This paper presents a novel framework for unsupervised anomaly detection on masked objects called ODDObjects, which stands for Out-of-Distribution Detection on Objects. ODDObjects is designed to detect anomalies of various categories using unsupervised autoencoders trained on COCO-style datasets. The method utilizes autoencoder-based image reconstruction, where high reconstruction error indicates the possibility of an anomaly. The framework extends previous work on anomaly detection with autoencoders, comparing state-of-the-art models trained on object recognition datasets. Various model architectures were compared, and experimental results show that memory-augmented deep convolutional autoencoders perform the best at detecting out-of-distribution objects.
Existing salient object detection (SOD) methods mainly rely on U-shaped convolution neural networks (CNNs) with skip connections to combine the global contexts and local spatial details that are crucial for locating salient objects and refining object details, respectively. Despite great successes, the ability of CNNs in learning global contexts is limited. Recently, the vision transformer has achieved revolutionary progress in computer vision owing to its powerful modeling of global dependencies. However, directly applying the transformer to SOD is suboptimal because the transformer lacks the ability to learn local spatial representations. To this end, this paper explores the combination of transformers and CNNs to learn both global and local representations for SOD. We propose a transformer-based Asymmetric Bilateral U-Net (ABiU-Net). The asymmetric bilateral encoder has a transformer path and a lightweight CNN path, where the two paths communicate at each encoder stage to learn complementary global contexts and local spatial details, respectively. The asymmetric bilateral decoder also consists of two paths to process features from the transformer and CNN encoder paths, with communication at each decoder stage for decoding coarse salient object locations and fine-grained object details, respectively. Such communication between the two encoder/decoder paths enables AbiU-Net to learn complementary global and local representations, taking advantage of the natural merits of transformers and CNNs, respectively. Hence, ABiU-Net provides a new perspective for transformer-based SOD. Extensive experiments demonstrate that ABiU-Net performs favorably against previous state-of-the-art SOD methods. The code is available at https://github.com/yuqiuyuqiu/ABiU-Net.
Human activity recognition is typically addressed by detecting key concepts like global and local motion, features related to object classes present in the scene, as well as features related to the global context. The next open challenges in activity recognition require a level of understanding that pushes beyond this and call for models with capabilities for fine distinction and detailed comprehension of interactions between actors and objects in a scene. We propose a model capable of learning to reason about semantically meaningful spatiotemporal interactions in videos. The key to our approach is a choice of performing this reasoning at the object level through the integration of state of the art object detection networks. This allows the model to learn detailed spatial interactions that exist at a semantic, object-interaction relevant level. We evaluate our method on three standard datasets (Twenty-BN Something-Something, VLOG and EPIC Kitchens) and achieve state of the art results on all of them. Finally, we show visualizations of the interactions learned by the model, which illustrate object classes and their interactions corresponding to different activity classes.
Single object tracking (SOT) heavily relies on the representation of the target object as a bounding box. However, due to the potential deformation and rotation experienced by the tracked targets, the genuine bounding box fails to capture the appearance information explicitly and introduces cluttered background. This paper proposes RTrack, a novel object representation baseline tracker that utilizes a set of sample points to get a pseudo bounding box. RTrack automatically arranges these points to define the spatial extents and highlight local areas. Building upon the baseline, we conducted an in-depth exploration of the training potential and introduced a one-to-many leading assignment strategy. It is worth noting that our approach achieves competitive performance to the state-of-the-art trackers on the GOT-10k dataset while reducing training time to just 10% of the previous state-of-the-art (SOTA) trackers' training costs. The substantial reduction in training costs brings single-object tracking (SOT) closer to the object detection (OD) task. Extensive experiments demonstrate that our proposed RTrack achieves SOTA results with faster convergence.
Trajectory forecasting is critical for autonomous platforms to make safe planning and actions. Currently, most trajectory forecasting methods assume that object trajectories have been extracted and directly develop trajectory predictors based on the ground truth trajectories. However, this assumption does not hold in practical situations. Trajectories obtained from object detection and tracking are inevitably noisy, which could cause serious forecasting errors to predictors built on ground truth trajectories. In this paper, we propose a trajectory predictor directly based on detection results without relying on explicitly formed trajectories. Different from the traditional methods which encode the motion cue of an agent based on its clearly defined trajectory, we extract the motion information only based on the affinity cues among detection results, in which an affinity-aware state update mechanism is designed to take the uncertainty of association into account. In addition, considering that there could be multiple plausible matching candidates, we aggregate the states of them. This design relaxes the undesirable effect of noisy trajectory obtained from data association. Extensive ablation experiments validate the effectiveness of our method and its generalization ability on different detectors. Cross-comparison to other forecasting schemes further proves the superiority of our method. Code will be released upon acceptance.
수면 반사는 컴퓨터 비전 시스템에 심각한 도전 과제를 제기한다. 표준 심층 학습 모델이 객체와 거울상을 혼동하는 경우가 빈번하여, 객체 검출 및 시맨틱 분할과 같은 태스크에서 허위 양성과 허위 음성을 유발하기 때문이다. 따라서 자연 수면 장면에서 반사축을 검출하는 것은 신뢰할 수 있는 객체 검출과 장면 이해에 핵심적이다. 이 문제를 완화하기 위해, 우리는 물의 내재적이고 불완전한 반사 대칭성을 활용하여 대칭 인식 수면 반사 검출 네트워크인 SAWRD-Net을 제안한다. 이 네트워크는 이면체군 등변 합성곱(dihedral group-equivariant convolution)과 행렬 분해 디코더(matrix-decomposition decoder)를 엔드-투-엔드 프레임워크로 결합한다. 먼저, 이면체군 합성곱 레이어가 회전 대칭과 거울 대칭을 모두 명시적으로 인코딩하는 기하학적으로 일관된 특징 맵을 추출한다. 이후 다중 스케일 반사 등변 블록(Multi-scale Reflection Equivariant block)이 다양한 스케일에 걸쳐 특징을 집계하고 대칭 어텐션 메커니즘을 활용하여 반사 관련 영역을 강조한다. 제안된 행렬 분해 디코더는 고차원 특징을 컴팩트한 저랭크 매개변수 공간과 신뢰도 공간으로 인수분해하며, 네트워크는 이를 통해 반사축 위의 키포인트를 직접 회귀한다. 이후 강건한 주성분 분석(robust principal component analysis)이 최종 축을 피팅한다. 현존하는 가장 큰 수면 반사 장면 데이터셋에서 평가한 결과, SAWRD-Net은 인간 주석 대비 0.890의 진양성률(true-positive rate)을 달성하여 기존의 모든 수면 반사 검출기를 능가한다.
Salient object detection plays an important role in many downstream tasks. However, complex real-world scenes with varying scales and numbers of salient objects still pose a challenge. In this paper, we directly address the problem of detecting multiple salient objects across complex scenes. We propose a network architecture incorporating non-local feature information in both the spatial and channel spaces, capturing the long-range dependencies between separate objects. Traditional bottom-up and non-local features are combined with edge features within a feature fusion gate that progressively refines the salient object prediction in the decoder. We show that our approach accurately locates multiple salient regions even in complex scenarios. To demonstrate the efficacy of our approach to the multiple salient objects problem, we curate a new dataset containing only multiple salient objects. Our experiments demonstrate the proposed method presents state-of-the-art results on five widely used datasets without any pre-processing and post-processing. We obtain a further performance improvement against competing techniques on our multi-objects dataset. The dataset and source code are avaliable at: https://github.com/EricDengbowen/DSLRDNet.
Recent 3D object detectors typically utilize multi-sensor data and unify multi-modal features in the shared bird's-eye view (BEV) representation space. However, our empirical findings indicate that previous methods have limitations in generating fusion BEV features free from cross-modal conflicts. These conflicts encompass extrinsic conflicts caused by BEV feature construction and inherent conflicts stemming from heterogeneous sensor signals. Therefore, we propose a novel Eliminating Conflicts Fusion (ECFusion) method to explicitly eliminate the extrinsic/inherent conflicts in BEV space and produce improved multi-modal BEV features. Specifically, we devise a Semantic-guided Flow-based Alignment (SFA) module to resolve extrinsic conflicts via unifying spatial distribution in BEV space before fusion. Moreover, we design a Dissolved Query Recovering (DQR) mechanism to remedy inherent conflicts by preserving objectness clues that are lost in the fusion BEV feature. In general, our method maximizes the effective information utilization of each modality and leverages inter-modal complementarity. Our method achieves state-of-the-art performance in the highly competitive nuScenes 3D object detection dataset. The code is released at https://github.com/fjhzhixi/ECFusion.
Infrared object tracking plays a crucial role in Anti-Unmanned Aerial Vehicle (Anti-UAV) applications. Existing trackers often depend on cropped template regions and have limited motion modeling capabilities, which pose challenges when dealing with tiny targets. To address this, we propose a simple yet effective infrared tiny-object tracker that enhances tracking performance by integrating global detection and motion-aware learning with temporal priors. Our method is based on object detection and achieves significant improvements through two key innovations. First, we introduce frame dynamics, leveraging frame difference and optical flow to encode both prior target features and motion characteristics at the input level, enabling the model to better distinguish the target from background clutter. Second, we propose a trajectory constraint filtering strategy in the post-processing stage, utilizing spatio-temporal priors to suppress false positives and enhance tracking robustness. Extensive experiments show that our method consistently outperforms existing approaches across multiple metrics in challenging infrared UAV tracking scenarios. Notably, we achieve state-of-the-art performance in the 4th Anti-UAV Challenge, securing 1st place in Track 1 and 2nd place in Track 2.
In this work, we apply an attention-gated network to real-time automated scan plane detection for fetal ultrasound screening. Scan plane detection in fetal ultrasound is a challenging problem due the poor image quality resulting in low interpretability for both clinicians and automated algorithms. To solve this, we propose incorporating self-gated soft-attention mechanisms. A soft-attention mechanism generates a gating signal that is end-to-end trainable, which allows the network to contextualise local information useful for prediction. The proposed attention mechanism is generic and it can be easily incorporated into any existing classification architectures, while only requiring a few additional parameters. We show that, when the base network has a high capacity, the incorporated attention mechanism can provide efficient object localisation while improving the overall performance. When the base network has a low capacity, the method greatly outperforms the baseline approach and significantly reduces false positives. Lastly, the generated attention maps allow us to understand the model's reasoning process, which can also be used for weakly supervised object localisation.
Many recent works on 3D object detection have focused on designing neural network architectures that can consume point cloud data. While these approaches demonstrate encouraging performance, they are typically based on a single modality and are unable to leverage information from other modalities, such as a camera. Although a few approaches fuse data from different modalities, these methods either use a complicated pipeline to process the modalities sequentially, or perform late-fusion and are unable to learn interaction between different modalities at early stages. In this work, we present PointFusion and VoxelFusion: two simple yet effective early-fusion approaches to combine the RGB and point cloud modalities, by leveraging the recently introduced VoxelNet architecture. Evaluation on the KITTI dataset demonstrates significant improvements in performance over approaches which only use point cloud data. Furthermore, the proposed method provides results competitive with the state-of-the-art multimodal algorithms, achieving top-2 ranking in five of the six bird's eye view and 3D detection categories on the KITTI benchmark, by using a simple single stage network.
This paper presents an improved scheme for the generation and adaption of synthetic images for the training of deep Convolutional Neural Networks(CNNs) to perform the object detection task in smart vending machines. While generating synthetic data has proved to be effective for complementing the training data in supervised learning methods, challenges still exist for generating virtual images which are similar to those of the complex real scenes and minimizing redundant training data. To solve these problems, we consider the simulation of cluttered objects placed in a virtual scene and the wide-angle camera with distortions used to capture the whole scene in the data generation process, and post-processed the generated images with a elaborately-designed generative network to make them more similar to the real images. Various experiments have been conducted to prove the efficiency of using the generated virtual images to enhance the detection precision on existing datasets with limited real training data and the generalization ability of applying the trained network to datasets collected in new environment.
We introduce the Lecture Video Visual Objects (LVVO) dataset, a new benchmark for visual object detection in educational video content. The dataset consists of 4,000 frames extracted from 245 lecture videos spanning biology, computer science, and geosciences. A subset of 1,000 frames, referred to as LVVO_1k, has been manually annotated with bounding boxes for four visual categories: Table, Chart-Graph, Photographic-image, and Visual-illustration. Each frame was labeled independently by two annotators, resulting in an inter-annotator F1 score of 83.41%, indicating strong agreement. To ensure high-quality consensus annotations, a third expert reviewed and resolved all cases of disagreement through a conflict resolution process. To expand the dataset, a semi-supervised approach was employed to automatically annotate the remaining 3,000 frames, forming LVVO_3k. The complete dataset offers a valuable resource for developing and evaluating both supervised and semi-supervised methods for visual content detection in educational videos. The LVVO dataset is publicly available to support further research in this domain.
건설 현장에서의 로봇 활용은 복잡한 문제를 해결하는 능력, 특히 철근이 포함된 시나리오에서 주목받는 분야로 부상하고 있습니다. 대부분의 기존 제품과 연구는 주로 모델 학습이 필요한 대량의 데이터 수집에 집중되어 있습니다. 이러한 격차를 해소하기 위해, 본 논문에서는 실제 환경 테스트에서 RGB에서 포인트 클라우드로의 생성과 오픈 어휘 철근 검출을 활용하는 학습이 필요 없는 3D 철근 결속 프레임워크인 OpenTie를 제안합니다. 우리는 양안 카메라가 장착된 로봇 팔을 통해 OpenTie를 구현하였으며, 이미지-포인트 클라우드 생성 프레임워크에 대해 제안한 후처리 절차로 필터링된 이미지에 프롬프트 기반 객체 검출 방법을 적용하여 높은 정확도를 보장합니다. 본 파이프라인은 학습 과정이 필요 없으며, 실제 환경 순차적 철근 결속 테스트를 통한 검증 결과 학습 기반 객체 검출 방식인 YOLO 기반 방법보다 우수한 성능을 보입니다. 이 시스템은 수평 및 수직 철근 결속 작업에 유연하게 적용될 수 있으며, 상업화 가능성과 함께 실제 건설 현장에 적용될 잠재력을 가지고 있습니다.
Object proposals have quickly become the de-facto pre-processing step in a number of vision pipelines (for object detection, object discovery, and other tasks). Their performance is usually evaluated on partially annotated datasets. In this paper, we argue that the choice of using a partially annotated dataset for evaluation of object proposals is problematic -- as we demonstrate via a thought experiment, the evaluation protocol is 'gameable', in the sense that progress under this protocol does not necessarily correspond to a "better" category independent object proposal algorithm. To alleviate this problem, we: (1) Introduce a nearly-fully annotated version of PASCAL VOC dataset, which serves as a test-bed to check if object proposal techniques are overfitting to a particular list of categories. (2) Perform an exhaustive evaluation of object proposal methods on our introduced nearly-fully annotated PASCAL dataset and perform cross-dataset generalization experiments; and (3) Introduce a diagnostic experiment to detect the bias capacity in an object proposal algorithm. This tool circumvents the need to collect a densely annotated dataset, which can be expensive and cumbersome to collect. Finally, we plan to release an easy-to-use toolbox which combines various publicly available implementations of object proposal algorithms which standardizes the proposal generation and evaluation so that new methods can be added and evaluated on different datasets. We hope that the results presented in the paper will motivate the community to test the category independence of various object proposal methods by carefully choosing the evaluation protocol.
Deep Siamese trackers have recently gained much attention in recent years since they can track visual objects at high speeds. Additionally, adaptive tracking methods, where target samples collected by the tracker are employed for online learning, have achieved state-of-the-art accuracy. However, single object tracking (SOT) remains a challenging task in real-world application due to changes and deformations in a target object's appearance. Learning on all the collected samples may lead to catastrophic forgetting, and thereby corrupt the tracking model. In this paper, SOT is formulated as an online incremental learning problem. A new method is proposed for dynamic sample selection and memory replay, preventing template corruption. In particular, we propose a change detection mechanism to detect gradual changes in object appearance and select the corresponding samples for online adaption. In addition, an entropy-based sample selection strategy is introduced to maintain a diversified auxiliary buffer for memory replay. Our proposed method can be integrated into any object tracking algorithm that leverages online learning for model adaptation. Extensive experiments conducted on the OTB-100, LaSOT, UAV123, and TrackingNet datasets highlight the cost-effectiveness of our method, along with the contribution of its key components. Results indicate that integrating our proposed method into state-of-art adaptive Siamese trackers can increase the potential benefits of a template update strategy, and significantly improve performance.
We introduce TIDE, a framework and associated toolbox for analyzing the sources of error in object detection and instance segmentation algorithms. Importantly, our framework is applicable across datasets and can be applied directly to output prediction files without required knowledge of the underlying prediction system. Thus, our framework can be used as a drop-in replacement for the standard mAP computation while providing a comprehensive analysis of each model's strengths and weaknesses. We segment errors into six types and, crucially, are the first to introduce a technique for measuring the contribution of each error in a way that isolates its effect on overall performance. We show that such a representation is critical for drawing accurate, comprehensive conclusions through in-depth analysis across 4 datasets and 7 recognition models. Available at https://dbolya.github.io/tide/
Open-vocabulary object detection (OVOD) has recently gained significant attention as a crucial step toward achieving human-like visual intelligence. Existing OVOD methods extend target vocabulary from pre-defined categories to open-world by transferring knowledge of arbitrary concepts from vision-language pre-training models to the detectors. While previous methods have shown remarkable successes, they suffer from indirect supervision or limited transferable concepts. In this paper, we propose a simple yet effective method to directly learn region-text alignment for arbitrary concepts. Specifically, the proposed method aims to learn arbitrary image-to-text mapping for pseudo-labeling of arbitrary concepts, named Pseudo-Labeling for Arbitrary Concepts (PLAC). The proposed method shows competitive performance on the standard OVOD benchmark for noun concepts and a large improvement on referring expression comprehension benchmark for arbitrary concepts.
On-orbit servicing (OOS), inspection of spacecraft, and active debris removal (ADR). Such missions require precise rendezvous and proximity operations in the vicinity of non-cooperative, possibly unknown, resident space objects. Safety concerns with manned missions and lag times with ground-based control necessitate complete autonomy. In this article, we present an approach for mapping geometries and high-confidence detection of components of unknown, non-cooperative satellites on orbit. We implement accelerated 3D Gaussian splatting to learn a 3D representation of the satellite, render virtual views of the target, and ensemble the YOLOv5 object detector over the virtual views, resulting in reliable, accurate, and precise satellite component detections. The full pipeline capable of running on-board and stand to enable downstream machine intelligence tasks necessary for autonomous guidance, navigation, and control tasks.
Incremental object detection is fundamentally challenged by catastrophic forgetting. A major factor contributing to this issue is background shift, where background categories in sequential tasks may overlap with either previously learned or future unseen classes. To address this, we propose a novel method called Class-Agnostic Shared Attribute Base (CASA) that encourages the model to learn category-agnostic attributes shared across incremental classes. Our approach leverages an LLM to generate candidate textual attributes, selects the most relevant ones based on the current training data, and records their importance in an assignment matrix. For subsequent tasks, the retained attributes are frozen, and new attributes are selected from the remaining candidates, ensuring both knowledge retention and adaptability. Extensive experiments on the COCO dataset demonstrate the state-of-the-art performance of our method.