的现有NAS方法需要数百至数千个GPU小时的搜索，使它们在快节奏的研究和开发中不切实际。在这项工作中，我们提出了一种新的零射NAS方法来解决这个问题。所提出的方法，命名为Zendet，在不训练网络参数的情况下自动设计有效的检测骨干网，从而降低了架构设计成本，几乎归零但提供了最先进的（SOTA）性能。在引擎盖下，Zendet最大化了检测骨干的差分熵，导致对象检测的更好的特征提取器，在相同的计算预算下。在仅为全自动设计的一个GPU日之后，Zendet在多个检测基准数据集上创新了SOTA检测骨干，具有很少的人为干预。与Reset-50个骨干相比，Zendet在Map中使用相同数量的拖波/参数时更好地+ 2.0％，并且在同一地图上的NVIDIA V100速度快1.54倍。稍后将发布代码和预先训练的型号。

特征金字塔网络（FPN）已成为对象检测模型考虑对象的各种尺度的重要模块。但是，小物体上的平均精度（AP）相对低于中和大物体上的AP。原因是CNN较深层导致信息丢失作为特征提取水平的原因。我们提出了一个新的比例顺序（S^2）特征FPN的特征提取，以增强小物体的特征信息。我们将FPN结构视为尺度空间和提取尺度序列（s^2）特征，该特征是在FPN的水平轴上通过3D卷积。它基本上是扩展不变的功能，并建立在小物体的高分辨率金字塔功能图上。此外，建议的S^2功能可以扩展到基于FPN的大多数对象检测模型。我们证明所提出的S2功能可以提高COCO数据集中一阶段和两阶段探测器的性能。根据提出的S2功能，我们分别为Yolov4-P5和Yolov4-P6获得了高达1.3％和1.1％的AP改善。对于更快的RCNN和Mask R-CNN，我们分别观察到AP改进的2.0％和1.6％，分别具有建议的S^2功能。

二进制神经网络（BNNS）对现实世界中嵌入式设备显示出巨大的希望。作为实现强大BNN的关键步骤之一，规模因子计算在减少其实价对应物的性能差距方面起着至关重要的作用。然而，现有的BNN忽略了实价重量和尺度因子的固有双线关系，从而导致训练过程不足引起的亚最佳模型。为了解决这个问题，提出了复发性双线性优化，以通过将固有的双线性变量关联到背面传播过程中，以改善BNNS（RBONN）的学习过程。我们的工作是从双线性角度优化BNN的首次尝试。具体而言，我们采用经常​​性优化和密度 - 列表来依次回溯稀疏的实价过滤器，该过滤器将经过充分的训练并基于可控的学习过程达到其性能限制。我们获得了强大的rbonn，在各种模型和数据集上的最先进的BNN上表现出令人印象深刻的性能。特别是，在对象检测的任务下，rbonn具有出色的概括性能。我们的代码在https://github.com/stevetsui/rbonn上进行开源。

In this paper, we aim to design an efficient real-time object detector that exceeds the YOLO series and is easily extensible for many object recognition tasks such as instance segmentation and rotated object detection. To obtain a more efficient model architecture, we explore an architecture that has compatible capacities in the backbone and neck, constructed by a basic building block that consists of large-kernel depth-wise convolutions. We further introduce soft labels when calculating matching costs in the dynamic label assignment to improve accuracy. Together with better training techniques, the resulting object detector, named RTMDet, achieves 52.8% AP on COCO with 300+ FPS on an NVIDIA 3090 GPU, outperforming the current mainstream industrial detectors. RTMDet achieves the best parameter-accuracy trade-off with tiny/small/medium/large/extra-large model sizes for various application scenarios, and obtains new state-of-the-art performance on real-time instance segmentation and rotated object detection. We hope the experimental results can provide new insights into designing versatile real-time object detectors for many object recognition tasks. Code and models are released at https://github.com/open-mmlab/mmdetection/tree/3.x/configs/rtmdet.

本文提出了平行残留的双融合特征金字塔网络（PRB-FPN），以快速准确地单光对象检测。特征金字塔（FP）在最近的视觉检测中被广泛使用，但是由于汇总转换，FP的自上而下的途径无法保留准确的定位。随着使用更多层的更深骨干，FP的优势被削弱了。此外，它不能同时准确地检测到小物体。为了解决这些问题，我们提出了一种新的并行FP结构，具有双向（自上而下和自下而上）的融合以及相关的改进，以保留高质量的特征以进行准确定位。我们提供以下设计改进：（1）具有自下而上的融合模块（BFM）的平行分歧FP结构，以高精度立即检测小物体和大对象。 （2）串联和重组（CORE）模块为特征融合提供了自下而上的途径，该途径导致双向融合FP，可以从低层特征图中恢复丢失的信息。 （3）进一步纯化核心功能以保留更丰富的上下文信息。自上而下和自下而上的途径中的这种核心净化只能在几次迭代中完成。 （4）将残留设计添加到核心中，导致了一个新的重核模块，该模块可以轻松训练和集成，并具有更深入或更轻的骨架。所提出的网络可在UAVDT17和MS COCO数据集上实现最新性能。代码可在https://github.com/pingyang1117/prbnet_pytorch上找到。

特征金字塔网络（FPN）是对象检测器的关键组件之一。但是，对于研究人员来说，长期存在的难题是，引入FPN后通常会抑制大规模物体的检测性能。为此，本文首先在检测框架中重新审视FPN，并从优化的角度揭示了FPN成功的性质。然后，我们指出，大规模对象的性能退化是由于集成FPN后出现不当后传播路径所致。它使每个骨干网络的每个级别都只能查看一定尺度范围内的对象。基于这些分析，提出了两种可行的策略，以使每个级别的级别能够查看基于FPN的检测框架中的所有对象。具体而言，一个是引入辅助目标功能，以使每个骨干级在训练过程中直接接收各种尺度对象的后传播信号。另一个是以更合理的方式构建特征金字塔，以避免非理性的背部传播路径。对可可基准测试的广泛实验验证了我们的分析的健全性和方法的有效性。没有铃铛和口哨，我们证明了我们的方法在各种检测框架上实现了可靠的改进（超过2％）：一阶段，两阶段，基于锚的，无锚和变压器的检测器。

锥体网络是多尺度对象检测的标准方法。当前对特征金字塔网络的研究通常采用层连接来从特征层次结构的某些级别收集特征，并且不考虑它们之间的显着差异。我们提出了一个更好的特征金字塔网络的体系结构，称为选择性多尺度学习（SMSL），以解决此问题。SMSL高效且泛滥，可以将其集成到单阶段和两阶段检测器中以提高检测性能，几乎没有额外的推理成本。视网膜与SMSL的结合获得了可可数据集的AP（从39.1 \％到40.9 \％）的1.8 \％改进。与SMSL集成时，两阶段探测器的AP可以提高1.0 \％。

由于卷积在提取物体的局部上下文中，在过去十年中，对象检测在过去十年中取得了重大进展。但是，对象的尺度是多样的，当前卷积只能处理单尺度输入。因此，传统卷积具有固定接收场在处理这种规模差异问题方面的能力受到限制。多尺度功能表示已被证明是缓解规模差异问题的有效方法。最近的研究主要与某些量表或各个尺度的总体特征采用部分联系，并专注于整个量表的全球信息。但是，跨空间和深度维度的信息被忽略了。受此启发，我们提出了多尺度卷积（MSCONV）来解决此问题。同时考虑到量表，空间和深度信息，MSCONV能够更全面地处理多尺度输入。 MSCONV是有效的，并且在计算上是有效的，只有少量计算成本增加。对于大多数单阶段对象探测器，在检测头中用MSCONV代替传统的卷积可以带来AP的2.5 \％改进（在Coco 2017数据集上），只有3 \％的拖鞋增加了。 MSCONV对于两阶段对象探测器也具有灵活性和有效性。当扩展到主流两阶段对象检测器时，MSCONV的AP可以提高3.0 \％。我们在单尺度测试下的最佳模型在Coco 2017上实现了48.9 \％AP，\ textit {test-dev} Split，它超过了许多最新方法。

Representing features at multiple scales is of great importance for numerous vision tasks. Recent advances in backbone convolutional neural networks (CNNs) continually demonstrate stronger multi-scale representation ability, leading to consistent performance gains on a wide range of applications. However, most existing methods represent the multi-scale features in a layerwise manner. In this paper, we propose a novel building block for CNNs, namely Res2Net, by constructing hierarchical residual-like connections within one single residual block. The Res2Net represents multi-scale features at a granular level and increases the range of receptive fields for each network layer. The proposed Res2Net block can be plugged into the state-of-the-art backbone CNN models, e.g., ResNet, ResNeXt, and DLA. We evaluate the Res2Net block on all these models and demonstrate consistent performance gains over baseline models on widely-used datasets, e.g., CIFAR-100 and ImageNet. Further ablation studies and experimental results on representative computer vision tasks, i.e., object detection, class activation mapping, and salient object detection, further verify the superiority of the Res2Net over the state-of-the-art baseline methods. The source code and trained models are available on https://mmcheng.net/res2net/.

In object detection, the intersection over union (IoU) threshold is frequently used to define positives/negatives. The threshold used to train a detector defines its quality. While the commonly used threshold of 0.5 leads to noisy (low-quality) detections, detection performance frequently degrades for larger thresholds. This paradox of high-quality detection has two causes: 1) overfitting, due to vanishing positive samples for large thresholds, and 2) inference-time quality mismatch between detector and test hypotheses. A multi-stage object detection architecture, the Cascade R-CNN, composed of a sequence of detectors trained with increasing IoU thresholds, is proposed to address these problems. The detectors are trained sequentially, using the output of a detector as training set for the next. This resampling progressively improves hypotheses quality, guaranteeing a positive training set of equivalent size for all detectors and minimizing overfitting. The same cascade is applied at inference, to eliminate quality mismatches between hypotheses and detectors. An implementation of the Cascade R-CNN without bells or whistles achieves state-of-the-art performance on the COCO dataset, and significantly improves high-quality detection on generic and specific object detection datasets, including VOC, KITTI, CityPerson, and WiderFace. Finally, the Cascade R-CNN is generalized to instance segmentation, with nontrivial improvements over the Mask R-CNN. To facilitate future research, two implementations are made available at https://github.com/zhaoweicai/cascade-rcnn (Caffe) and https://github.com/zhaoweicai/Detectron-Cascade-RCNN (Detectron).

Batch Normalization (BN) is a milestone technique in the development of deep learning, enabling various networks to train. However, normalizing along the batch dimension introduces problems -BN's error increases rapidly when the batch size becomes smaller, caused by inaccurate batch statistics estimation. This limits BN's usage for training larger models and transferring features to computer vision tasks including detection, segmentation, and video, which require small batches constrained by memory consumption. In this paper, we present Group Normalization (GN) as a simple alternative to BN. GN divides the channels into groups and computes within each group the mean and variance for normalization. GN's computation is independent of batch sizes, and its accuracy is stable in a wide range of batch sizes. On ResNet-50 trained in ImageNet, GN has 10.6% lower error than its BN counterpart when using a batch size of 2; when using typical batch sizes, GN is comparably good with BN and outperforms other normalization variants. Moreover, GN can be naturally transferred from pre-training to fine-tuning. GN can outperform its BNbased counterparts for object detection and segmentation in COCO, 1 and for video classification in Kinetics, showing that GN can effectively replace the powerful BN in a variety of tasks. GN can be easily implemented by a few lines of code in modern libraries.