There are a huge number of features which are said to improve Convolutional Neural Network (CNN) accuracy. Practical testing of combinations of such features on large datasets, and theoretical justification of the result, is required. Some features operate on certain models exclusively and for certain problems exclusively, or only for small-scale datasets; while some features, such as batch-normalization and residual-connections, are applicable to the majority of models, tasks, and datasets. We assume that such universal features include Weighted-Residual-Connections (WRC), Cross-Stage-Partial-connections (CSP), Cross mini-Batch Normalization (CmBN), Self-adversarial-training (SAT) and Mish-activation. We use new features: WRC, CSP, CmBN, SAT, Mish activation, Mosaic data augmentation, CmBN, DropBlock regularization, and CIoU loss, and combine some of them to achieve state-of-the-art results: 43.5% AP (65.7% AP50) for the MS COCO dataset at a realtime speed of ~65 FPS on Tesla V100. Source code is at https://github.com/AlexeyAB/darknet
Video processing solutions for motion analysis are key tasks in many computer vision applications, ranging from human activity recognition to object detection. In particular, speed estimation algorithms may be relevant in contexts such as street monitoring and environment surveillance. In most realistic scenarios, the projection of a framed object of interest onto the image plane is likely to be affected by dynamic changes mainly related to perspectival transformations or periodic behaviours. Therefore, advanced speed estimation techniques need to rely on robust algorithms for object detection…
Object detection is an important yet challenging task in video understanding & analysis, where one major challenge lies in the proper balance between two contradictive factors: detection accuracy and detection speed. In this paper, we propose a new adaptive patch-of-interest composition approach for boosting both the accuracy and speed for object detection. The proposed approach first extracts patches in a video frame which have the potential to include objects-of-interest. Then, an adaptive composition process is introduced to compose the extracted patches into an optimal number of sub-frames…
Don Bosco College of Engineering and Technology of Assam Don Bosco University（阿萨姆顿巴斯科学院与顿博斯科大学工程学院）
This study is a part of design of an audio system for in-house object detection system for visually impaired, low vision personnel by birth or by an accident or due to old age. The input of the system will be scene and output as audio. Alert facility is provided based on severity levels of the objects (snake, broke glass etc) and also during difficulties. The study proposed techniques to provide speedy detection of objects based on shapes and its scale. Features are extraction to have minimum spaces using dynamic scaling. From a scene, clusters of objects are formed based on the scale and shap…
Object detection is widely used on embedded devices. With the wide availability of CNN (Convolutional Neural Networks) accelerator chips, the object detection applications are expected to run with low power consumption, and high inference speed. In addition, the CPU load is expected to be as low as possible for a CNN accelerator chip working as a co-processor with a host CPU. In this paper, we optimize the object detection model on the CNN accelerator chip by minimizing the CPU load. The resulting model is called GnetDet. The experimental result shows that the GnetDet model running on a 224mW …
The goal of this paper is to serve as a guide for selecting a detection architecture that achieves the right speed/memory/accuracy balance for a given application and platform. To this end, we investigate various ways to trade accuracy for speed and memory usage in modern convolutional object detection systems. A number of successful systems have been proposed in recent years, but apples-to-apples comparisons are difficult due to different base feature extractors (e.g., VGG, Residual Networks), different default image resolutions, as well as different hardware and software platforms. We presen…
Carnegie Mellon University（卡内基梅隆大学）；University of Texas at Austin（得克萨斯大学奥斯汀分校）
In recent years, Convolutional Neural Networks (CNNs) have shown superior capability in visual learning tasks. While accuracy-wise CNNs provide unprecedented performance, they are also known to be computationally intensive and energy demanding for modern computer systems. In this paper, we propose Virtual Pooling (ViP), a model-level approach to improve speed and energy consumption of CNN-based image classification and object detection tasks, with a provable error bound. We show the efficacy of ViP through experiments on four CNN models, three representative datasets, both desktop and mobile p…
Institute of Information Science, Academia Sinica（中央研究院信息科学研究所）
YOLOv7 surpasses all known object detectors in both speed and accuracy in the range from 5 FPS to 160 FPS and has the highest accuracy 56.8% AP among all known real-time object detectors with 30 FPS or higher on GPU V100. YOLOv7-E6 object detector (56 FPS V100, 55.9% AP) outperforms both transformer-based detector SWIN-L Cascade-Mask R-CNN (9.2 FPS A100, 53.9% AP) by 509% in speed and 2% in accuracy, and convolutional-based detector ConvNeXt-XL Cascade-Mask R-CNN (8.6 FPS A100, 55.2% AP) by 551% in speed and 0.7% AP in accuracy, as well as YOLOv7 outperforms: YOLOR, YOLOX, Scaled-YOLOv4, YOLOv…
In vision-enabled autonomous systems such as robots and autonomous cars, video object detection plays a crucial role, and both its speed and accuracy are important factors to provide reliable operation. The key insight we show in this paper is that speed and accuracy are not necessarily a trade-off when it comes to image scaling. Our results show that re-scaling the image to a lower resolution will sometimes produce better accuracy. Based on this observation, we propose a novel approach, dubbed AdaScale, which adaptively selects the input image scale that improves both accuracy and speed for v…
Small objects have relatively low resolution, the unobvious visual features which are difficult to be extracted, so the existing object detection methods cannot effectively detect small objects, and the detection speed and stability are poor. Thus, this paper proposes a small object detection algorithm based on FSSD, meanwhile, in order to reduce the computational cost and storage space, pruning is carried out to achieve model compression. Firstly, the semantic information contained in the features of different layers can be used to detect different scale objects, and the feature fusion method…
Northeastern University（东北大学）；William & Mary（威廉玛丽学院）；University of Pittsburgh（匹兹堡大学）
The rapid development and wide utilization of object detection techniques have aroused attention on both accuracy and speed of object detectors. However, the current state-of-the-art object detection works are either accuracy-oriented using a large model but leading to high latency or speed-oriented using a lightweight model but sacrificing accuracy. In this work, we propose YOLObile framework, a real-time object detection on mobile devices via compression-compilation co-design. A novel block-punched pruning scheme is proposed for any kernel size. To improve computational efficiency on mobile …
Interpolation is responsible for digital signal resampling and can significantly degrade the original signal quality if not done properly. For many years, optimal interpolation algorithms were sought within constrained classes of interpolation kernel functions. We derive a new family of unconstrained L2-optimal interpolation kernels, and compare their properties to the previously known. Although digital images are used to illustrate this work, our L2-optimal kernels can be applied to interpolate any digital signals.
Tsinghua University（清华大学）；Nuctech AI R&D Center（Nuctech人工智能研发中心）
Filter pruning has drawn more attention since resource constrained platform requires more compact model for deployment. However, current pruning methods suffer either from the inferior performance of one-shot methods, or the expensive time cost of iterative training methods. In this paper, we propose a balanced filter pruning method for both performance and pruning speed. Based on the filter importance criteria, our method is able to prune a layer with approximate layer-wise optimal pruning rate at preset loss variation. The network is pruned in the layer-wise way without the time consuming pr…
We propose a state of the art method for intelligent object recognition and video surveillance based on human visual attention. Bottom up and top down attention are applied respectively in the process of acquiring interested object(saliency map) and object recognition. The revision of 4 channel PFT method is proposed for bottom up attention and enhances the speed and accuracy. Inhibit of return (IOR) is applied in judging the sequence of saliency object pop out. Euclidean distance of color distribution, object center coordinates and speed are considered in judging whether the target is match a…
We present DroTrack, a high-speed visual single-object tracking framework for drone-captured video sequences. Most of the existing object tracking methods are designed to tackle well-known challenges, such as occlusion and cluttered backgrounds. The complex motion of drones, i.e., multiple degrees of freedom in three-dimensional space, causes high uncertainty. The uncertainty problem leads to inaccurate location predictions and fuzziness in scale estimations. DroTrack solves such issues by discovering the dependency between object representation and motion geometry. We implement an effective o…
The core of everyday tasks like reading and driving is active object recognition. Attempts to model such tasks are currently stymied by the inability to incorporate time. People show a flexible tradeoff between speed and accuracy and this tradeoff is a crucial human skill. Deep neural networks have emerged as promising candidates for predicting peak human object recognition performance and neural activity. However, modeling the temporal dimension i.e., the speed-accuracy tradeoff (SAT), is essential for them to serve as useful computational models for how humans recognize objects. To this end,…
