Modeling implicit feature interaction patterns is of significant importance to object detection tasks. However, in the two-stage detectors, due to the excessive use of hand-crafted components, it is very difficult to reason about the implicit relationship of the instance features. To tackle this problem, we analyze three different levels of feature interaction relationships, namely, the dependency relationship between the cropped local features and global features, the feature autocorrelation within the instance, and the cross-correlation relationship between the instances. To this end, we propose a more compact object detector head network (CODH), which can not only preserve global context information and condense the information density, but also allows instance-wise feature enhancement and relational reasoning in a larger matrix space. Without bells and whistles, our method can effectively improve the detection performance while significantly reducing the parameters of the model, e.g., with our method, the parameters of the head network is 0.6 times smaller than the state-of-the-art Cascade R-CNN, yet the performance boost is 1.3% on COCO test-dev. Without losing generality, we can also build a more lighter head network for other multi-stage detectors by assembling our method.
Underwater object detection (UOD) is crucial for marine economic development, environmental protection, and the planet's sustainable development. The main challenges of this task arise from low-contrast, small objects, and mimicry of aquatic organisms. The key to addressing these challenges is to focus the model on obtaining more discriminative information. We observe that the edges of underwater objects are highly unique and can be distinguished from low-contrast or mimicry environments based on their edges. Motivated by this observation, we propose an Edge-guided Representation Learning Network, termed ERL-Net, that aims to achieve discriminative representation learning and aggregation under the guidance of edge cues. Firstly, we introduce an edge-guided attention module to model the explicit boundary information, which generates more discriminative features. Secondly, a feature aggregation module is proposed to aggregate the multi-scale discriminative features by regrouping them into three levels, effectively aggregating global and local information for locating and recognizing underwater objects. Finally, we propose a wide and asymmetric receptive field block to enable features to have a wider receptive field, allowing the model to focus on more small object information. Comprehensive experiments on three challenging underwater datasets show that our method achieves superior performance on the UOD task.
We present an architecture and a training recipe that adapts pre-trained open-world image models to localization in videos. Understanding the open visual world (without being constrained by fixed label spaces) is crucial for many real-world vision tasks. Contrastive pre-training on large image-text datasets has recently led to significant improvements for image-level tasks. For more structured tasks involving object localization applying pre-trained models is more challenging. This is particularly true for video tasks, where task-specific data is limited. We show successful transfer of open-world models by building on the OWL-ViT open-vocabulary detection model and adapting it to video by adding a transformer decoder. The decoder propagates object representations recurrently through time by using the output tokens for one frame as the object queries for the next. Our model is end-to-end trainable on video data and enjoys improved temporal consistency compared to tracking-by-detection baselines, while retaining the open-world capabilities of the backbone detector. We evaluate our model on the challenging TAO-OW benchmark and demonstrate that open-world capabilities, learned from large-scale image-text pre-training, can be transferred successfully to open-world localization across diverse videos.
In industrial manufacturing, numerous tasks of visually inspecting or detecting specific objects exist that are currently performed manually or by classical image processing methods. Therefore, introducing recent deep learning models to industrial environments holds the potential to increase productivity and enable new applications. However, gathering and labeling sufficient data is often intractable, complicating the implementation of such projects. Hence, image synthesis methods are commonly used to generate synthetic training data from 3D models and annotate them automatically, although it results in a sim-to-real domain gap. In this paper, we investigate the sim-to-real generalization performance of standard object detectors on the complex industrial application of terminal strip object detection. Combining domain randomization and domain knowledge, we created an image synthesis pipeline for automatically generating the training data. Moreover, we manually annotated 300 real images of terminal strips for the evaluation. The results show the cruciality of the objects of interest to have the same scale in either domain. Nevertheless, under optimized scaling conditions, the sim-to-real performance difference in mean average precision amounts to 2.69 % for RetinaNet and 0.98 % for Faster R-CNN, qualifying this approach for industrial requirements.
Extracting and matching Re-Identification (ReID) features is used by many state-of-the-art (SOTA) Multiple Object Tracking (MOT) methods, particularly effective against frequent and long-term occlusions. While end-to-end object detection and tracking have been the main focus of recent research, they have yet to outperform traditional methods in benchmarks like MOT17 and MOT20. Thus, from an application standpoint, methods with separate detection and embedding remain the best option for accuracy, modularity, and ease of implementation, though they are impractical for edge devices due to the overhead involved. In this paper, we investigate a selective approach to minimize the overhead of feature extraction while preserving accuracy, modularity, and ease of implementation. This approach can be integrated into various SOTA methods. We demonstrate its effectiveness by applying it to StrongSORT and Deep OC-SORT. Experiments on MOT17, MOT20, and DanceTrack datasets show that our mechanism retains the advantages of feature extraction during occlusions while significantly reducing runtime. Additionally, it improves accuracy by preventing confusion in the feature-matching stage, particularly in cases of deformation and appearance similarity, which are common in DanceTrack. https://github.com/emirhanbayar/Fast-StrongSORT, https://github.com/emirhanbayar/Fast-Deep-OC-SORT
We improved an existing end-to-end polyp detection model with better average precision validated by different data sets with trivial cost on detection speed. Our previous work on detecting polyps within colonoscopy provided an efficient end-to-end solution to alleviate doctor's examination overhead. However, our later experiments found this framework is not as robust as before as the condition of polyp capturing varies. In this work, we conducted several studies on data set, identifying main issues that causes low precision rate in the task of polyp detection. We used an optimized anchor generation methods to get better anchor box shape and more boxes are used for detection as we believe this is necessary for small object detection. A alternative backbone is used to compensate the heavy time cost introduced by dense anchor box regression. With use of the attention gate module, our model can achieve state-of-the-art polyp detection performance while still maintain real-time detection speed.
This paper strives to classify and detect the relationship between object tubelets appearing within a video as a <subject-predicate-object> triplet. Where existing works treat object proposals or tubelets as single entities and model their relations a posteriori, we propose to classify and detect predicates for pairs of object tubelets a priori. We also propose Social Fabric: an encoding that represents a pair of object tubelets as a composition of interaction primitives. These primitives are learned over all relations, resulting in a compact representation able to localize and classify relations from the pool of co-occurring object tubelets across all timespans in a video. The encoding enables our two-stage network. In the first stage, we train Social Fabric to suggest proposals that are likely interacting. We use the Social Fabric in the second stage to simultaneously fine-tune and predict predicate labels for the tubelets. Experiments demonstrate the benefit of early video relation modeling, our encoding and the two-stage architecture, leading to a new state-of-the-art on two benchmarks. We also show how the encoding enables query-by-primitive-example to search for spatio-temporal video relations. Code: https://github.com/shanshuo/Social-Fabric.
In the realm of computer vision (CV), balancing speed and accuracy remains a significant challenge. Recent efforts have focused on developing lightweight networks that optimize computational efficiency and feature extraction. However, in remote sensing (RS) imagery, where small and multiscale object detection is critical, these networks often fall short in performance. To address these challenges, DecoupleNet is proposed, an innovative lightweight backbone network specifically designed for RS visual tasks in resource-constrained environments. DecoupleNet incorporates two key modules: the feature integration downsampling (FID) module and the multibranch feature decoupling (MBFD) module. The FID module preserves small object features during downsampling, while the MBFD module enhances small and multiscale object feature representation through a novel decoupling approach. Comprehensive evaluations on three RS visual tasks demonstrate DecoupleNet’s superior balance of accuracy and computational efficiency compared to existing lightweight networks. On the NWPU-RESISC45 classification dataset, DecoupleNet achieves a top-1 accuracy of 95.30%, surpassing FasterNet by 2%, with fewer parameters and lower computational overhead. In object detection tasks using the DOTA 1.0 test set, DecoupleNet records an accuracy of 78.04%, outperforming ARC-R50 by 0.69%. For semantic segmentation on the LoveDA test set, DecoupleNet achieves 53.1% accuracy, surpassing UnetFormer by 0.70%. These findings open new avenues for advancing RS image analysis on resource-constrained devices, addressing a pivotal gap in the field. The code and pretrained models are publicly available at https://github.com/lwCVer/DecoupleNet.
3D time-of-flight (ToF) imaging is used in a variety of applications such as augmented reality (AR), computer interfaces, robotics and autonomous systems. Single-photon avalanche diodes (SPADs) are one of the enabling technologies providing accurate depth data even over long ranges. By developing SPADs in array format with integrated processing combined with pulsed, flood-type illumination, high-speed 3D capture is possible. However, array sizes tend to be relatively small, limiting the lateral resolution of the resulting depth maps, and, consequently, the information that can be extracted from the image for applications such as object detection. In this paper, we demonstrate that these limitations can be overcome through the use of convolutional neural networks (CNNs) for high-performance object detection. We present outdoor results from a portable SPAD camera system that outputs 16-bin photon timing histograms with 64x32 spatial resolution. The results, obtained with exposure times down to 2 ms (equivalent to 500 FPS) and in signal-to-background (SBR) ratios as low as 0.05, point to the advantages of providing the CNN with full histogram data rather than point clouds alone. Alternatively, a combination of point cloud and active intensity data may be used as input, for a similar level of performance. In either case, the GPU-accelerated processing time is less than 1 ms per frame, leading to an overall latency (image acquisition plus processing) in the millisecond range, making the results relevant for safety-critical computer vision applications which would benefit from faster than human reaction times.
Advancements in deep learning-based 3D object detection necessitate the availability of large-scale datasets. However, this requirement introduces the challenge of manual annotation, which is often both burdensome and time-consuming. To tackle this issue, the literature has seen the emergence of several weakly supervised frameworks for 3D object detection which can automatically generate pseudo labels for unlabeled data. Nevertheless, these generated pseudo labels contain noise and are not as accurate as those labeled by humans. In this paper, we present the first approach that addresses the inherent ambiguities present in pseudo labels by introducing an Evidential Deep Learning (EDL) based uncertainty estimation framework. Specifically, we propose MEDL-U, an EDL framework based on MTrans, which not only generates pseudo labels but also quantifies the associated uncertainties. However, applying EDL to 3D object detection presents three primary challenges: (1) relatively lower pseudolabel quality in comparison to other autolabelers; (2) excessively high evidential uncertainty estimates; and (3) lack of clear interpretability and effective utilization of uncertainties for downstream tasks. We tackle these issues through the introduction of an uncertainty-aware IoU-based loss, an evidence-aware multi-task loss function, and the implementation of a post-processing stage for uncertainty refinement. Our experimental results demonstrate that probabilistic detectors trained using the outputs of MEDL-U surpass deterministic detectors trained using outputs from previous 3D annotators on the KITTI val set for all difficulty levels. Moreover, MEDL-U achieves state-of-the-art results on the KITTI official test set compared to existing 3D automatic annotators.
Recent studies have used unsupervised domain adaptive object detection (UDAOD) methods to bridge the domain gap in remote sensing (RS) images. However, UDAOD methods typically assume that the source domain data can be accessed during the domain adaptation process. This setting is often impractical in the real world due to RS data privacy and transmission difficulty. To address this challenge, we propose a practical source-free object detection (SFOD) setting for RS images, which aims to perform target domain adaptation using only the source pre-trained model. We propose a new SFOD method for RS images consisting of two parts: perturbed domain generation and alignment. The proposed multilevel perturbation constructs the perturbed domain in a simple yet efficient form by perturbing the domain-variant features at the image level and feature level according to the color and style bias. The proposed multilevel alignment calculates feature and label consistency between the perturbed domain and the target domain across the teacher-student network, and introduces the distillation of feature prototype to mitigate the noise of pseudo-labels. By requiring the detector to be consistent in the perturbed domain and the target domain, the detector is forced to focus on domaininvariant features. Extensive results of three synthetic-to-real experiments and three cross-sensor experiments have validated the effectiveness of our method which does not require access to source domain RS images. Furthermore, experiments on computer vision datasets show that our method can be extended to other fields as well. Our code will be available at: https://weixliu.github.io/ .
This paper examines the use of computer vision algorithms to estimate aspects of the psychosocial work environment using CCTV footage. We present a proof of concept for a methodology that detects and tracks people in video footage and estimates interactions between customers and employees by estimating their poses and calculating the duration of their encounters. We propose a pipeline that combines existing object detection and tracking algorithms (YOLOv8 and DeepSORT) with pose estimation algorithms (BlazePose) to estimate the number of customers and employees in the footage as well as the duration of their encounters. We use a simple rule-based approach to classify the interactions as positive, neutral or negative based on three different criteria: distance, duration and pose. The proposed methodology is tested on a small dataset of CCTV footage. While the data is quite limited in particular with respect to the quality of the footage, we have chosen this case as it represents a typical setting where the method could be applied. The results show that the object detection and tracking part of the pipeline has a reasonable performance on the dataset with a high degree of recall and reasonable accuracy. At this stage, the pose estimation is still limited to fully detect the type of interactions due to difficulties in tracking employees in the footage. We conclude that the method is a promising alternative to self-reported measures of the psychosocial work environment and could be used in future studies to obtain external observations of the work environment.
Out-of-Distribution(OOD) detection, a fundamental machine learning task aimed at identifying abnormal samples, traditionally requires model retraining for different inlier distributions. While recent research demonstrates the applicability of diffusion models to OOD detection, existing approaches are limited to Euclidean or latent image spaces. Our work extends OOD detection to trajectories in the Special Euclidean Group in 3D ($\mathbb{SE}(3)$), addressing a critical need in computer vision, robotics, and engineering applications that process object pose sequences in $\mathbb{SE}(3)$. We present $\textbf{D}$iffusion-based $\textbf{O}$ut-of-distribution detection on $\mathbb{SE}(3)$ ($\mathbf{DOSE3}$), a novel OOD framework that extends diffusion to a unified sample space of $\mathbb{SE}(3)$ pose sequences. Through extensive validation on multiple benchmark datasets, we demonstrate $\mathbf{DOSE3}$'s superior performance compared to state-of-the-art OOD detection frameworks.
This paper presents a comprehensive evaluation of state-of-the-art object detection models, including YOLOv9, YOLOv10, and RT-DETR, for the task of weed detection in smart-spraying applications focusing on three classes: Sugarbeet, Monocot, and Dicot. The performance of these models is compared based on mean Average Precision (mAP) scores and inference times on different GPU and CPU devices. We consider various model variations, such as nano, small, medium, large alongside different image resolutions (320px, 480px, 640px, 800px, 960px). The results highlight the trade-offs between inference time and detection accuracy, providing valuable insights for selecting the most suitable model for real-time weed detection. This study aims to guide the development of efficient and effective smart spraying systems, enhancing agricultural productivity through precise weed management.
This paper addresses temporal sentence grounding. Previous works typically solve this task by learning frame-level video features and align them with the textual information. A major limitation of these works is that they fail to distinguish ambiguous video frames with subtle appearance differences due to frame-level feature extraction. Recently, a few methods adopt Faster R-CNN to extract detailed object features in each frame to differentiate the fine-grained appearance similarities. However, the object-level features extracted by Faster R-CNN suffer from missing motion analysis since the object detection model lacks temporal modeling. To solve this issue, we propose a novel Motion-Appearance Reasoning Network (MARN), which incorporates both motion-aware and appearance-aware object features to better reason object relations for modeling the activity among successive frames. Specifically, we first introduce two individual video encoders to embed the video into corresponding motion-oriented and appearance-aspect object representations. Then, we develop separate motion and appearance branches to learn motion-guided and appearance-guided object relations, respectively. At last, both motion and appearance information from two branches are associated to generate more representative features for final grounding. Extensive experiments on two challenging datasets (Charades-STA and TACoS) show that our proposed MARN significantly outperforms previous state-of-the-art methods by a large margin.
Visual object tracking is an important task in computer vision, which has many real-world applications, e.g., video surveillance, visual navigation. Visual object tracking also has many challenges, e.g., object occlusion and deformation. To solve above problems and track the target accurately and efficiently, many tracking algorithms have emerged in recent years. This paper presents the rationale and representative works of two most popular tracking frameworks in past ten years, i.e., the corelation filter and Siamese network for object tracking. Then we present some deep learning based tracking methods categorized by different network structures. We also introduce some classical strategies for handling the challenges in tracking problem. Further, this paper detailedly present and compare the benchmarks and challenges for tracking, from which we summarize the development history and development trend of visual tracking. Focusing on the future development of object tracking, which we think would be applied in real-world scenes before some problems to be addressed, such as the problems in long-term tracking, low-power high-speed tracking and attack-robust tracking. In the future, the integration of multimodal data, e.g., the depth image, thermal image with traditional color image, will provide more solutions for visual tracking. Moreover, tracking task will go together with some other tasks, e.g., video object detection and segmentation.
Many practically relevant robot grasping problems feature a target object for which all grasps are occluded, e.g., by the environment. Single-shot grasp planning invariably fails in such scenarios. Instead, it is necessary to first manipulate the object into a configuration that affords a grasp. We solve this problem by learning a sequence of actions that utilize the environment to change the object's pose. Concretely, we employ hierarchical reinforcement learning to combine a sequence of learned parameterized manipulation primitives. By learning the low-level manipulation policies, our approach can control the object's state through exploiting interactions between the object, the gripper, and the environment. Designing such a complex behavior analytically would be infeasible under uncontrolled conditions, as an analytic approach requires accurate physical modeling of the interaction and contact dynamics. In contrast, we learn a hierarchical policy model that operates directly on depth perception data, without the need for object detection, pose estimation, or manual design of controllers. We evaluate our approach on picking box-shaped objects of various weight, shape, and friction properties from a constrained table-top workspace. Our method transfers to a real robot and is able to successfully complete the object picking task in 98\% of experimental trials. Supplementary information and videos can be found at https://shihminyang.github.io/ED-PMP/.
In this paper, we tackle the domain adaptive object detection problem, where the main challenge lies in significant domain gaps between source and target domains. Previous work seeks to plainly align image-level and instance-level shifts to eventually minimize the domain discrepancy. However, they still overlook to match crucial image regions and important instances across domains, which will strongly affect domain shift mitigation. In this work, we propose a simple but effective categorical regularization framework for alleviating this issue. It can be applied as a plug-and-play component on a series of Domain Adaptive Faster R-CNN methods which are prominent for dealing with domain adaptive detection. Specifically, by integrating an image-level multi-label classifier upon the detection backbone, we can obtain the sparse but crucial image regions corresponding to categorical information, thanks to the weakly localization ability of the classification manner. Meanwhile, at the instance level, we leverage the categorical consistency between image-level predictions (by the classifier) and instance-level predictions (by the detection head) as a regularization factor to automatically hunt for the hard aligned instances of target domains. Extensive experiments of various domain shift scenarios show that our method obtains a significant performance gain over original Domain Adaptive Faster R-CNN detectors. Furthermore, qualitative visualization and analyses can demonstrate the ability of our method for attending on the key regions/instances targeting on domain adaptation. Our code is open-source and available at \url{https://github.com/Megvii-Nanjing/CR-DA-DET}.
Developing artificial intelligence (AI) at the edge is always challenging, since edge devices have limited computation capability and memory resources but need to meet demanding requirements, such as real-time processing, high throughput performance, and high inference accuracy. To overcome these challenges, we propose SkyNet, an extremely lightweight DNN with 12 convolutional (Conv) layers and only 1.82 megabyte (MB) of parameters following a bottom-up DNN design approach. SkyNet is demonstrated in the 56th IEEE/ACM Design Automation Conference System Design Contest (DAC-SDC), a low power object detection challenge in images captured by unmanned aerial vehicles (UAVs). SkyNet won the first place award for both the GPU and FPGA tracks of the contest: we deliver 0.731 Intersection over Union (IoU) and 67.33 frames per second (FPS) on a TX2 GPU and deliver 0.716 IoU and 25.05 FPS on an Ultra96 FPGA.
Soft labels in image classification are vector representations of an image's true classification. In this paper, we investigate soft labels in the context of satellite object detection. We propose using detections as the basis for a new dataset of soft labels. Much of the effort in creating a high-quality model is gathering and annotating the training data. If we could use a model to generate a dataset for us, we could not only rapidly create datasets, but also supplement existing open-source datasets. Using a subset of the xView dataset, we train a YOLOv5 model to detect cars, planes, and ships. We then use that model to generate soft labels for the second training set which we then train and compare to the original model. We show that soft labels can be used to train a model that is almost as accurate as a model trained on the original data.