Object detection is critical in autonomous driving, and it is more practical yet challenging to localize objects of unknown categories: an endeavour known as Class-Agnostic Object Detection (CAOD). Existing studies on CAOD predominantly rely on ordinary cameras, but these frame-based sensors usually have high latency and limited dynamic range, leading to safety risks in real-world scenarios. In this study, we turn to a new modality enabled by the so-called event camera, featured by its sub-millisecond latency and high dynamic range, for robust CAOD. We propose Detecting Every Object in Events (DEOE), an approach tailored for achieving high-speed, class-agnostic open-world object detection in event-based vision. Built upon the fast event-based backbone: recurrent vision transformer, we jointly consider the spatial and temporal consistencies to identify potential objects. The discovered potential objects are assimilated as soft positive samples to avoid being suppressed as background. Moreover, we introduce a disentangled objectness head to separate the foreground-background classification and novel object discovery tasks, enhancing the model's generalization in localizing novel objects while maintaining a strong ability to filter out the background. Extensive experiments confirm the superiority of our proposed DEOE in comparison with three strong baseline methods that integrate the state-of-the-art event-based object detector with advancements in RGB-based CAOD. Our code is available at https://github.com/Hatins/DEOE.
3D object detection based on roadside cameras is an additional way for autonomous driving to alleviate the challenges of occlusion and short perception range from vehicle cameras. Previous methods for roadside 3D object detection mainly focus on modeling the depth or height of objects, neglecting the stationary of cameras and the characteristic of inter-frame consistency. In this work, we propose a novel framework, namely MOSE, for MOnocular 3D object detection with Scene cuEs. The scene cues are the frame-invariant scene-specific features, which are crucial for object localization and can be intuitively regarded as the height between the surface of the real road and the virtual ground plane. In the proposed framework, a scene cue bank is designed to aggregate scene cues from multiple frames of the same scene with a carefully designed extrinsic augmentation strategy. Then, a transformer-based decoder lifts the aggregated scene cues as well as the 3D position embeddings for 3D object location, which boosts generalization ability in heterologous scenes. The extensive experiment results on two public benchmarks demonstrate the state-of-the-art performance of the proposed method, which surpasses the existing methods by a large margin.
Traditional deep learning-based object detection networks often resize images during the data preprocessing stage to achieve a uniform size and scale in the feature map. Resizing is done to facilitate model propagation and fully connected classification. However, resizing inevitably leads to object deformation and loss of valuable information in the images. This drawback becomes particularly pronounced for tiny objects like distribution towers with linear shapes and few pixels. To address this issue, we propose abandoning the resizing operation. Instead, we introduce Positional-Encoding Multi-head Criss-Cross Attention. This allows the model to capture contextual information and learn from multiple representation subspaces, effectively enriching the semantics of distribution towers. Additionally, we enhance Spatial Pyramid Pooling by reshaping three pooled feature maps into a new unified one while also reducing the computational burden. This approach allows images of different sizes and scales to generate feature maps with uniform dimensions and can be employed in feature map propagation. Our SCAResNet incorporates these aforementioned improvements into the backbone network ResNet. We evaluated our SCAResNet using the Electric Transmission and Distribution Infrastructure Imagery dataset from Duke University. Without any additional tricks, we employed various object detection models with Gaussian Receptive Field based Label Assignment as the baseline. When incorporating the SCAResNet into the baseline model, we achieved a 2.1% improvement in mAPs. This demonstrates the advantages of our SCAResNet in detecting transmission and distribution towers and its value in tiny object detection. The source code is available at https://github.com/LisavilaLee/SCAResNet_mmdet.
In most modern object detection pipelines, the detection proposals are processed independently given the feature map. Therefore, they overlook the underlying relationships between objects and the surrounding background, which could have provided additional context for accurate detection. Because aerial imagery is almost orthographic, the spatial relations in image space closely align with those in the physical world, and inter-object and object-background relationships become particularly significant. To address this oversight, we propose a framework that leverages the strengths of Transformer-based models and Contrastive Language-Image Pre-training (CLIP) features to capture such relationships. Specifically, Building on two-stage detectors, we treat Region of Interest (RoI) proposals as tokens, accompanied by CLIP Tokens obtained from multi-level image segments. These tokens are then passed through a Transformer encoder, where specific spatial and geometric relations are incorporated into the attention weights, which are adaptively modulated and regularized. Additionally, we introduce self-supervised constraints on CLIP Tokens to ensure consistency. Extensive experiments on three benchmark datasets demonstrate that our approach achieves consistent improvements, setting new state-of-the-art results with increases of 1.37 mAP$_{50}$ on DOTA-v1.0, 5.30 mAP$_{50}$ on DOTA-v1.5, 2.30 mAP$_{50}$ on DOTA-v2.0 and 3.23 mAP$_{50}$ on DIOR-R.
Modern applications increasingly demand flexible computer vision models that adapt to novel concepts not encountered during training. This necessity is pivotal in emerging domains like extended reality, robotics, and autonomous driving, which require the ability to respond to open-world stimuli. A key ingredient is the ability to identify objects based on free-form textual queries defined at inference time - a task known as open-vocabulary object detection. Multimodal backbones like CLIP are the main enabling technology for current open-world perception solutions. Despite performing well on generic queries, recent studies highlighted limitations on the fine-grained recognition capabilities in open-vocabulary settings - i.e., for distinguishing subtle object features like color, shape, and material. In this paper, we perform a detailed examination of these open-vocabulary object recognition limitations to find the root cause. We evaluate the performance of CLIP, the most commonly used vision-language backbone, against a fine-grained object-matching benchmark, revealing interesting analogies between the limitations of open-vocabulary object detectors and their backbones. Experiments suggest that the lack of fine-grained understanding is caused by the poor separability of object characteristics in the CLIP latent space. Therefore, we try to understand whether fine-grained knowledge is present in CLIP embeddings but not exploited at inference time due, for example, to the unsuitability of the cosine similarity matching function, which may discard important object characteristics. Our preliminary experiments show that simple CLIP latent-space re-projections help separate fine-grained concepts, paving the way towards the development of backbones inherently able to process fine-grained details. The code for reproducing these experiments is available at https://github.com/lorebianchi98/FG-CLIP.
Despite previous DETR-like methods having performed successfully in generic object detection, tiny object detection is still a challenging task for them since the positional information of object queries is not customized for detecting tiny objects, whose scale is extraordinarily smaller than general objects. Also, DETR-like methods using a fixed number of queries make them unsuitable for aerial datasets, which only contain tiny objects, and the numbers of instances are imbalanced between different images. Thus, we present a simple yet effective model, named DQ-DETR, which consists of three different components: categorical counting module, counting-guided feature enhancement, and dynamic query selection to solve the above-mentioned problems. DQ-DETR uses the prediction and density maps from the categorical counting module to dynamically adjust the number of object queries and improve the positional information of queries. Our model DQ-DETR outperforms previous CNN-based and DETR-like methods, achieving state-of-the-art mAP 30.2% on the AI-TOD-V2 dataset, which mostly consists of tiny objects. Our code will be available at https://github.com/hoiliu-0801/DQ-DETR.
Monocular 3D object detection has attracted widespread attention due to its potential to accurately obtain object 3D localization from a single image at a low cost. Depth estimation is an essential but challenging subtask of monocular 3D object detection due to the ill-posedness of 2D to 3D mapping. Many methods explore multiple local depth clues such as object heights and keypoints and then formulate the object depth estimation as an ensemble of multiple depth predictions to mitigate the insufficiency of single-depth information. However, the errors of existing multiple depths tend to have the same sign, which hinders them from neutralizing each other and limits the overall accuracy of combined depth. To alleviate this problem, we propose to increase the complementarity of depths with two novel designs. First, we add a new depth prediction branch named complementary depth that utilizes global and efficient depth clues from the entire image rather than the local clues to reduce the correlation of depth predictions. Second, we propose to fully exploit the geometric relations between multiple depth clues to achieve complementarity in form. Benefiting from these designs, our method achieves higher complementarity. Experiments on the KITTI benchmark demonstrate that our method achieves state-of-the-art performance without introducing extra data. In addition, complementary depth can also be a lightweight and plug-and-play module to boost multiple existing monocular 3d object detectors. Code is available at https://github.com/elvintanhust/MonoCD.
The perception of autonomous vehicles has to be efficient, robust, and cost-effective. However, cameras are not robust against severe weather conditions, lidar sensors are expensive, and the performance of radar-based perception is still inferior to the others. Camera-radar fusion methods have been proposed to address this issue, but these are constrained by the typical sparsity of radar point clouds and often designed for radars without elevation information. We propose a novel camera-radar fusion approach called Dual Perspective Fusion Transformer (DPFT), designed to overcome these limitations. Our method leverages lower-level radar data (the radar cube) instead of the processed point clouds to preserve as much information as possible and employs projections in both the camera and ground planes to effectively use radars with elevation information and simplify the fusion with camera data. As a result, DPFT has demonstrated state-of-the-art performance on the K-Radar dataset while showing remarkable robustness against adverse weather conditions and maintaining a low inference time. The code is made available as open-source software under https://github.com/TUMFTM/DPFT.
Autonomous Driving (AD) systems are considered as the future of human mobility and transportation. Solving computer vision tasks such as image classification and object detection/segmentation, with high accuracy and low power/energy consumption, is highly needed to realize AD systems in real life. These requirements can potentially be satisfied by Spiking Neural Networks (SNNs). However, the state-of-the-art works in SNN-based AD systems still focus on proposing network models that can achieve high accuracy, and they have not systematically studied the roles of SNN parameters when used for learning event-based automotive data. Therefore, we still lack understanding of how to effectively develop SNN models for AD systems. Toward this, we propose a novel methodology to systematically study and analyze the impact of SNN parameters considering event-based automotive data, then leverage this analysis for enhancing SNN developments. To do this, we first explore different settings of SNN parameters that directly affect the learning mechanism (i.e., batch size, learning rate, neuron threshold potential, and weight decay), then analyze the accuracy results. Afterward, we propose techniques that jointly improve SNN accuracy and reduce training time. Experimental results show that our methodology can improve the SNN models for AD systems than the state-of-the-art, as it achieves higher accuracy (i.e., 86%) for the NCARS dataset, and it can also achieve iso-accuracy (i.e., ~85% with standard deviation less than 0.5%) while speeding up the training time by 1.9x. In this manner, our research work provides a set of guidelines for SNN parameter enhancements, thereby enabling the practical developments of SNN-based AD systems.
Three-dimensional perception from multi-view cameras is a crucial component in autonomous driving systems, which involves multiple tasks like 3D object detection and bird's-eye-view (BEV) semantic segmentation. To improve perception precision, large image encoders, high-resolution images, and long-term temporal inputs have been adopted in recent 3D perception models, bringing remarkable performance gains. However, these techniques are often incompatible in training and inference scenarios due to computational resource constraints. Besides, modern autonomous driving systems prefer to adopt an end-to-end framework for multi-task 3D perception, which can simplify the overall system architecture and reduce the implementation complexity. However, conflict between tasks often arises when optimizing multiple tasks jointly within an end-to-end 3D perception model. To alleviate these issues, we present an end-to-end framework named HENet for multi-task 3D perception in this paper. Specifically, we propose a hybrid image encoding network, using a large image encoder for short-term frames and a small image encoder for long-term temporal frames. Then, we introduce a temporal feature integration module based on the attention mechanism to fuse the features of different frames extracted by the two aforementioned hybrid image encoders. Finally, according to the characteristics of each perception task, we utilize BEV features of different grid sizes, independent BEV encoders, and task decoders for different tasks. Experimental results show that HENet achieves state-of-the-art end-to-end multi-task 3D perception results on the nuScenes benchmark, including 3D object detection and BEV semantic segmentation. The source code and models will be released at https://github.com/VDIGPKU/HENet.
In this paper, we investigate that the normalized coordinate expression is a key factor as reliance on hand-crafted components in query-based detectors for temporal action detection (TAD). Despite significant advancements towards an end-to-end framework in object detection, query-based detectors have been limited in achieving full end-to-end modeling in TAD. To address this issue, we propose \modelname{}, a full end-to-end temporal action detection transformer that integrates time-aligned coordinate expression. We reformulate coordinate expression utilizing actual timeline values, ensuring length-invariant representations from the extremely diverse video duration environment. Furthermore, our proposed adaptive query selection dynamically adjusts the number of queries based on video length, providing a suitable solution for varying video durations compared to a fixed query set. Our approach not only simplifies the TAD process by eliminating the need for hand-crafted components but also significantly improves the performance of query-based detectors. Our TE-TAD outperforms the previous query-based detectors and achieves competitive performance compared to state-of-the-art methods on popular benchmark datasets. Code is available at: https://github.com/Dotori-HJ/TE-TAD
Object detection in remotely sensed satellite pictures is fundamental in many fields such as biophysical, and environmental monitoring. While deep learning algorithms are constantly evolving, they have been mostly implemented and tested on popular ground-based taken photos. This paper critically evaluates and compares a suite of advanced object detection algorithms customized for the task of identifying aircraft within satellite imagery. Using the large HRPlanesV2 dataset, together with a rigorous validation with the GDIT dataset, this research encompasses an array of methodologies including YOLO versions 5 and 8, Faster RCNN, CenterNet, RetinaNet, RTMDet, and DETR, all trained from scratch. This exhaustive training and validation study reveal YOLOv5 as the preeminent model for the specific case of identifying airplanes from remote sensing data, showcasing high precision and adaptability across diverse imaging conditions. This research highlight the nuanced performance landscapes of these algorithms, with YOLOv5 emerging as a robust solution for aerial object detection, underlining its importance through superior mean average precision, Recall, and Intersection over Union scores. The findings described here underscore the fundamental role of algorithm selection aligned with the specific demands of satellite imagery analysis and extend a comprehensive framework to evaluate model efficacy. The benchmark toolkit and codes, available via https://github.com/toelt-llc/FlightScope_Bench, aims to further exploration and innovation in the realm of remote sensing object detection, paving the way for improved analytical methodologies in satellite imagery applications.
Detecting human-object interaction (HOI) has long been limited by the amount of supervised data available. Recent approaches address this issue by pre-training according to pseudo-labels, which align object regions with HOI triplets parsed from image captions. However, pseudo-labeling is tricky and noisy, making HOI pre-training a complex process. Therefore, we propose an efficient disentangled pre-training method for HOI detection (DP-HOI) to address this problem. First, DP-HOI utilizes object detection and action recognition datasets to pre-train the detection and interaction decoder layers, respectively. Then, we arrange these decoder layers so that the pre-training architecture is consistent with the downstream HOI detection task. This facilitates efficient knowledge transfer. Specifically, the detection decoder identifies reliable human instances in each action recognition dataset image, generates one corresponding query, and feeds it into the interaction decoder for verb classification. Next, we combine the human instance verb predictions in the same image and impose image-level supervision. The DP-HOI structure can be easily adapted to the HOI detection task, enabling effective model parameter initialization. Therefore, it significantly enhances the performance of existing HOI detection models on a broad range of rare categories. The code and pre-trained weight are available at https://github.com/xingaoli/DP-HOI.
Knowledge distillation is a widely adopted technique for model lightening. However, the performance of most knowledge distillation methods in the domain of object detection is not satisfactory. Typically, knowledge distillation approaches consider only the classification task among the two sub-tasks of an object detector, largely overlooking the regression task. This oversight leads to a partial understanding of the object detector's comprehensive task, resulting in skewed estimations and potentially adverse effects. Therefore, we propose a knowledge distillation method that addresses both the classification and regression tasks, incorporating a task significance strategy. By evaluating the importance of features based on the output of the detector's two sub-tasks, our approach ensures a balanced consideration of both classification and regression tasks in object detection. Drawing inspiration from real-world teaching processes and the definition of learning condition, we introduce a method that focuses on both key and weak areas. By assessing the value of features for knowledge distillation based on their importance differences, we accurately capture the current model's learning situation. This method effectively prevents the issue of biased predictions about the model's learning reality caused by an incomplete utilization of the detector's outputs.
In real-world scenarios, image recognition tasks, such as semantic segmentation and object detection, often pose greater challenges due to the lack of information available within low-resolution (LR) content. Image super-resolution (SR) is one of the promising solutions for addressing the challenges. However, due to the ill-posed property of SR, it is challenging for typical SR methods to restore task-relevant high-frequency contents, which may dilute the advantage of utilizing the SR method. Therefore, in this paper, we propose Super-Resolution for Image Recognition (SR4IR) that effectively guides the generation of SR images beneficial to achieving satisfactory image recognition performance when processing LR images. The critical component of our SR4IR is the task-driven perceptual (TDP) loss that enables the SR network to acquire task-specific knowledge from a network tailored for a specific task. Moreover, we propose a cross-quality patch mix and an alternate training framework that significantly enhances the efficacy of the TDP loss by addressing potential problems when employing the TDP loss. Through extensive experiments, we demonstrate that our SR4IR achieves outstanding task performance by generating SR images useful for a specific image recognition task, including semantic segmentation, object detection, and image classification. The implementation code is available at https://github.com/JaehaKim97/SR4IR.
Remote sensing target detection aims to identify and locate critical targets within remote sensing images, finding extensive applications in agriculture and urban planning. Feature pyramid networks (FPNs) are commonly used to extract multi-scale features. However, existing FPNs often overlook extracting low-level positional information and fine-grained context interaction. To address this, we propose a novel location refined feature pyramid network (LR-FPN) to enhance the extraction of shallow positional information and facilitate fine-grained context interaction. The LR-FPN consists of two primary modules: the shallow position information extraction module (SPIEM) and the contextual interaction module (CIM). Specifically, SPIEM first maximizes the retention of solid location information of the target by simultaneously extracting positional and saliency information from the low-level feature map. Subsequently, CIM injects this robust location information into different layers of the original FPN through spatial and channel interaction, explicitly enhancing the object area. Moreover, in spatial interaction, we introduce a simple local and non-local interaction strategy to learn and retain the saliency information of the object. Lastly, the LR-FPN can be readily integrated into common object detection frameworks to improve performance significantly. Extensive experiments on two large-scale remote sensing datasets (i.e., DOTAV1.0 and HRSC2016) demonstrate that the proposed LR-FPN is superior to state-of-the-art object detection approaches. Our code and models will be publicly available.
In autonomous driving and robotics, there is a growing interest in utilizing short-term historical data to enhance multi-camera 3D object detection, leveraging the continuous and correlated nature of input video streams. Recent work has focused on spatially aligning BEV-based features over timesteps. However, this is often limited as its gain does not scale well with long-term past observations. To address this, we advocate for supervising a model to predict objects' poses given past observations, thus explicitly guiding to learn objects' temporal cues. To this end, we propose a model called DAP (Detection After Prediction), consisting of a two-branch network: (i) a branch responsible for forecasting the current objects' poses given past observations and (ii) another branch that detects objects based on the current and past observations. The features predicting the current objects from branch (i) is fused into branch (ii) to transfer predictive knowledge. We conduct extensive experiments with the large-scale nuScenes datasets, and we observe that utilizing such predictive information significantly improves the overall detection performance. Our model can be used plug-and-play, showing consistent performance gain.
Rotation-equivariance is an essential yet challenging property in oriented object detection. While general object detectors naturally leverage robustness to spatial shifts due to the translation-equivariance of the conventional CNNs, achieving rotation-equivariance remains an elusive goal. Current detectors deploy various alignment techniques to derive rotation-invariant features, but still rely on high capacity models and heavy data augmentation with all possible rotations. In this paper, we introduce a Fully Rotation-Equivariant Oriented Object Detector (FRED), whose entire process from the image to the bounding box prediction is strictly equivariant. Specifically, we decouple the invariant task (object classification) and the equivariant task (object localization) to achieve end-to-end equivariance. We represent the bounding box as a set of rotation-equivariant vectors to implement rotation-equivariant localization. Moreover, we utilized these rotation-equivariant vectors as offsets in the deformable convolution, thereby enhancing the existing advantages of spatial adaptation. Leveraging full rotation-equivariance, our FRED demonstrates higher robustness to image-level rotation compared to existing methods. Furthermore, we show that FRED is one step closer to non-axis aligned learning through our experiments. Compared to state-of-the-art methods, our proposed method delivers comparable performance on DOTA-v1.0 and outperforms by 1.5 mAP on DOTA-v1.5, all while significantly reducing the model parameters to 16%.
Accurately identifying lychee-picking points in unstructured orchard environments and obtaining their coordinate locations is critical to the success of lychee-picking robots. However, traditional two-dimensional (2D) image-based object detection methods often struggle due to the complex geometric structures of branches, leaves and fruits, leading to incorrect determination of lychee picking points. In this study, we propose a Fcaf3d-lychee network model specifically designed for the accurate localisation of lychee picking points. Point cloud data of lychee picking points in natural environments are acquired using Microsoft's Azure Kinect DK time-of-flight (TOF) camera through multi-view stitching. We augment the Fully Convolutional Anchor-Free 3D Object Detection (Fcaf3d) model with a squeeze-and-excitation(SE) module, which exploits human visual attention mechanisms for improved feature extraction of lychee picking points. The trained network model is evaluated on a test set of lychee-picking locations and achieves an impressive F1 score of 88.57%, significantly outperforming existing models. Subsequent three-dimensional (3D) position detection of picking points in real lychee orchard environments yields high accuracy, even under varying degrees of occlusion. Localisation errors of lychee picking points are within 1.5 cm in all directions, demonstrating the robustness and generality of the model.
Because of its use in practice, open-world object detection (OWOD) has gotten a lot of attention recently. The challenge is how can a model detect novel classes and then incrementally learn them without forgetting previously known classes. Previous approaches hinge on strongly-supervised or weakly-supervised novel-class data for novel-class detection, which may not apply to real applications. We construct a new benchmark that novel classes are only encountered at the inference stage. And we propose a new OWOD detector YOLOOC, based on the YOLO architecture yet for the Open-Class setup. We introduce label smoothing to prevent the detector from over-confidently mapping novel classes to known classes and to discover novel classes. Extensive experiments conducted on our more realistic setup demonstrate the effectiveness of our method for discovering novel classes in our new benchmark.