Salient object detection (SOD) is viewed as a pixel-wise saliency modeling task by traditional deep learning-based methods. A limitation of current SOD models is insufficient utilization of inter-pixel information, which usually results in imperfect segmentation near edge regions and low spatial coherence. As we demonstrate, using a saliency mask as the only label is suboptimal. To address this limitation, we propose a connectivity-based approach called bilateral connectivity network (BiconNet), which uses connectivity masks together with saliency masks as labels for effective modeling of inter-pixel relationships and object saliency. Moreover, we propose a bilateral voting module to enhance the output connectivity map, and a novel edge feature enhancement method that efficiently utilizes edge-specific features. Through comprehensive experiments on five benchmark datasets, we demonstrate that our proposed method can be plugged into any existing state-of-the-art saliency-based SOD framework to improve its performance with negligible parameter increase.
Video salient object detection (VSOD) aims to locate and segment the most attractive object by exploiting both spatial cues and temporal cues hidden in video sequences. However, spatial and temporal cues are often unreliable in real-world scenarios, such as low-contrast foreground, fast motion, and multiple moving objects. To address these problems, we propose a new framework to adaptively capture available information from spatial and temporal cues, which contains Confidence-guided Adaptive Gate (CAG) modules and Dual Differential Enhancement (DDE) modules. For both RGB features and optical flow features, CAG estimates confidence scores supervised by the IoU between predictions and the ground truths to re-calibrate the information with a gate mechanism. DDE captures the differential feature representation to enrich the spatial and temporal information and generate the fused features. Experimental results on four widely used datasets demonstrate the effectiveness of the proposed method against thirteen state-of-the-art methods.
In order to make autonomous driving a reality, artificial neural networks have to work reliably in the open-world. However, the open-world is vast and continuously changing, so it is not technically feasible to collect and annotate training datasets which accurately represent this domain. Therefore, there are always domain gaps between training datasets and the open-world which must be understood. In this work, we investigate the domain gaps between high-resolution and low-resolution LiDAR sensors in object detection networks. Using a unique dataset, which enables us to study sensor resolution domain gaps independent of other effects, we show two distinct domain gaps - an inference domain gap and a training domain gap. The inference domain gap is characterised by a strong dependence on the number of LiDAR points per object, while the training gap shows no such dependence. These fndings show that different approaches are required to close these inference and training domain gaps.
Automatic classification of pigmented, non-pigmented, and depigmented non-melanocytic skin lesions have garnered lots of attention in recent years. However, imaging variations in skin texture, lesion shape, depigmentation contrast, lighting condition, etc. hinder robust feature extraction, affecting classification accuracy. In this paper, we propose a new deep neural network that exploits input data for robust feature extraction. Specifically, we analyze the convolutional network's behavior (field-of-view) to find the location of deep supervision for improved feature extraction. To achieve this, first, we perform activation mapping to generate an object mask, highlighting the input regions most critical for classification output generation. Then the network layer whose layer-wise effective receptive field matches the approximated object shape in the object mask is selected as our focus for deep supervision. Utilizing different types of convolutional feature extractors and classifiers on three melanoma detection datasets and two vitiligo detection datasets, we verify the effectiveness of our new method.
Recent advancements in diffusion models have significantly enhanced the data synthesis with 2D control. Yet, precise 3D control in street view generation, crucial for 3D perception tasks, remains elusive. Specifically, utilizing Bird's-Eye View (BEV) as the primary condition often leads to challenges in geometry control (e.g., height), affecting the representation of object shapes, occlusion patterns, and road surface elevations, all of which are essential to perception data synthesis, especially for 3D object detection tasks. In this paper, we introduce MagicDrive, a novel street view generation framework, offering diverse 3D geometry controls including camera poses, road maps, and 3D bounding boxes, together with textual descriptions, achieved through tailored encoding strategies. Besides, our design incorporates a cross-view attention module, ensuring consistency across multiple camera views. With MagicDrive, we achieve high-fidelity street-view image & video synthesis that captures nuanced 3D geometry and various scene descriptions, enhancing tasks like BEV segmentation and 3D object detection.
The advancement of computer vision has pushed visual analysis tasks from still images to the video domain. In recent years, video instance segmentation, which aims to track and segment multiple objects in video frames, has drawn much attention for its potential applications in various emerging areas such as autonomous driving, intelligent transportation, and smart retail. In this paper, we propose an effective framework for instance-level visual analysis on video frames, which can simultaneously conduct object detection, instance segmentation, and multi-object tracking. The core idea of our method is collaborative multi-task learning which is achieved by a novel structure, named associative connections among detection, segmentation, and tracking task heads in an end-to-end learnable CNN. These additional connections allow information propagation across multiple related tasks, so as to benefit these tasks simultaneously. We evaluate the proposed method extensively on KITTI MOTS and MOTS Challenge datasets and obtain quite encouraging results.
Object detection and semantic segmentation are both scene understanding tasks yet they differ in data structure and information level. Object detection requires box coordinates for object instances while semantic segmentation requires pixel-wise class labels. Making use of one task's information to train the other would be beneficial for multi-task partially supervised learning where each training example is annotated only for a single task, having the potential to expand training sets with different-task datasets. This paper studies various weak losses for partially annotated data in combination with existing supervised losses. We propose Box-for-Mask and Mask-for-Box strategies, and their combination BoMBo, to distil necessary information from one task annotations to train the other. Ablation studies and experimental results on VOC and COCO datasets show favorable results for the proposed idea. Source code and data splits can be found at https://github.com/lhoangan/multas.
This review marks the tenth anniversary of You Only Look Once (YOLO), one of the most influential frameworks in real-time object detection. Over the past decade, YOLO has evolved from a streamlined detector into a diverse family of architectures characterized by efficient design, modular scalability, and cross-domain adaptability. The paper presents a technical overview of the main versions, highlights key architectural trends, and surveys the principal application areas in which YOLO has been adopted. It also addresses evaluation practices, ethical considerations, and potential future directions for the framework's continued development. The analysis aims to provide a comprehensive and critical perspective on YOLO's trajectory and ongoing transformation.
실외 3D 객체 탐지를 위한 클래스 증분 학습(CIL)은 여전히 거의 연구되지 않았다. 기존 실외 연구는 단일 벤치마크 평가에 한정되어 있으며, SDCoT++는 KITTI를, CL2OD는 nuScenes를 서로 다른 증분 설정에서 다룬다. 이로 인해 관찰된 지속 학습 거동이 자율주행 벤치마크 전반에 일반화되는지 평가하기 어렵다. 우리가 아는 한, 본 연구는 2-과제 설정과 다단계 설정을 모두 포괄하여 여러 자율주행 벤치마크에 걸친 실외 클래스 증분 3D 객체 탐지에 대한 최초의 통합 교차 벤치마크 분석을 제공한다. 우리는 (1) 기존 3D 탐지기가 이전에 학습한 클래스를 얼마나 심각하게 망각하는지, (2) 증분 학습이 지식 유지와 신규 클래스 습득 사이의 안정성-가소성 딜레마를 어떻게 드러내는지, (3) 이러한 목표의 균형을 맞추는 데 어떤 형태의 지도가 가장 효과적인지를 조사한다. 우리는 이전 단계 탐지기의 예측을 이용해 이전 클래스에 대해 누락된 지도 신호를 복원하고, 질의 단위 지식 증류를 통해 기존 클래스의 응답을 보존하며, EMA 기반 시간적 일관성 정규화를 사용하는 클래스 증분 3D 탐지 프레임워크인 CL3DOD를 제안한다. KITTI와 nuScenes에서의 실험은 두 벤치마크 모두에서 일관된 안정성-가소성 딜레마가 존재함을 보여 준다. CL3DOD는 통제된 증분 기준선보다 대체로 더 유리한 안정성-가소성 균형을 달성하며, 보고된 벤치마크 비교에서 기존에 발표된 방법들을 능가한다. 이러한 우위는 여러 증분 단계에 걸쳐 유지되어, 신규 클래스를 효과적으로 습득하면서도 이전에 학습한 지식을 강하게 유지함을 보여 준다. 우리의 코드, 평가 설정, 증분 과제 분할은 공개될 예정이다.
Wood defect detection is critical for ensuring quality control in the wood processing industry. However, current industrial applications face two major challenges: traditional methods are costly, subjective, and labor-intensive, while mainstream deep learning models often struggle to balance detection accuracy and computational efficiency for edge deployment. To address these issues, this study proposes CFIS-YOLO, a lightweight object detection model optimized for edge devices. The model introduces an enhanced C2f structure, a dynamic feature recombination module, and a novel loss function that incorporates auxiliary bounding boxes and angular constraints. These innovations improve multi-scale feature fusion and small object localization while significantly reducing computational overhead. Evaluated on a public wood defect dataset, CFIS-YOLO achieves a mean Average Precision ([email omitted]) of 77.5\%, outperforming the baseline YOLOv10s by 4 percentage points. On SOPHON BM1684X edge devices, CFIS-YOLO delivers 135 FPS, reduces power consumption to 17.3\% of the original implementation, and incurs only a 0.5 percentage point drop in mAP. These results demonstrate that CFIS-YOLO is a practical and effective solution for real-world wood defect detection in resource-constrained environments.
Most visual scene understanding tasks in the field of computer vision involve identification of the objects present in the scene. Image regions like hideouts, turns, & other obscured regions of the scene also contain crucial information, for specific surveillance tasks. Task proposed in this paper involves the design of an intelligent visual aid for identification of such locations in an image, which has either the potential to create an imminent threat from an adversary or appear as the target zones needing further investigation. Covert places (CGL) for hiding behind an occluding object are concealed 3D locations, not detectable from the viewpoint (camera). Hence this involves delineating specific image regions around the projections of outer boundary of the occluding objects, as places to be accessed around the potential hideouts. CGL detection finds applications in military counter-insurgency operations, surveillance with path planning for an exploratory robot. Given an RGB image, the goal is to identify all CGLs in the 2D scene. Identification of such regions would require knowledge about the 3D boundaries of obscuring items (pillars, furniture), their spatial location with respect to the neighboring regions of the scene. We propose this as a novel task, termed Covert Geo-Location (CGL) Detection. Classification of any region of an image as a CGL (as boundary sub-segments of an occluding object that conceals the hideout) requires examining the 3D relation between boundaries of occluding objects and their neighborhoods & surroundings. Our method successfully extracts relevant depth features from a single RGB image and quantitatively yields significant improvement over existing object detection and segmentation models adapted and trained for CGL detection. We also introduce a novel hand-annotated CGL detection dataset containing 1.5K real-world images for experimentation.
Fine-grained recognition is a challenging task due to the small intra-category variances. Most of top-performing fine-grained recognition methods leverage parts of objects for better performance. Therefore, part annotations which are extremely computationally expensive are required. In this paper, we propose a novel cascaded deep CNN detection framework for fine-grained recognition which is trained to detect the whole object without considering parts. Nevertheless, most of current top-performing detection networks use the N+1 class (N object categories plus background) softmax loss, and the background category with much more training samples dominates the feature learning progress so that the features are not good for object categories with fewer samples. To bridge this gap, we introduce a cascaded structure to eliminate background and exploit a one-vs-rest loss to capture more minute variances among different subordinate categories. Experiments show that our proposed recognition framework achieves comparable performance with state-of-the-art, part-free, fine-grained recognition methods on the CUB-200-2011 Bird dataset. Moreover, our method even outperforms most of part-based methods while does not need part annotations at the training stage and is free from any annotations at test stage.
Although low-rank and sparse decomposition based methods have been successfully applied to the problem of moving object detection using structured sparsity-inducing norms, they are still vulnerable to significant illumination changes that arise in certain applications. We are interested in moving object detection in applications involving time-lapse image sequences for which current methods mistakenly group moving objects and illumination changes into foreground. Our method relies on the multilinear (tensor) data low-rank and sparse decomposition framework to address the weaknesses of existing methods. The key to our proposed method is to create first a set of prior maps that can characterize the changes in the image sequence due to illumination. We show that they can be detected by a k-support norm. To deal with concurrent, two types of changes, we employ two regularization terms, one for detecting moving objects and the other for accounting for illumination changes, in the tensor low-rank and sparse decomposition formulation. Through comprehensive experiments using challenging datasets, we show that our method demonstrates a remarkable ability to detect moving objects under discontinuous change in illumination, and outperforms the state-of-the-art solutions to this challenging problem.
Many recent semi-supervised learning (SSL) studies build teacher-student architecture and train the student network by the generated supervisory signal from the teacher. Data augmentation strategy plays a significant role in the SSL framework since it is hard to create a weak-strong augmented input pair without losing label information. Especially when extending SSL to semi-supervised object detection (SSOD), many strong augmentation methodologies related to image geometry and interpolation-regularization are hard to utilize since they possibly hurt the location information of the bounding box in the object detection task. To address this, we introduce a simple yet effective data augmentation method, Mix/UnMix (MUM), which unmixes feature tiles for the mixed image tiles for the SSOD framework. Our proposed method makes mixed input image tiles and reconstructs them in the feature space. Thus, MUM can enjoy the interpolation-regularization effect from non-interpolated pseudo-labels and successfully generate a meaningful weak-strong pair. Furthermore, MUM can be easily equipped on top of various SSOD methods. Extensive experiments on MS-COCO and PASCAL VOC datasets demonstrate the superiority of MUM by consistently improving the mAP performance over the baseline in all the tested SSOD benchmark protocols.
Arbitrary-oriented object detection (AOOD) has been widely applied to locate and classify objects with diverse orientations in remote sensing images. However, the inconsistent features for the localization and classification tasks in AOOD models may lead to ambiguity and low-quality object predictions, which constrains the detection performance. In this article, an AOOD method called task-wise sampling convolutions (TS-Conv) is proposed. TS-Conv adaptively samples task-wise features from respective sensitive regions and maps these features together in alignment to guide a dynamic label assignment for better predictions. Specifically, sampling positions of the localization convolution in TS-Conv are supervised by the oriented bounding box (OBB) prediction associated with spatial coordinates, while sampling positions and convolutional kernel of the classification convolution are designed to be adaptively adjusted according to different orientations for improving the orientation robustness of features. Furthermore, a dynamic task-consistent-aware label assignment (DTLA) strategy is developed to select optimal candidate positions and assign labels dynamically according to ranked task-aware scores obtained from TS-Conv. Extensive experiments on several public datasets covering multiple scenes, multimodal images, and multiple categories of objects demonstrate the effectiveness, scalability, and superior performance of the proposed TS-Conv.
Accurate 3D object detection in all weather conditions remains a key challenge to enable the widespread deployment of autonomous vehicles, as most work to date has been performed on clear weather data. In order to generalize to adverse weather conditions, supervised methods perform best if trained from scratch on all weather data instead of finetuning a model pretrained on clear weather data. Training from scratch on all data will eventually become computationally infeasible and expensive as datasets continue to grow and encompass the full extent of possible weather conditions. On the other hand, naive finetuning on data from a different weather domain can result in catastrophic forgetting of the previously learned domain. Inspired by the success of replay-based continual learning methods, we propose Gradient-based Maximally Interfered Retrieval (GMIR), a gradient based sampling strategy for replay. During finetuning, GMIR periodically retrieves samples from the previous domain dataset whose gradient vectors show maximal interference with the gradient vector of the current update. Our 3D object detection experiments on the SeeingThroughFog (STF) dataset show that GMIR not only overcomes forgetting but also offers competitive performance compared to scratch training on all data with a 46.25% reduction in total training time.
Open World Object Detection (OWOD) combines open-set object detection with incremental learning capabilities to handle the challenge of the open and dynamic visual world. Existing works assume that a foreground predictor trained on the seen categories can be directly transferred to identify the unseen categories' locations by selecting the top-k most confident foreground predictions. However, the assumption is hardly valid in practice. This is because the predictor is inevitably biased to the known categories, and fails under the shift in the appearance of the unseen categories. In this work, we aim to build an unbiased foreground predictor by re-formulating the task under Unsupervised Domain Adaptation, where the current biased predictor helps form the domains: the seen object locations and confident background locations as the source domain, and the rest ambiguous ones as the target domain. Then, we adopt the simple and effective self-training method to learn a predictor based on the domain-invariant foreground features, hence achieving unbiased prediction robust to the shift in appearance between the seen and unseen categories. Our approach's pipeline can adapt to various detection frameworks and UDA methods, empirically validated by OWOD evaluation, where we achieve state-of-the-art performance.
In recent years, there have been frequent incidents of foreign objects intruding into railway and Airport runways. These objects can include pedestrians, vehicles, animals, and debris. This paper introduces an improved YOLOv5 architecture incorporating FasterNet and attention mechanisms to enhance the detection of foreign objects on railways and Airport runways. This study proposes a new dataset, AARFOD (Aero and Rail Foreign Object Detection), which combines two public datasets for detecting foreign objects in aviation and railway systems.The dataset aims to improve the recognition capabilities of foreign object targets. Experimental results on this large dataset have demonstrated significant performance improvements of the proposed model over the baseline YOLOv5 model, reducing computational requirements.Improved YOLO model shows a significant improvement in precision by 1.2%, recall rate by 1.0%, and mAP@.5 by 0.6%, while mAP@.5-.95 remained unchanged. The parameters were reduced by approximately 25.12%, and GFLOPs were reduced by about 10.63%. In the ablation experiment, it is found that the FasterNet module can significantly reduce the number of parameters of the model, and the reference of the attention mechanism can slow down the performance loss caused by lightweight.
We propose D-RISE, a method for generating visual explanations for the predictions of object detectors. Utilizing the proposed similarity metric that accounts for both localization and categorization aspects of object detection allows our method to produce saliency maps that show image areas that most affect the prediction. D-RISE can be considered "black-box" in the software testing sense, as it only needs access to the inputs and outputs of an object detector. Compared to gradient-based methods, D-RISE is more general and agnostic to the particular type of object detector being tested, and does not need knowledge of the inner workings of the model. We show that D-RISE can be easily applied to different object detectors including one-stage detectors such as YOLOv3 and two-stage detectors such as Faster-RCNN. We present a detailed analysis of the generated visual explanations to highlight the utilization of context and possible biases learned by object detectors.
Detection of military assets on the ground can be performed by applying deep learning-based object detectors on drone surveillance footage. The traditional way of hiding military assets from sight is camouflage, for example by using camouflage nets. However, large assets like planes or vessels are difficult to conceal by means of traditional camouflage nets. An alternative type of camouflage is the direct misleading of automatic object detectors. Recently, it has been observed that small adversarial changes applied to images of the object can produce erroneous output by deep learning-based detectors. In particular, adversarial attacks have been successfully demonstrated to prohibit person detections in images, requiring a patch with a specific pattern held up in front of the person, thereby essentially camouflaging the person for the detector. Research into this type of patch attacks is still limited and several questions related to the optimal patch configuration remain open. This work makes two contributions. First, we apply patch-based adversarial attacks for the use case of unmanned aerial surveillance, where the patch is laid on top of large military assets, camouflaging them from automatic detectors running over the imagery. The patch can prevent automatic detection of the whole object while only covering a small part of it. Second, we perform several experiments with different patch configurations, varying their size, position, number and saliency. Our results show that adversarial patch attacks form a realistic alternative to traditional camouflage activities, and should therefore be considered in the automated analysis of aerial surveillance imagery.