Visual object detection is a computer vision-based artificial intelligence (AI) technique which has many practical applications (e.g., fire hazard monitoring). However, due to privacy concerns and the high cost of transmitting video data, it is highly challenging to build object detection models on centrally stored large training datasets following the current approach. Federated learning (FL) is a promising approach to resolve this challenge. Nevertheless, there currently lacks an easy to use tool to enable computer vision application developers who are not experts in federated learning to conveniently leverage this technology and apply it in their systems. In this paper, we report FedVision - a machine learning engineering platform to support the development of federated learning powered computer vision applications. The platform has been deployed through a collaboration between WeBank and Extreme Vision to help customers develop computer vision-based safety monitoring solutions in smart city applications. Over four months of usage, it has achieved significant efficiency improvement and cost reduction while removing the need to transmit sensitive data for three major corporate customers. To the best of our knowledge, this is the first real application of FL in computer vision-based tasks.
Object detection has recently achieved a breakthrough for removing the last one non-differentiable component in the pipeline, Non-Maximum Suppression (NMS), and building up an end-to-end system. However, what makes for its one-to-one prediction has not been well understood. In this paper, we first point out that one-to-one positive sample assignment is the key factor, while, one-to-many assignment in previous detectors causes redundant predictions in inference. Second, we surprisingly find that even training with one-to-one assignment, previous detectors still produce redundant predictions. We identify that classification cost in matching cost is the main ingredient: (1) previous detectors only consider location cost, (2) by additionally introducing classification cost, previous detectors immediately produce one-to-one prediction during inference. We introduce the concept of score gap to explore the effect of matching cost. Classification cost enlarges the score gap by choosing positive samples as those of highest score in the training iteration and reducing noisy positive samples brought by only location cost. Finally, we demonstrate the advantages of end-to-end object detection on crowded scenes. The code is available at: \url{https://github.com/PeizeSun/OneNet}.
Salient object detection(SOD) aims at locating the most significant object within a given image. In recent years, great progress has been made in applying SOD on many vision tasks. The depth map could provide additional spatial prior and boundary cues to boost the performance. Combining the depth information with image data obtained from standard visual cameras has been widely used in recent SOD works, however, introducing depth information in a suboptimal fusion strategy may have negative influence in the performance of SOD. In this paper, we discuss about the advantages of the so-called progressive multi-scale fusion method and propose a mask-guided feature aggregation module(MGFA). The proposed framework can effectively combine the two features of different modalities and, furthermore, alleviate the impact of erroneous depth features, which are inevitably caused by the variation of depth quality. We further introduce a mask-guided refinement module(MGRM) to complement the high-level semantic features and reduce the irrelevant features from multi-scale fusion, leading to an overall refinement of detection. Experiments on five challenging benchmarks demonstrate that the proposed method outperforms 11 state-of-the-art methods under different evaluation metrics.
Besides standard cameras, autonomous vehicles typically include multiple additional sensors, such as lidars and radars, which help acquire richer information for perceiving the content of the driving scene. While several recent works focus on fusing certain pairs of sensors - such as camera with lidar or radar - by using architectural components specific to the examined setting, a generic and modular sensor fusion architecture is missing from the literature. In this work, we propose HRFuser, a modular architecture for multi-modal 2D object detection. It fuses multiple sensors in a multi-resolution fashion and scales to an arbitrary number of input modalities. The design of HRFuser is based on state-of-the-art high-resolution networks for image-only dense prediction and incorporates a novel multi-window cross-attention block as the means to perform fusion of multiple modalities at multiple resolutions. We demonstrate via extensive experiments on nuScenes and the adverse conditions DENSE datasets that our model effectively leverages complementary features from additional modalities, substantially improving upon camera-only performance and consistently outperforming state-of-the-art 3D and 2D fusion methods evaluated on 2D object detection metrics. The source code is publicly available.
Recent human-object interaction (HOI) detection methods depend on extensively annotated image datasets, which require a significant amount of manpower. In this paper, we propose a novel self-adaptive, language-driven HOI detection method, termed FreeA. This method leverages the adaptability of the text-image model to generate latent HOI labels without requiring manual annotation. Specifically, FreeA aligns image features of human-object pairs with HOI text templates and employs a knowledge-based masking technique to decrease improbable interactions. Furthermore, FreeA implements a proposed method for matching interaction correlations to increase the probability of actions associated with a particular action, thereby improving the generated HOI labels. Experiments on two benchmark datasets showcase that FreeA achieves state-of-the-art performance among weakly supervised HOI competitors. Our proposal gets +\textbf{13.29} (\textbf{159\%$\uparrow$}) mAP and +\textbf{17.30} (\textbf{98\%$\uparrow$}) mAP than the newest ``Weakly'' supervised model, and +\textbf{7.19} (\textbf{28\%$\uparrow$}) mAP and +\textbf{14.69} (\textbf{34\%$\uparrow$}) mAP than the latest ``Weakly+'' supervised model, respectively, on HICO-DET and V-COCO datasets, more accurate in localizing and classifying the interactive actions. The source code will be made public.
Recently, numerous methods have achieved impressive performance in remote sensing object detection, relying on convolution or transformer architectures. Such detectors typically have a feature backbone to extract useful features from raw input images. For the remote sensing domain, a common practice among current detectors is to initialize the backbone with pre-training on ImageNet consisting of natural scenes. Fine-tuning the backbone is then typically required to generate features suitable for remote-sensing images. However, this could hinder the extraction of basic visual features in long-term training, thus restricting performance improvement. To mitigate this issue, we propose a novel method named DBF (Dynamic Backbone Freezing) for feature backbone fine-tuning on remote sensing object detection. Our method aims to handle the dilemma of whether the backbone should extract low-level generic features or possess specific knowledge of the remote sensing domain, by introducing a module called 'Freezing Scheduler' to dynamically manage the update of backbone features during training. Extensive experiments on DOTA and DIOR-R show that our approach enables more accurate model learning while substantially reducing computational costs. Our method can be seamlessly adopted without additional effort due to its straightforward design.
Camouflaged object detection (COD) aims to identify the objects that seamlessly blend into the surrounding backgrounds. Due to the intrinsic similarity between the camouflaged objects and the background region, it is extremely challenging to precisely distinguish the camouflaged objects by existing approaches. In this paper, we propose a hierarchical graph interaction network termed HGINet for camouflaged object detection, which is capable of discovering imperceptible objects via effective graph interaction among the hierarchical tokenized features. Specifically, we first design a region-aware token focusing attention (RTFA) with dynamic token clustering to excavate the potentially distinguishable tokens in the local region. Afterwards, a hierarchical graph interaction transformer (HGIT) is proposed to construct bi-directional aligned communication between hierarchical features in the latent interaction space for visual semantics enhancement. Furthermore, we propose a decoder network with confidence aggregated feature fusion (CAFF) modules, which progressively fuses the hierarchical interacted features to refine the local detail in ambiguous regions. Extensive experiments conducted on the prevalent datasets, i.e. COD10K, CAMO, NC4K and CHAMELEON demonstrate the superior performance of HGINet compared to existing state-of-the-art methods. Our code is available at https://github.com/Garyson1204/HGINet.
A major challenge in scaling object detection is the difficulty of obtaining labeled images for large numbers of categories. Recently, deep convolutional neural networks (CNNs) have emerged as clear winners on object classification benchmarks, in part due to training with 1.2M+ labeled classification images. Unfortunately, only a small fraction of those labels are available for the detection task. It is much cheaper and easier to collect large quantities of image-level labels from search engines than it is to collect detection data and label it with precise bounding boxes. In this paper, we propose Large Scale Detection through Adaptation (LSDA), an algorithm which learns the difference between the two tasks and transfers this knowledge to classifiers for categories without bounding box annotated data, turning them into detectors. Our method has the potential to enable detection for the tens of thousands of categories that lack bounding box annotations, yet have plenty of classification data. Evaluation on the ImageNet LSVRC-2013 detection challenge demonstrates the efficacy of our approach. This algorithm enables us to produce a >7.6K detector by using available classification data from leaf nodes in the ImageNet tree. We additionally demonstrate how to modify our architecture to produce a fast detector (running at 2fps for the 7.6K detector). Models and software are available at
Object counting is an important task in computer vision due to its growing demand in applications such as surveillance, traffic monitoring, and counting everyday objects. State-of-the-art methods use regression-based optimization where they explicitly learn to count the objects of interest. These often perform better than detection-based methods that need to learn the more difficult task of predicting the location, size, and shape of each object. However, we propose a detection-based method that does not need to estimate the size and shape of the objects and that outperforms regression-based methods. Our contributions are three-fold: (1) we propose a novel loss function that encourages the network to output a single blob per object instance using point-level annotations only; (2) we design two methods for splitting large predicted blobs between object instances; and (3) we show that our method achieves new state-of-the-art results on several challenging datasets including the Pascal VOC and the Penguins dataset. Our method even outperforms those that use stronger supervision such as depth features, multi-point annotations, and bounding-box labels.
Object recognition and 6DoF pose estimation are quite challenging tasks in computer vision applications. Despite efficiency in such tasks, standard methods deliver far from real-time processing rates. This paper presents a novel pipeline to estimate a fine 6DoF pose of objects, applied to realistic scenarios in real-time. We split our proposal into three main parts. Firstly, a Color feature classification leverages the use of pre-trained CNN color features trained on the ImageNet for object detection. A Feature-based registration module conducts a coarse pose estimation, and finally, a Fine-adjustment step performs an ICP-based dense registration. Our proposal achieves, in the best case, an accuracy performance of almost 83\% on the RGB-D Scenes dataset. Regarding processing time, the object detection task is done at a frame processing rate up to 90 FPS, and the pose estimation at almost 14 FPS in a full execution strategy. We discuss that due to the proposal's modularity, we could let the full execution occurs only when necessary and perform a scheduled execution that unlocks real-time processing, even for multitask situations.
In the field of deep learning based computer vision, the development of deep object detection has led to unique paradigms (e.g., two-stage or set-based) and architectures (e.g., Faster-RCNN or DETR) which enable outstanding performance on challenging benchmark datasets. Despite this, the trained object detectors typically do not reliably assess uncertainty regarding their own knowledge, and the quality of their probabilistic predictions is usually poor. As these are often used to make subsequent decisions, such inaccurate probabilistic predictions must be avoided. In this work, we investigate the uncertainty calibration properties of different pretrained object detection architectures in a multi-class setting. We propose a framework to ensure a fair, unbiased, and repeatable evaluation and conduct detailed analyses assessing the calibration under distributional changes (e.g., distributional shift and application to out-of-distribution data). Furthermore, by investigating the influence of different detector paradigms, post-processing steps, and suitable choices of metrics, we deliver novel insights into why poor detector calibration emerges. Based on these insights, we are able to improve the calibration of a detector by simply finetuning its last layer.
Accurate grasping is the key to several robotic tasks including assembly and household robotics. Executing a successful grasp in a cluttered environment requires multiple levels of scene understanding: First, the robot needs to analyze the geometric properties of individual objects to find feasible grasps. These grasps need to be compliant with the local object geometry. Second, for each proposed grasp, the robot needs to reason about the interactions with other objects in the scene. Finally, the robot must compute a collision-free grasp trajectory while taking into account the geometry of the target object. Most grasp detection algorithms directly predict grasp poses in a monolithic fashion, which does not capture the composability of the environment. In this paper, we introduce an end-to-end architecture for object-centric grasping. The method uses pointcloud data from a single arbitrary viewing direction as an input and generates an instance-centric representation for each partially observed object in the scene. This representation is further used for object reconstruction and grasp detection in cluttered table-top scenes. We show the effectiveness of the proposed method by extensively evaluating it against state-of-the-art methods on synthetic datasets, indicating superior performance for grasping and reconstruction. Additionally, we demonstrate real-world applicability by decluttering scenes with varying numbers of objects.
Recent advances in single-frame object detection and segmentation techniques have motivated a wide range of works to extend these methods to process video streams. In this paper, we explore the idea of hard attention aimed for latency-sensitive applications. Instead of reasoning about every frame separately, our method selects and only processes a small sub-window of the frame. Our technique then makes predictions for the full frame based on the sub-windows from previous frames and the update from the current sub-window. The latency reduction by this hard attention mechanism comes at the cost of degraded accuracy. We made two contributions to address this. First, we propose a specialized memory cell that recovers lost context when processing sub-windows. Secondly, we adopt a Q-learning-based policy training strategy that enables our approach to intelligently select the sub-windows such that the staleness in the memory hurts the performance the least. Our experiments suggest that our approach reduces the latency by approximately four times without significantly sacrificing the accuracy on the ImageNet VID video object detection dataset and the DAVIS video object segmentation dataset. We further demonstrate that we can reinvest the saved computation into other parts of the network, and thus resulting in an accuracy increase at a comparable computational cost as the original system and beating other recently proposed state-of-the-art methods in the low latency range.
Semi-supervised 3D object detection is a promising yet under-explored direction to reduce data annotation costs, especially for cluttered indoor scenes. A few prior works, such as SESS and 3DIoUMatch, attempt to solve this task by utilizing a teacher model to generate pseudo-labels for unlabeled samples. However, the availability of unlabeled samples in the 3D domain is relatively limited compared to its 2D counterpart due to the greater effort required to collect 3D data. Moreover, the loose consistency regularization in SESS and restricted pseudo-label selection strategy in 3DIoUMatch lead to either low-quality supervision or a limited amount of pseudo labels. To address these issues, we present a novel Dual-Perspective Knowledge Enrichment approach named DPKE for semi-supervised 3D object detection. Our DPKE enriches the knowledge of limited training data, particularly unlabeled data, from two perspectives: data-perspective and feature-perspective. Specifically, from the data-perspective, we propose a class-probabilistic data augmentation method that augments the input data with additional instances based on the varying distribution of class probabilities. Our DPKE achieves feature-perspective knowledge enrichment by designing a geometry-aware feature matching method that regularizes feature-level similarity between object proposals from the student and teacher models. Extensive experiments on the two benchmark datasets demonstrate that our DPKE achieves superior performance over existing state-of-the-art approaches under various label ratio conditions. The source code will be made available to the public.
With the rapid advancement of Unmanned Aerial Vehicle (UAV) and computer vision technologies, object detection from UAV perspectives has emerged as a prominent research area. However, challenges for detection brought by the extremely small proportion of target pixels, significant scale variations of objects, and complex background information in UAV images have greatly limited the practical applications of UAV. To address these challenges, we propose a novel object detection network Multi-scale Context Aggregation and Scale-adaptive Fusion YOLO (MASF-YOLO), which is developed based on YOLOv11. Firstly, to tackle the difficulty of detecting small objects in UAV images, we design a Multi-scale Feature Aggregation Module (MFAM), which significantly improves the detection accuracy of small objects through parallel multi-scale convolutions and feature fusion. Secondly, to mitigate the interference of background noise, we propose an Improved Efficient Multi-scale Attention Module (IEMA), which enhances the focus on target regions through feature grouping, parallel sub-networks, and cross-spatial learning. Thirdly, we introduce a Dimension-Aware Selective Integration Module (DASI), which further enhances multi-scale feature fusion capabilities by adaptively weighting and fusing low-dimensional features and high-dimensional features. Finally, we conducted extensive performance evaluations of our proposed method on the VisDrone2019 dataset. Compared to YOLOv11-s, MASFYOLO-s achieves improvements of 4.6% in [email omitted] and 3.5% in [email omitted]:0.95 on the VisDrone2019 validation set. Remarkably, MASF-YOLO-s outperforms YOLOv11-m while requiring only approximately 60% of its parameters and 65% of its computational cost. Furthermore, comparative experiments with state-of-the-art detectors confirm that MASF-YOLO-s maintains a clear competitive advantage in both detection accuracy and model efficiency.
Event-based vision sensors encode local pixel-wise brightness changes in streams of events rather than image frames and yield sparse, energy-efficient encodings of scenes, in addition to low latency, high dynamic range, and lack of motion blur. Recent progress in object recognition from event-based sensors has come from conversions of deep neural networks, trained with backpropagation. However, using these approaches for event streams requires a transformation to a synchronous paradigm, which not only loses computational efficiency, but also misses opportunities to extract spatio-temporal features. In this article we propose a hybrid architecture for end-to-end training of deep neural networks for event-based pattern recognition and object detection, combining a spiking neural network (SNN) backbone for efficient event-based feature extraction, and a subsequent analog neural network (ANN) head to solve synchronous classification and detection tasks. This is achieved by combining standard backpropagation with surrogate gradient training to propagate gradients through the SNN. Hybrid SNN-ANNs can be trained without conversion, and result in highly accurate networks that are substantially more computationally efficient than their ANN counterparts. We demonstrate results on event-based classification and object detection datasets, in which only the architecture of the ANN heads need to be adapted to the tasks, and no conversion of the event-based input is necessary. Since ANNs and SNNs require different hardware paradigms to maximize their efficiency, we envision that SNN backbone and ANN head can be executed on different processing units, and thus analyze the necessary bandwidth to communicate between the two parts. Hybrid networks are promising architectures to further advance machine learning approaches for event-based vision, without having to compromise on efficiency.
The safety of autonomous cars has come under scrutiny in recent years, especially after 16 documented incidents involving Teslas (with autopilot engaged) crashing into parked emergency vehicles (police cars, ambulances, and firetrucks). While previous studies have revealed that strong light sources often introduce flare artifacts in the captured image, which degrade the image quality, the impact of flare on object detection performance remains unclear. In this research, we unveil PaniCar, a digital phenomenon that causes an object detector's confidence score to fluctuate below detection thresholds when exposed to activated emergency vehicle lighting. This vulnerability poses a significant safety risk, and can cause autonomous vehicles to fail to detect objects near emergency vehicles. In addition, this vulnerability could be exploited by adversaries to compromise the security of advanced driving assistance systems (ADASs). We assess seven commercial ADASs (Tesla Model 3, "manufacturer C", HP, Pelsee, AZDOME, Imagebon, Rexing), four object detectors (YOLO, SSD, RetinaNet, Faster R-CNN), and 14 patterns of emergency vehicle lighting to understand the influence of various technical and environmental factors. We also evaluate four SOTA flare removal methods and show that their performance and latency are insufficient for real-time driving constraints. To mitigate this risk, we propose Caracetamol, a robust framework designed to enhance the resilience of object detectors against the effects of activated emergency vehicle lighting. Our evaluation shows that on YOLOv3 and Faster RCNN, Caracetamol improves the models' average confidence of car detection by 0.20, the lower confidence bound by 0.33, and reduces the fluctuation range by 0.33. In addition, Caracetamol is capable of processing frames at a rate of between 30-50 FPS, enabling real-time ADAS car detection.
비전-언어 강화학습은 최근 위장 객체 검출(COD)에서 타깃 존재 국소화에서 강한 성능을 보여 주었다. 그러나 국소화는 결정의 한 면에 불과하다. 에이전트가 위장 타깃이 없는 평범한 이미지를 마주할 때, 여전히 위장 객체가 존재한다고 주장할까? 표준 COD 학습 및 평가 데이터는 양성(positive)만 포함하므로, 이 설정에서 최적화된 에이전트는 과탐지 바이어스를 갖게 될 수 있으며, 이는 객체 환각의 과제 특이적 형태로서 표준 COD 평가에서는 측정되지 않는다. 이 타깃 부재 행동을 정량화하기 위해, 우리는 각 hold-out COD 평가 이미지에서 위장 타깃을 제거하되 그럴듯한 배경은 유지하는 쌍(pair) 벤치마크인 Counterfactual COD(CF-COD)를 구축한다. CF-COD는 모델이 원본 이미지에서 타깃을 탐지하고 타깃 부재 반사실(counterfactual) 이미지에서는 기권(abstain)하는지 평가하며, 이를 Pair Accuracy(PA)로 요약한다. 또한 우리는 기권을 포함한 COD를 위한 쌍 반사실 프레임워크 CFCamo를 제안한다. 학습에서는 CFCamo가 Counterfactual Sequence Policy Optimization(CSPO)으로 Qwen3-VL-4B-Instruct 에이전트를 최적화하며, CSPO는 원본-반사실 쌍 롤아웃을 샘플링하고 Counterfactual Paired Reward(CPR)를 사용해 원본 이미지 탐지와 반사실 기권을 결합한다. CAMO-test에서 CFCamo는 기존 RL 기반 COD 기준선 대비 S_alpha를 +3.7%p 개선했고, CF-COD 전체에서 80.0-90.8% PA를 달성했다. 어블레이션은 반사실 결합을 제거하면 타깃 존재 COD 점수가 높음에도 PA가 1.4-5.2%로 떨어짐을 보여 주며, 타깃 존재 평가만으로는 탐지 또는 기권 행동을 특성화할 수 없음을 시사한다. 전반적으로, 이 결과는 CFCamo가 단순히 타깃 존재 국소화를 강화하는 것이 아니라, 타깃 존재 탐지와 타깃 부재 기권을 결합함으로써 COD 에이전트를 개선함을 나타낸다. 코드와 데이터는 https://github.com/suhang2000/CFCamo 에서 이용할 수 있다.
벤치마크 모음은 정제된 데이터셋뿐 아니라 재현 가능한 비교를 위한 표준화된 평가 프로토콜을 제공하므로 컴퓨터 비전 연구의 발전에 매우 중요하다. 철도 분야에는 이러한 자원이 부족하여 자동 열차 운행의 발전이 저해되고 있다. 이러한 격차를 해소하기 위해, 본 논문에서는 철도를 위해 특별히 설계된 최초의 인식 벤치마크 모음인 RAIL-BENCH를 제시한다. RAIL-BENCH는 철도 선로 검출, 객체 검출, 식생 분할, 다중 객체 추적, 단안 시각 주행 거리 측정의 다섯 가지 과제로 구성되며, 각 과제는 철도 고유의 특성에 맞추어져 있고 다양한 실제 시나리오의 정제된 데이터셋, 평가 지표, 공개 순위표를 포함한다. 본 논문에서는 이 중 처음 세 가지 과제를 시연한다. 또한 선로 검출을 위한 새로운 선분 기반 평균 정밀도 지표인 LineAP를 소개한다. 이 지표는 기하학적 정확도를 인스턴스 수준의 그룹화와 분리하고, 고정된 실제 거리를 근사하는 선로 폭 기반 거리 임계값을 사용하여 기존 선 검출 지표의 주요 한계를 해결한다. 본 벤치마크 모음은 https://www.mrt.kit.edu/railbench/ 에서 공개되어 있다.
The accelerating development of autonomous driving technology has placed greater demands on obtaining large amounts of high-quality data. Representative, labeled, real world data serves as the fuel for training deep learning networks, critical for improving self-driving perception algorithms. In this paper, we introduce PandaSet, the first dataset produced by a complete, high-precision autonomous vehicle sensor kit with a no-cost commercial license. The dataset was collected using one 360{\deg} mechanical spinning LiDAR, one forward-facing, long-range LiDAR, and 6 cameras. The dataset contains more than 100 scenes, each of which is 8 seconds long, and provides 28 types of labels for object classification and 37 types of labels for semantic segmentation. We provide baselines for LiDAR-only 3D object detection, LiDAR-camera fusion 3D object detection and LiDAR point cloud segmentation. For more details about PandaSet and the development kit, see https://scale.com/open-datasets/pandaset.