Current large-scale generative models have impressive efficiency in generating high-quality images based on text prompts. However, they lack the ability to precisely control the size and position of objects in the generated image. In this study, we analyze the generative mechanism of the stable diffusion model and propose a new interactive generation paradigm that allows users to specify the position of generated objects without additional training. Moreover, we propose an object detection-based evaluation metric to assess the control capability of location aware generation task. Our experimental results show that our method outperforms state-of-the-art methods on both control capacity and image quality.
Recently, 3D object detection has attracted significant attention and achieved continuous improvement in real road scenarios. The environmental information is collected from a single sensor or multi-sensor fusion to detect interested objects. However, most of the current 3D object detection approaches focus on developing advanced network architectures to improve the detection precision of the object rather than considering the dynamic driving scenes, where data collected from sensors equipped in the vehicle contain various perturbation features. As a result, existing work cannot still tackle the perturbation issue. In order to solve this problem, we propose a group equivariant bird's eye view network (GeqBevNet) based on the group equivariant theory, which introduces the concept of group equivariant into the BEV fusion object detection network. The group equivariant network is embedded into the fused BEV feature map to facilitate the BEV-level rotational equivariant feature extraction, thus leading to lower average orientation error. In order to demonstrate the effectiveness of the GeqBevNet, the network is verified on the nuScenes validation dataset in which mAOE can be decreased to 0.325. Experimental results demonstrate that GeqBevNet can extract more rotational equivariant features in the 3D object detection of the actual road scene and improve the performance of object orientation prediction.
In this paper, we study the problem of semi-supervised 3D object detection, which is of great importance considering the high annotation cost for cluttered 3D indoor scenes. We resort to the robust and principled framework of selfteaching, which has triggered notable progress for semisupervised learning recently. While this paradigm is natural for image-level or pixel-level prediction, adapting it to the detection problem is challenged by the issue of proposal matching. Prior methods are based upon two-stage pipelines, matching heuristically selected proposals generated in the first stage and resulting in spatially sparse training signals. In contrast, we propose the first semisupervised 3D detection algorithm that works in the singlestage manner and allows spatially dense training signals. A fundamental issue of this new design is the quantization error caused by point-to-voxel discretization, which inevitably leads to misalignment between two transformed views in the voxel domain. To this end, we derive and implement closed-form rules that compensate this misalignment onthe-fly. Our results are significant, e.g., promoting ScanNet [email omitted] from 35.2% to 48.5% using 20% annotation. Codes and data will be publicly available.
This work presents Focal-Stable-DINO, a strong and reproducible object detection model which achieves 64.6 AP on COCO val2017 and 64.8 AP on COCO test-dev using only 700M parameters without any test time augmentation. It explores the combination of the powerful FocalNet-Huge backbone with the effective Stable-DINO detector. Different from existing SOTA models that utilize an extensive number of parameters and complex training techniques on large-scale private data or merged data, our model is exclusively trained on the publicly available dataset Objects365, which ensures the reproducibility of our approach.
Depth completion and object detection are two crucial tasks often used for aerial 3D mapping, path planning, and collision avoidance of Uncrewed Aerial Vehicles (UAVs). Common solutions include using measurements from a LiDAR sensor; however, the generated point cloud is often sparse and irregular and limits the system's capabilities in 3D rendering and safety-critical decision-making. To mitigate this challenge, information from other sensors on the UAV (viz., a camera used for object detection) is utilized to help the depth completion process generate denser 3D models. Performing both aerial depth completion and object detection tasks while fusing the data from the two sensors poses a challenge to resource efficiency. We address this challenge by proposing a novel approach to jointly execute the two tasks in a single pass. The proposed method is based on an encoder-focused multi-task learning model that exposes the two tasks to jointly learned features. We demonstrate how semantic expectations of the objects in the scene learned by the object detection pathway can boost the performance of the depth completion pathway while placing the missing depth values. Experimental results show that the proposed multi-task network outperforms its single-task counterpart, particularly when exposed to defective inputs.
Optical flow is an indispensable building block for various important computer vision tasks, including motion estimation, object tracking, and disparity measurement. In this work, we propose TransFlow, a pure transformer architecture for optical flow estimation. Compared to dominant CNN-based methods, TransFlow demonstrates three advantages. First, it provides more accurate correlation and trustworthy matching in flow estimation by utilizing spatial self-attention and cross-attention mechanisms between adjacent frames to effectively capture global dependencies; Second, it recovers more compromised information (e.g., occlusion and motion blur) in flow estimation through long-range temporal association in dynamic scenes; Third, it enables a concise self-learning paradigm and effectively eliminate the complex and laborious multi-stage pre-training procedures. We achieve the state-of-the-art results on the Sintel, KITTI-15, as well as several downstream tasks, including video object detection, interpolation and stabilization. For its efficacy, we hope TransFlow could serve as a flexible baseline for optical flow estimation.
Language-based object detection is a promising direction towards building a natural interface to describe objects in images that goes far beyond plain category names. While recent methods show great progress in that direction, proper evaluation is lacking. With OmniLabel, we propose a novel task definition, dataset, and evaluation metric. The task subsumes standard- and open-vocabulary detection as well as referring expressions. With more than 28K unique object descriptions on over 25K images, OmniLabel provides a challenging benchmark with diverse and complex object descriptions in a naturally open-vocabulary setting. Moreover, a key differentiation to existing benchmarks is that our object descriptions can refer to one, multiple or even no object, hence, providing negative examples in free-form text. The proposed evaluation handles the large label space and judges performance via a modified average precision metric, which we validate by evaluating strong language-based baselines. OmniLabel indeed provides a challenging test bed for future research on language-based detection.
Object detection is one of the key tasks in many applications of computer vision. Deep Neural Networks (DNNs) are undoubtedly a well-suited approach for object detection. However, such DNNs need highly adapted hardware together with hardware-specific optimization to guarantee high efficiency during inference. This is especially the case when aiming for efficient object detection in video streaming applications on limited hardware such as edge devices. Comparing vendor-specific hardware and related optimization software pipelines in a fair experimental setup is a challenge. In this paper, we propose a framework that uses a host computer with a host software application together with a light-weight interface based on the Message Queuing Telemetry Transport (MQTT) protocol. Various different target devices with target apps can be connected via MQTT with this host computer. With well-defined and standardized MQTT messages, object detection results can be reported to the host computer, where the results are evaluated without harming or influencing the processing on the device. With this quite generic framework, we can measure the object detection performance, the runtime, and the energy efficiency at the same time. The effectiveness of this framework is demonstrated in multiple experiments that offer deep insights into the optimization of DNNs.
The advancement of multi-channel synthetic aperture radar (SAR) system is considered as an upgraded technology for surveillance activities. SAR sensors onboard provide data for coastal ocean surveillance and a view of the oceanic surface features. Vessel monitoring has earlier been performed using Constant False Alarm Rate (CFAR) algorithm which is not a smart technique as it lacks decision-making capabilities, therefore we introduce wavelet transformation-based Convolution Neural Network approach to recognize objects from SAR images during the heavy naval traffic, which corresponds to the numerous object detection. The utilized information comprises Sentinel-1 SAR-C dual-polarization data acquisitions over the western coastal zones of India and with help of the proposed technique we have obtained 95.46% detection accuracy. Utilizing this model can automatize the monitoring of naval objects and recognition of foreign maritime intruders.
Noise has always been nonnegligible trouble in object detection by creating confusion in model reasoning, thereby reducing the informativeness of the data. It can lead to inaccurate recognition due to the shift in the observed pattern, that requires a robust generalization of the models. To implement a general vision model, we need to develop deep learning models that can adaptively select valid information from multi-modal data. This is mainly based on two reasons. Multi-modal learning can break through the inherent defects of single-modal data, and adaptive information selection can reduce chaos in multi-modal data. To tackle this problem, we propose a universal uncertainty-aware multi-modal fusion model. It adopts a multi-pipeline loosely coupled architecture to combine the features and results from point clouds and images. To quantify the correlation in multi-modal information, we model the uncertainty, as the inverse of data information, in different modalities and embed it in the bounding box generation. In this way, our model reduces the randomness in fusion and generates reliable output. Moreover, we conducted a completed investigation on the KITTI 2D object detection dataset and its derived dirty data. Our fusion model is proven to resist severe noise interference like Gaussian, motion blur, and frost, with only slight degradation. The experiment results demonstrate the benefits of our adaptive fusion. Our analysis on the robustness of multi-modal fusion will provide further insights for future research.
The recently proposed data augmentation TransMix employs attention labels to help visual transformers (ViT) achieve better robustness and performance. However, TransMix is deficient in two aspects: 1) The image cropping method of TransMix may not be suitable for ViTs. 2) At the early stage of training, the model produces unreliable attention maps. TransMix uses unreliable attention maps to compute mixed attention labels that can affect the model. To address the aforementioned issues, we propose MaskMix and Progressive Attention Labeling (PAL) in image and label space, respectively. In detail, from the perspective of image space, we design MaskMix, which mixes two images based on a patch-like grid mask. In particular, the size of each mask patch is adjustable and is a multiple of the image patch size, which ensures each image patch comes from only one image and contains more global contents. From the perspective of label space, we design PAL, which utilizes a progressive factor to dynamically re-weight the attention weights of the mixed attention label. Finally, we combine MaskMix and Progressive Attention Labeling as our new data augmentation method, named MixPro. The experimental results show that our method can improve various ViT-based models at scales on ImageNet classification (73.8\% top-1 accuracy based on DeiT-T for 300 epochs). After being pre-trained with MixPro on ImageNet, the ViT-based models also demonstrate better transferability to semantic segmentation, object detection, and instance segmentation. Furthermore, compared to TransMix, MixPro also shows stronger robustness on several benchmarks. The code is available at https://github.com/fistyee/MixPro.
Transformers have shown promising progress in various visual object detection tasks, including monocular 2D/3D detection and surround-view 3D detection. More importantly, the attention mechanism in the Transformer model and the 3D information extraction in binocular stereo are both similarity-based. However, directly applying existing Transformer-based detectors to binocular stereo 3D object detection leads to slow convergence and significant precision drops. We argue that a key cause of that defect is that existing Transformers ignore the binocular-stereo-specific image correspondence information. In this paper, we explore the model design of Transformers in binocular 3D object detection, focusing particularly on extracting and encoding task-specific image correspondence information. To achieve this goal, we present TS3D, a Transformer-based Stereo-aware 3D object detector. In the TS3D, a Disparity-Aware Positional Encoding (DAPE) module is proposed to embed the image correspondence information into stereo features. The correspondence is encoded as normalized sub-pixel-level disparity and is used in conjunction with sinusoidal 2D positional encoding to provide the 3D location information of the scene. To enrich multi-scale stereo features, we propose a Stereo Preserving Feature Pyramid Network (SPFPN). The SPFPN is designed to preserve the correspondence information while fusing intra-scale and aggregating cross-scale stereo features. Our proposed TS3D achieves a 41.29% Moderate Car detection average precision on the KITTI test set and takes 88 ms to detect objects from each binocular image pair. It is competitive with advanced counterparts in terms of both precision and inference speed.
Feature distillation makes the student mimic the intermediate features of the teacher. Nearly all existing feature-distillation methods use L2 distance or its slight variants as the distance metric between teacher and student features. However, while L2 distance is isotropic w.r.t. all dimensions, the neural network's operation on different dimensions is usually anisotropic, i.e., perturbations with the same 2-norm but in different dimensions of intermediate features lead to changes in the final output with largely different magnitude. Considering this, we argue that the similarity between teacher and student features should not be measured merely based on their appearance (i.e., L2 distance), but should, more importantly, be measured by their difference in function, namely how later layers of the network will read, decode, and process them. Therefore, we propose Function-Consistent Feature Distillation (FCFD), which explicitly optimizes the functional similarity between teacher and student features. The core idea of FCFD is to make teacher and student features not only numerically similar, but more importantly produce similar outputs when fed to the later part of the same network. With FCFD, the student mimics the teacher more faithfully and learns more from the teacher. Extensive experiments on image classification and object detection demonstrate the superiority of FCFD to existing methods. Furthermore, we can combine FCFD with many existing methods to obtain even higher accuracy. Our codes are available at https://github.com/LiuDongyang6/FCFD.
Occlusion between objects is one of the overlooked challenges for object detection in UAV images. Due to the variable altitude and angle of UAVs, occlusion in UAV images happens more frequently than that in natural scenes. Compared to occlusion in natural scene images, occlusion in UAV images happens with feature confusion problem and local aggregation characteristic. And we found that extracting or localizing occlusion between objects is beneficial for the detector to address this challenge. According to this finding, the occlusion localization task is introduced, which together with the object detection task constitutes our occlusion-guided multi-task network (OGMN). The OGMN contains the localization of occlusion and two occlusion-guided multi-task interactions. In detail, an occlusion estimation module (OEM) is proposed to precisely localize occlusion. Then the OGMN utilizes the occlusion localization results to implement occlusion-guided detection with two multi-task interactions. One interaction for the guide is between two task decoders to address the feature confusion problem, and an occlusion decoupling head (ODH) is proposed to replace the general detection head. Another interaction for guide is designed in the detection process according to local aggregation characteristic, and a two-phase progressive refinement process (TPP) is proposed to optimize the detection process. Extensive experiments demonstrate the effectiveness of our OGMN on the Visdrone and UAVDT datasets. In particular, our OGMN achieves 35.0% mAP on the Visdrone dataset and outperforms the baseline by 5.3%. And our OGMN provides a new insight for accurate occlusion localization and achieves competitive detection performance.
This paper aims for high-performance offline LiDAR-based 3D object detection. We first observe that experienced human annotators annotate objects from a track-centric perspective. They first label the objects with clear shapes in a track, and then leverage the temporal coherence to infer the annotations of obscure objects. Drawing inspiration from this, we propose a high-performance offline detector in a track-centric perspective instead of the conventional object-centric perspective. Our method features a bidirectional tracking module and a track-centric learning module. Such a design allows our detector to infer and refine a complete track once the object is detected at a certain moment. We refer to this characteristic as "onCe detecTed, neveR Lost" and name the proposed system CTRL. Extensive experiments demonstrate the remarkable performance of our method, surpassing the human-level annotating accuracy and the previous state-of-the-art methods in the highly competitive Waymo Open Dataset without model ensemble. The code will be made publicly available at https://github.com/tusen-ai/SST.
Currently prevalent multimodal 3D detection methods are built upon LiDAR-based detectors that usually use dense Bird's-Eye-View (BEV) feature maps. However, the cost of such BEV feature maps is quadratic to the detection range, making it not suitable for long-range detection. Fully sparse architecture is gaining attention as they are highly efficient in long-range perception. In this paper, we study how to effectively leverage image modality in the emerging fully sparse architecture. Particularly, utilizing instance queries, our framework integrates the well-studied 2D instance segmentation into the LiDAR side, which is parallel to the 3D instance segmentation part in the fully sparse detector. This design achieves a uniform query-based fusion framework in both the 2D and 3D sides while maintaining the fully sparse characteristic. Extensive experiments showcase state-of-the-art results on the widely used nuScenes dataset and the long-range Argoverse 2 dataset. Notably, the inference speed of the proposed method under the long-range LiDAR perception setting is 2.7 $\times$ faster than that of other state-of-the-art multimodal 3D detection methods. Code will be released at \url{https://github.com/BraveGroup/FullySparseFusion}.
Few-shot object detection, the problem of modelling novel object detection categories with few training instances, is an emerging topic in the area of few-shot learning and object detection. Contemporary techniques can be divided into two groups: fine-tuning based and meta-learning based approaches. While meta-learning approaches aim to learn dedicated meta-models for mapping samples to novel class models, fine-tuning approaches tackle few-shot detection in a simpler manner, by adapting the detection model to novel classes through gradient based optimization. Despite their simplicity, fine-tuning based approaches typically yield competitive detection results. Based on this observation, we focus on the role of loss functions and augmentations as the force driving the fine-tuning process, and propose to tune their dynamics through meta-learning principles. The proposed training scheme, therefore, allows learning inductive biases that can boost few-shot detection, while keeping the advantages of fine-tuning based approaches. In addition, the proposed approach yields interpretable loss functions, as opposed to highly parametric and complex few-shot meta-models. The experimental results highlight the merits of the proposed scheme, with significant improvements over the strong fine-tuning based few-shot detection baselines on benchmark Pascal VOC and MS-COCO datasets, in terms of both standard and generalized few-shot performance metrics.
The recent work known as Segment Anything (SA) has made significant strides in pushing the boundaries of semantic segmentation into the era of foundation models. The impact of SA has sparked extremely active discussions and ushered in an encouraging new wave of developing foundation models for the diverse tasks in the Euclidean domain, such as object detection and image inpainting. Despite the promising advances led by SA, the concept has yet to be extended to the non-Euclidean graph domain. In this paper, we explore a novel Segment Non-Euclidean Anything (SNA) paradigm that strives to develop foundation models that can handle the diverse range of graph data within the non-Euclidean domain, seeking to expand the scope of SA and lay the groundwork for future research in this direction. To achieve this goal, we begin by discussing the recent achievements in foundation models associated with SA. We then shed light on the unique challenges that arise when applying the SA concept to graph analysis, which involves understanding the differences between the Euclidean and non-Euclidean domains from both the data and task perspectives. Motivated by these observations, we present several preliminary solutions to tackle the challenges of SNA and detail their corresponding limitations, along with several potential directions to pave the way for future SNA research. Experiments on five Open Graph Benchmark (OGB) datasets across various tasks, including graph property classification and regression, as well as multi-label prediction, demonstrate that the performance of the naive SNA solutions has considerable room for improvement, pointing towards a promising avenue for future exploration of Graph General Intelligence.
The advancement of computer vision and machine learning has made datasets a crucial element for further research and applications. However, the creation and development of robots with advanced recognition capabilities are hindered by the lack of appropriate datasets. Existing image or video processing datasets are unable to accurately depict observations from a moving robot, and they do not contain the kinematics information necessary for robotic tasks. Synthetic data, on the other hand, are cost-effective to create and offer greater flexibility for adapting to various applications. Hence, they are widely utilized in both research and industry. In this paper, we propose the dataset HabitatDyn, which contains both synthetic RGB videos, semantic labels, and depth information, as well as kinetics information. HabitatDyn was created from the perspective of a mobile robot with a moving camera, and contains 30 scenes featuring six different types of moving objects with varying velocities. To demonstrate the usability of our dataset, two existing algorithms are used for evaluation and an approach to estimate the distance between the object and camera is implemented based on these segmentation methods and evaluated through the dataset. With the availability of this dataset, we aspire to foster further advancements in the field of mobile robotics, leading to more capable and intelligent robots that can navigate and interact with their environments more effectively. The code is publicly available at https://github.com/ignc-research/HabitatDyn.
Despite their superior performance, deep-learning methods often suffer from the disadvantage of needing large-scale well-annotated training data. In response, recent literature has seen a proliferation of efforts aimed at reducing the annotation burden. This paper focuses on a weakly-supervised training setting for single-cell segmentation models, where the only available training label is the rough locations of individual cells. The specific problem is of practical interest due to the widely available nuclei counter-stain data in biomedical literature, from which the cell locations can be derived programmatically. Of more general interest is a proposed self-learning method called collaborative knowledge sharing, which is related to but distinct from the more well-known consistency learning methods. This strategy achieves self-learning by sharing knowledge between a principal model and a very light-weight collaborator model. Importantly, the two models are entirely different in their architectures, capacities, and model outputs: In our case, the principal model approaches the segmentation problem from an object-detection perspective, whereas the collaborator model a sematic segmentation perspective. We assessed the effectiveness of this strategy by conducting experiments on LIVECell, a large single-cell segmentation dataset of bright-field images, and on A431 dataset, a fluorescence image dataset in which the location labels are generated automatically from nuclei counter-stain data. Implementing code is available at https://github.com/jiyuuchc/lacss