This study provides a comprehensive analysis of the YOLOv9 object detection model, focusing on its architectural innovations, training methodologies, and performance improvements over its predecessors. Key advancements, such as the Generalized Efficient Layer Aggregation Network GELAN and Programmable Gradient Information PGI, significantly enhance feature extraction and gradient flow, leading to improved accuracy and efficiency. By incorporating Depthwise Convolutions and the lightweight C3Ghost architecture, YOLOv9 reduces computational complexity while maintaining high precision. Benchmark tests on Microsoft COCO demonstrate its superior mean Average Precision mAP and faster inference times, outperforming YOLOv8 across multiple metrics. The model versatility is highlighted by its seamless deployment across various hardware platforms, from edge devices to high performance GPUs, with built in support for PyTorch and TensorRT integration. This paper provides the first in depth exploration of YOLOv9s internal features and their real world applicability, establishing it as a state of the art solution for real time object detection across industries, from IoT devices to large scale industrial applications.
Australian National University（澳大利亚国立大学）；Data61-CSIRO
Recently, deep Convolutional Neural Networks (CNN) have demonstrated strong performance on RGB salient object detection. Although, depth information can help improve detection results, the exploration of CNNs for RGB-D salient object detection remains limited. Here we propose a novel deep CNN architecture for RGB-D salient object detection that exploits high-level, mid-level, and low level features. Further, we present novel depth features that capture the ideas of background enclosure and depth contrast that are suitable for a learned approach. We show improved results compared to state-of-th…
Northwestern Polytechnical University（西北工业大学）；Australian National University（澳大利亚国立大学）；SenseTime（商汤科技）
Camouflaged object detection (COD) aims to segment camouflaged objects hiding in the environment, which is challenging due to the similar appearance of camouflaged objects and their surroundings. Research in biology suggests depth can provide useful object localization cues for camouflaged object discovery. In this paper, we study the depth contribution for camouflaged object detection, where the depth maps are generated with existing monocular depth estimation (MDE) methods. Due to the domain gap between the MDE dataset and our COD dataset, the generated depth maps are not accurate enough to …
Australian National University（澳大利亚国立大学）；Australian Centre for Robotic Vision（澳大利亚机器人视觉中心）
The dual-pixel (DP) hardware works by splitting each pixel in half and creating an image pair in a single snapshot. Several works estimate depth/inverse depth by treating the DP pair as a stereo pair. However, dual-pixel disparity only occurs in image regions with the defocus blur. The heavy defocus blur in DP pairs affects the performance of matching-based depth estimation approaches. Instead of removing the blur effect blindly, we study the formation of the DP pair which links the blur and the depth information. In this paper, we propose a mathematical DP model which can benefit depth estima…
Self-supervised learning for depth estimation uses geometry in image sequences for supervision and shows promising results. Like many computer vision tasks, depth network performance is determined by the capability to learn accurate spatial and semantic representations from images. Therefore, it is natural to exploit semantic segmentation networks for depth estimation. In this work, based on a well-developed semantic segmentation network HRNet, we propose a novel depth estimation network DIFFNet, which can make use of semantic information in down and upsampling procedures. By applying feature …
Depth factorization and quantization have emerged as two of the principal strategies for designing efficient deep convolutional neural network (CNN) architectures tailored for low-power inference on the edge. However, there is still little detailed understanding of how different depth factorization choices affect the final, trained distributions of each layer in a CNN, particularly in the situation of quantized weights and activations. In this study, we introduce a progressive depth factorization strategy for efficient CNN architecture exploration under quantization constraints. By algorithmic…
Graz University of Technology（格拉茨工业大学）；Ulm University（乌尔姆大学）；Shanghai Jiao Tong University（上海交通大学）；BioTechMed-Graz（格拉茨生物科技医疗）；Katharinenhospital（卡塔琳娜医院）
The manual outlining of hepatic metastasis in (US) ultrasound acquisitions from patients suffering from pancreatic cancer is common practice. However, such pure manual measurements are often very time consuming, and the results repeatedly differ between the raters. In this contribution, we study the in-depth assessment of an interactive graph-based approach for the segmentation for pancreatic metastasis in US images of the liver with two specialists in Internal Medicine. Thereby, evaluating the approach with over one hundred different acquisitions of metastases. The two physicians or the algor…
Fondazione Istituto Italiano di Tecnologia (IIT)（意大利理工学院基金会）
In this work we address the problem of autonomous 3D exploration of an unknown indoor environment using a depth camera. We cast the problem as the estimation of the Next Best View (NBV) that maximises the coverage of the unknown area. We do this by re-formulating NBV estimation as a classification problem and we propose a novel learning-based metric that encodes both, the current 3D observation (a depth frame) and the history of the ongoing reconstruction. One of the major contributions of this work is about introducing a new representation for the 3D reconstruction history as an auxiliary uti…
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Microsoft Research Asia（微软亚洲研究院）；City University of Hong Kong（香港城市大学）；Peng Cheng Laboratory（鹏城实验室）
Deep learning has achieved great success in the past few years. However, the performance of deep learning is likely to impede in face of non-IID situations. Domain generalization (DG) enables a model to generalize to an unseen test distribution, i.e., to learn domain-invariant representations. In this paper, we argue that domain-invariant features should be originating from both internal and mutual sides. Internal invariance means that the features can be learned with a single domain and the features capture intrinsic semantics of data, i.e., the property within a domain, which is agnostic to …
We propose a method to reconstruct, complete and semantically label a 3D scene from a single input depth image. We improve the accuracy of the regressed semantic 3D maps by a novel architecture based on adversarial learning. In particular, we suggest using multiple adversarial loss terms that not only enforce realistic outputs with respect to the ground truth, but also an effective embedding of the internal features. This is done by correlating the latent features of the encoder working on partial 2.5D data with the latent features extracted from a variational 3D auto-encoder trained to recons…
Technical University of Munich（慕尼黑工业大学）；Canon Inc.（佳能公司）
While conventional depth estimation can infer the geometry of a scene from a single RGB image, it fails to estimate scene regions that are occluded by foreground objects. This limits the use of depth prediction in augmented and virtual reality applications, that aim at scene exploration by synthesizing the scene from a different vantage point, or at diminished reality. To address this issue, we shift the focus from conventional depth map prediction to the regression of a specific data representation called Layered Depth Image (LDI), which contains information about the occluded regions in the …
Fluid-filled soft visuotactile sensors such as the Soft-bubbles alleviate key challenges for robust manipulation, as they enable reliable grasps along with the ability to obtain high-resolution sensory feedback on contact geometry and forces. Although they are simple in construction, their utility has been limited due to size constraints introduced by enclosed custom IR/depth imaging sensors to directly measure surface deformations. Towards mitigating this limitation, we investigate the application of state-of-the-art monocular depth estimation to infer dense internal (tactile) depth maps dire…
