Monocular 3D object detection is an essential perception task for autonomous driving. However, the high reliance on large-scale labeled data make it costly and time-consuming during model optimization. To reduce such over-reliance on human annotations, we propose Mix-Teaching, an effective semi-supervised learning framework applicable to employ both labeled and unlabeled images in training stage. Mix-Teaching first generates pseudo-labels for unlabeled images by self-training. The student model is then trained on the mixed images possessing much more intensive and precise labeling by merging instance-level image patches into empty backgrounds or labeled images. This is the first to break the image-level limitation and put high-quality pseudo labels from multi frames into one image for semi-supervised training. Besides, as a result of the misalignment between confidence score and localization quality, it's hard to discriminate high-quality pseudo-labels from noisy predictions using only confidence-based criterion. To that end, we further introduce an uncertainty-based filter to help select reliable pseudo boxes for the above mixing operation. To the best of our knowledge, this is the first unified SSL framework for monocular 3D object detection. Mix-Teaching consistently improves MonoFlex and GUPNet by significant margins under various labeling ratios on KITTI dataset. For example, our method achieves around +6.34% [email omitted] improvement against the GUPNet baseline on validation set when using only 10% labeled data. Besides, by leveraging full training set and the additional 48K raw images of KITTI, it can further improve the MonoFlex by +4.65% improvement on [email omitted] for car detection, reaching 18.54% [email omitted], which ranks the 1st place among all monocular based methods on KITTI test leaderboard. The code and pretrained models will be released at https://github.com/yanglei18/Mix-Teaching.
Existing salient instance detection (SID) methods typically learn from pixel-level annotated datasets. In this paper, we present the first weakly-supervised approach to the SID problem. Although weak supervision has been considered in general saliency detection, it is mainly based on using class labels for object localization. However, it is non-trivial to use only class labels to learn instance-aware saliency information, as salient instances with high semantic affinities may not be easily separated by the labels. As the subitizing information provides an instant judgement on the number of salient items, it is naturally related to detecting salient instances and may help separate instances of the same class while grouping different parts of the same instance. Inspired by this observation, we propose to use class and subitizing labels as weak supervision for the SID problem. We propose a novel weakly-supervised network with three branches: a Saliency Detection Branch leveraging class consistency information to locate candidate objects; a Boundary Detection Branch exploiting class discrepancy information to delineate object boundaries; and a Centroid Detection Branch using subitizing information to detect salient instance centroids. This complementary information is then fused to produce a salient instance map. To facilitate the learning process, we further propose a progressive training scheme to reduce label noise and the corresponding noise learned by the model, via reciprocating the model with progressive salient instance prediction and model refreshing. Our extensive evaluations show that the proposed method plays favorably against carefully designed baseline methods adapted from related tasks.
Lack of shape guidance and label jitter caused by information deficiency of weak label are the main problems in 3D weakly-supervised object detection. Current weakly-supervised models often use heuristics or assumptions methods to infer information from weak labels without taking advantage of the inherent clues of weakly-supervised and fully-supervised methods, thus it is difficult to explore a method that combines data utilization efficiency and model accuracy. In an attempt to address these issues, we propose a novel plug-and-in point cloud feature representation network called Multi-scale Mixed Attention (MMA). MMA utilizes adjacency attention within neighborhoods and disparity attention at different density scales to build a feature representation network. The smart feature representation obtained from MMA has shape tendency and object existence area inference, which can constrain the region of the detection boxes, thereby alleviating the problems caused by the information default of weak labels. Extensive experiments show that in indoor weak label scenarios, the fully-supervised network can perform close to that of the weakly-supervised network merely through the improvement of point feature by MMA. At the same time, MMA can turn waste into treasure, reversing the label jitter problem that originally interfered with weakly-supervised detection into the source of data enhancement, strengthening the performance of existing weak supervision detection methods. Our code is available at https://github.com/hzx-9894/MMA.
We present Region Similarity Representation Learning (ReSim), a new approach to self-supervised representation learning for localization-based tasks such as object detection and segmentation. While existing work has largely focused on solely learning global representations for an entire image, ReSim learns both regional representations for localization as well as semantic image-level representations. ReSim operates by sliding a fixed-sized window across the overlapping area between two views (e.g., image crops), aligning these areas with their corresponding convolutional feature map regions, and then maximizing the feature similarity across views. As a result, ReSim learns spatially and semantically consistent feature representation throughout the convolutional feature maps of a neural network. A shift or scale of an image region, e.g., a shift or scale of an object, has a corresponding change in the feature maps; this allows downstream tasks to leverage these representations for localization. Through object detection, instance segmentation, and dense pose estimation experiments, we illustrate how ReSim learns representations which significantly improve the localization and classification performance compared to a competitive MoCo-v2 baseline: $+2.7$ AP$^{\text{bb}}_{75}$ VOC, $+1.1$ AP$^{\text{bb}}_{75}$ COCO, and $+1.9$ AP$^{\text{mk}}$ Cityscapes. Code and pre-trained models are released at: \url{https://github.com/Tete-Xiao/ReSim}
Tracking-by-detection is a very popular framework for single object tracking which attempts to search the target object within a local search window for each frame. Although such local search mechanism works well on simple videos, however, it makes the trackers sensitive to extremely challenging scenarios, such as heavy occlusion and fast motion. In this paper, we propose a novel and general target-aware attention mechanism (termed TANet) and integrate it with tracking-by-detection framework to conduct joint local and global search for robust tracking. Specifically, we extract the features of target object patch and continuous video frames, then we concatenate and feed them into a decoder network to generate target-aware global attention maps. More importantly, we resort to adversarial training for better attention prediction. The appearance and motion discriminator networks are designed to ensure its consistency in spatial and temporal views. In the tracking procedure, we integrate the target-aware attention with multiple trackers by exploring candidate search regions for robust tracking. Extensive experiments on both short-term and long-term tracking benchmark datasets all validated the effectiveness of our algorithm. The project page of this paper can be found at \url{https://sites.google.com/view/globalattentiontracking/home/extend}.
Objects in aerial images have greater variations in scale and orientation than in typical images, so detection is more difficult. Convolutional neural networks use a variety of frequency- and orientation-specific kernels to identify objects subject to different transformations; these require many parameters. Sampling equivariant networks can adjust sampling from input feature maps according to the transformation of the object, allowing a kernel to extract features of an object under different transformations. Doing so requires fewer parameters, and makes the network more suitable for representing deformable objects, like those in aerial images. However, methods like deformable convolutional networks can only provide sampling equivariance under certain circumstances, because of the locations used for sampling. We propose sampling equivariant self-attention networks which consider self-attention restricted to a local image patch as convolution sampling with masks instead of locations, and design a transformation embedding module to further improve the equivariant sampling ability. We also use a novel randomized normalization module to tackle overfitting due to limited aerial image data. We show that our model (i) provides significantly better sampling equivariance than existing methods, without additional supervision, (ii) provides improved classification on ImageNet, and (iii) achieves state-of-the-art results on the DOTA dataset, without increased computation.
Modern computer vision applications rely on learning-based perception modules parameterized with neural networks for tasks like object detection. These modules frequently have low expected error overall but high error on atypical groups of data due to biases inherent in the training process. In building autonomous vehicles (AV), this problem is an especially important challenge because their perception modules are crucial to the overall system performance. After identifying failures in AV, a human team will comb through the associated data to group perception failures that share common causes. More data from these groups is then collected and annotated before retraining the model to fix the issue. In other words, error groups are found and addressed in hindsight. Our main contribution is a pseudo-automatic method to discover such groups in foresight by performing causal interventions on simulated scenes. To keep our interventions on the data manifold, we utilize masked language models. We verify that the prioritized groups found via intervention are challenging for the object detector and show that retraining with data collected from these groups helps inordinately compared to adding more IID data. We also plan to release software to run interventions in simulated scenes, which we hope will benefit the causality community.
We study the challenging incremental few-shot object detection (iFSD) setting. Recently, hypernetwork-based approaches have been studied in the context of continuous and finetune-free iFSD with limited success. We take a closer look at important design choices of such methods, leading to several key improvements and resulting in a more accurate and flexible framework, which we call Sylph. In particular, we demonstrate the effectiveness of decoupling object classification from localization by leveraging a base detector that is pretrained for class-agnostic localization on a large-scale dataset. Contrary to what previous results have suggested, we show that with a carefully designed class-conditional hypernetwork, finetune-free iFSD can be highly effective, especially when a large number of base categories with abundant data are available for meta-training, almost approaching alternatives that undergo test-time-training. This result is even more significant considering its many practical advantages: (1) incrementally learning new classes in sequence without additional training, (2) detecting both novel and seen classes in a single pass, and (3) no forgetting of previously seen classes. We benchmark our model on both COCO and LVIS, reporting as high as 17% AP on the long-tail rare classes on LVIS, indicating the promise of hypernetwork-based iFSD.
Trichomoniasis is a common infectious disease with high incidence caused by the parasite Trichomonas vaginalis, increasing the risk of getting HIV in humans if left untreated. Automated detection of Trichomonas vaginalis from microscopic images can provide vital information for the diagnosis of trichomoniasis. However, accurate Trichomonas vaginalis segmentation (TVS) is a challenging task due to the high appearance similarity between the Trichomonas and other cells (e.g., leukocyte), the large appearance variation caused by their motility, and, most importantly, the lack of large-scale annotated data for deep model training. To address these challenges, we elaborately collected the first large-scale Microscopic Image dataset of Trichomonas Vaginalis, named TVMI3K, which consists of 3,158 images covering Trichomonas of various appearances in diverse backgrounds, with high-quality annotations including object-level mask labels, object boundaries, and challenging attributes. Besides, we propose a simple yet effective baseline, termed TVNet, to automatically segment Trichomonas from microscopic images, including high-resolution fusion and foreground-background attention modules. Extensive experiments demonstrate that our model achieves superior segmentation performance and outperforms various cutting-edge object detection models both quantitatively and qualitatively, making it a promising framework to promote future research in TVS tasks. The dataset and results will be publicly available at: https://github.com/CellRecog/cellRecog.
Object Detection (OD) has proven to be a significant computer vision method in extracting localized class information and has multiple applications in the industry. Although many of the state-of-the-art (SOTA) OD models perform well on medium and large sized objects, they seem to under perform on small objects. In most of the industrial use cases, it is difficult to collect and annotate data for small objects, as it is time-consuming and prone to human errors. Additionally, those datasets are likely to be unbalanced and often result in an inefficient model convergence. To tackle this challenge, this study presents a novel approach that injects additional data points to improve the performance of the OD models. Using synthetic data generation, the difficulties in data collection and annotations for small object data points can be minimized and to create a dataset with balanced distribution. This paper discusses the effects of a simple proportional class-balancing technique, to enable better anchor matching of the OD models. A comparison was carried out on the performances of the SOTA OD models: YOLOv5, YOLOv7 and SSD, for combinations of real and synthetic datasets within an industrial use case.
Skins wrapping around our bodies, leathers covering over the sofa, sheet metal coating the car - it suggests that objects are enclosed by a series of continuous surfaces, which provides us with informative geometry prior for objectness deduction. In this paper, we propose Gaussian-Det which leverages Gaussian Splatting as surface representation for multi-view based 3D object detection. Unlike existing monocular or NeRF-based methods which depict the objects via discrete positional data, Gaussian-Det models the objects in a continuous manner by formulating the input Gaussians as feature descriptors on a mass of partial surfaces. Furthermore, to address the numerous outliers inherently introduced by Gaussian splatting, we accordingly devise a Closure Inferring Module (CIM) for the comprehensive surface-based objectness deduction. CIM firstly estimates the probabilistic feature residuals for partial surfaces given the underdetermined nature of Gaussian Splatting, which are then coalesced into a holistic representation on the overall surface closure of the object proposal. In this way, the surface information Gaussian-Det exploits serves as the prior on the quality and reliability of objectness and the information basis of proposal refinement. Experiments on both synthetic and real-world datasets demonstrate that Gaussian-Det outperforms various existing approaches, in terms of both average precision and recall.
The field of indoor monocular 3D object detection is gaining significant attention, fueled by the increasing demand in VR/AR and robotic applications. However, its advancement is impeded by the limited availability and diversity of 3D training data, owing to the labor-intensive nature of 3D data collection and annotation processes. In this paper, we present V-MIND (Versatile Monocular INdoor Detector), which enhances the performance of indoor 3D detectors across a diverse set of object classes by harnessing publicly available large-scale 2D datasets. By leveraging well-established monocular depth estimation techniques and camera intrinsic predictors, we can generate 3D training data by converting large-scale 2D images into 3D point clouds and subsequently deriving pseudo 3D bounding boxes. To mitigate distance errors inherent in the converted point clouds, we introduce a novel 3D self-calibration loss for refining the pseudo 3D bounding boxes during training. Additionally, we propose a novel ambiguity loss to address the ambiguity that arises when introducing new classes from 2D datasets. Finally, through joint training with existing 3D datasets and pseudo 3D bounding boxes derived from 2D datasets, V-MIND achieves state-of-the-art object detection performance across a wide range of classes on the Omni3D indoor dataset.
This paper addresses the issue on how to more effectively coordinate the depth with RGB aiming at boosting the performance of RGB-D object detection. Particularly, we investigate two primary ideas under the CNN model: property derivation and property fusion. Firstly, we propose that the depth can be utilized not only as a type of extra information besides RGB but also to derive more visual properties for comprehensively describing the objects of interest. So a two-stage learning framework consisting of property derivation and fusion is constructed. Here the properties can be derived either from the provided color/depth or their pairs (e.g. the geometry contour adopted in this paper). Secondly, we explore the fusion method of different properties in feature learning, which is boiled down to, under the CNN model, from which layer the properties should be fused together. The analysis shows that different semantic properties should be learned separately and combined before passing into the final classifier. Actually, such a detection way is in accordance with the mechanism of the primary neural cortex (V1) in brain. We experimentally evaluate the proposed method on the challenging dataset, and have achieved state-of-the-art performance.
Robust environment perception is essential for decision-making on robots operating in complex domains. Principled treatment of uncertainty sources in a robot's observation model is necessary for accurate mapping and object detection. This is important not only for low-level observations (e.g., accelerometer data), but for high-level observations such as semantic object labels as well. This paper presents an approach for filtering sequences of object classification probabilities using online modeling of the noise characteristics of the classifier outputs. A hierarchical Bayesian approach is used to model per-class noise distributions, while simultaneously allowing sharing of high-level noise characteristics between classes. The proposed filtering scheme, called Hierarchical Bayesian Noise Inference (HBNI), is shown to outperform classification accuracy of existing methods. The paper also presents real-time filtered classification hardware experiments running fully onboard a moving quadrotor, where the proposed approach is demonstrated to work in a challenging domain where noise-agnostic filtering fails.
A robust visual tracking system requires an object appearance model that is able to handle occlusion, pose, and illumination variations in the video stream. This can be difficult to accomplish when the model is trained using only a single image. In this paper, we first propose a tracking approach based on affine subspaces (constructed from several images) which are able to accommodate the abovementioned variations. We use affine subspaces not only to represent the object, but also the candidate areas that the object may occupy. We furthermore propose a novel approach to measure affine subspace-to-subspace distance via the use of non-Euclidean geometry of Grassmann manifolds. The tracking problem is then considered as an inference task in a Markov Chain Monte Carlo framework via particle filtering. Quantitative evaluation on challenging video sequences indicates that the proposed approach obtains considerably better performance than several recent state-of-the-art methods such as Tracking-Learning-Detection and MILtrack.
This paper presents a new loss function for the prediction of oriented bounding boxes, named head-tail-loss. The loss function consists in minimizing the distance between the prediction and the annotation of two key points that are representing the annotation of the object. The first point is the center point and the second is the head of the object. However, for the second point, the minimum distance between the prediction and either the head or tail of the groundtruth is used. On this way, either prediction is valid (with the head pointing to the tail or the tail pointing to the head). At the end the importance is to detect the direction of the object but not its heading. The new loss function has been evaluated on the DOTA and HRSC2016 datasets and has shown potential for elongated objects such as ships and also for other types of objects with different shapes.
Corrosion is a form of damage that often appears on the surface of metal-made objects used in industrial applications. Those damages can be critical depending on the purpose of the used object. Optical-based testing systems provide a form of non-contact data acquisition, where the acquired data can then be used to analyse the surface of an object. In the field of industrial image processing, this is called surface inspection. We provide a testing setup consisting of a rotary table which rotates the object by 360 degrees, as well as industrial RGB cameras and laser triangulation sensors for the acquisition of 2D and 3D data as our multi-sensor system. These sensors acquire data while the object to be tested takes a full rotation. Further on, data augmentation is applied to prepare new data or enhance already acquired data. In order to evaluate the impact of a laser triangulation sensor for corrosion detection, one challenge is to at first fuse the data of both domains. After the data fusion process, 5 different channels can be utilized to create a 5D feature space. Besides the red, green and blue channels of the image (1-3), additional range data from the laser triangulation sensor is incorporated (4). As a fifth channel, said sensor provides additional intensity data (5). With a multi-channel image classification, a 5D feature space will lead to slightly superior results opposed to a 3D feature space, composed of only the RGB channels of the image.
객체 검출기는 조명, 날씨, 가림(occlusion) 변화와 같은 도메인 이동(domain shift) 하에서 성능이 자주 저하된다. 이러한 이동은 객체 외형을 바꾸고, 도메인 간 일반화되지 않는 학습 분포에서 학습된 시각적 지름길(visual shortcuts)에 대한 의존을 드러낸다. 이러한 도메인 변이를 포착할 만큼 충분한 실세계 샘플을 확보하는 것은 특히 특수하고 저데이터(low-data) 환경에서 어렵다. 최근 확산(diffusion) 기반 생성형 이미지 편집의 발전은 합성 데이터 증강을 통해 객체 검출기의 도메인 내(in-domain) 성능을 개선할 가능성을 보여 주었다. 그러나 도메인 외(out-of-domain) 강건성을 높이는 잠재력은 대체로 탐색되지 않았다. 우리는 생성형 이미지 편집이 학습 데이터에서 통제된 도메인 이동을 시뮬레이션하여 소스와 타깃 도메인 간 격차를 효과적으로 메울 수 있다고 가설한다. 이를 검증하기 위해 위장 군용 차량 검출을 어려운 도메인 이동 시나리오로 연구했다. 위장하지 않은 데이터로 학습한 검출기는 15개 차량 클래스에 대한 근접·지상 수준 영상에서 잎사귀, 그물망, 다중 스펙트럼 위장이 포함된 실제 테스트 영상에서 상당한 성능 저하를 보인다. Qwen Image Edit 2509와 Flux.2 Dev 두 가지 확산 기반 편집 모델, 그리고 Qwen의 LoRA 미세조정 버전을 사용해 학습 데이터에 위장을 합성적으로 추가했으며, 비생성적 검은 막대 가림 기준선이 증강 품질의 하한으로 사용되었다. 실제 및 합성 데이터로 학습한 GroundingDINO 검출기에서 생성형 위장 증강은 잎사귀 위장(+20.1)과 그물망 위장(+14.4)에 대해 mAP를 크게 향상시켰다. 다중 스펙트럼 위장 생성은 더 어려웠지만, LoRA 미세조정은 위장하지 않은 기준선 대비 4.4 mAP만큼 성능을 개선했다.
Simultaneous Localization And Mapping (SLAM) is a fundamental problem in mobile robotics. While point-based SLAM methods provide accurate camera localization, the generated maps lack semantic information. On the other hand, state of the art object detection methods provide rich information about entities present in the scene from a single image. This work marries the two and proposes a method for representing generic objects as quadrics which allows object detections to be seamlessly integrated in a SLAM framework. For scene coverage, additional dominant planar structures are modeled as infinite planes. Experiments show that the proposed points-planes-quadrics representation can easily incorporate Manhattan and object affordance constraints, greatly improving camera localization and leading to semantically meaningful maps. The performance of our SLAM system is demonstrated in https://youtu.be/dR-rB9keF8M .
Despite the success of many advanced tracking methods in this area, tracking targets with drastic variation of appearance such as deformation, view change and partial occlusion in video sequences is still a challenge in practical applications. In this letter, we take these serious tracking problems into account simultaneously, proposing a dynamic graph based model to track object and its deformable parts at multiple resolutions. The method introduces well learned structural object detection models into object tracking applications as prior knowledge to deal with deformation and view change. Meanwhile, it explicitly formulates partial occlusion by integrating spatial potentials and temporal potentials with an unparameterized occlusion handling mechanism in the dynamic conditional random field framework. Empirical results demonstrate that the method outperforms state-of-the-art trackers on different challenging video sequences.