The main challenge for small object detection algorithms is to ensure accuracy while pursuing real-time performance. The RT-DETR model performs well in real-time object detection, but performs poorly in small object detection accuracy. In order to compensate for the shortcomings of the RT-DETR model in small object detection, two key improvements are proposed in this study. Firstly, The RT-DETR utilises a Transformer that receives input solely from the final layer of Backbone features. This means that the Transformer's input only receives semantic information from the highest level of abstraction in the Deep Network, and ignores detailed information such as edges, texture or color gradients that are critical to the location of small objects at lower levels of abstraction. Including only deep features can introduce additional background noise. This can have a negative impact on the accuracy of small object detection. To address this issue, we propose the fine-grained path augmentation method. This method helps to locate small objects more accurately by providing detailed information to the deep network. So, the input to the transformer contains both semantic and detailed information. Secondly, In RT-DETR, the decoder takes feature maps of different levels as input after concatenating them with equal weight. However, this operation is not effective in dealing with the complex relationship of multi-scale information captured by feature maps of different sizes. Therefore, we propose an adaptive feature fusion algorithm that assigns learnable parameters to each feature map from different levels. This allows the model to adaptively fuse feature maps from different levels and effectively integrate feature information from different scales. This enhances the model's ability to capture object features at different scales, thereby improving the accuracy of detecting small objects.
In recent years, deep learning based object detection methods have achieved promising performance in controlled environments. However, these methods lack sufficient capabilities to handle underwater object detection due to these challenges: (1) images in the underwater datasets and real applications are blurry whilst accompanying severe noise that confuses the detectors and (2) objects in real applications are usually small. In this paper, we propose a novel Sample-WeIghted hyPEr Network (SWIPENET), and a robust training paradigm named Curriculum Multi-Class Adaboost (CMA), to address these two problems at the same time. Firstly, the backbone of SWIPENET produces multiple high resolution and semantic-rich Hyper Feature Maps, which significantly improve small object detection. Secondly, a novel sample-weighted detection loss function is designed for SWIPENET, which focuses on learning high weight samples and ignore learning low weight samples. Moreover, inspired by the human education process that drives the learning from easy to hard concepts, we here propose the CMA training paradigm that first trains a clean detector which is free from the influence of noisy data. Then, based on the clean detector, multiple detectors focusing on learning diverse noisy data are trained and incorporated into a unified deep ensemble of strong noise immunity. Experiments on two underwater robot picking contest datasets (URPC2017 and URPC2018) show that the proposed SWIPENET+CMA framework achieves better accuracy in object detection against several state-of-the-art approaches.
Lidar-based perception pipelines rely on 3D object detection models to interpret complex scenes. While multiple representations for lidar exist, the range-view is enticing since it losslessly encodes the entire lidar sensor output. In this work, we achieve state-of-the-art amongst range-view 3D object detection models without using multiple techniques proposed in past range-view literature. We explore range-view 3D object detection across two modern datasets with substantially different properties: Argoverse 2 and Waymo Open. Our investigation reveals key insights: (1) input feature dimensionality significantly influences the overall performance, (2) surprisingly, employing a classification loss grounded in 3D spatial proximity works as well or better compared to more elaborate IoU-based losses, and (3) addressing non-uniform lidar density via a straightforward range subsampling technique outperforms existing multi-resolution, range-conditioned networks. Our experiments reveal that techniques proposed in recent range-view literature are not needed to achieve state-of-the-art performance. Combining the above findings, we establish a new state-of-the-art model for range-view 3D object detection -- improving AP by 2.2% on the Waymo Open dataset while maintaining a runtime of 10 Hz. We establish the first range-view model on the Argoverse 2 dataset and outperform strong voxel-based baselines. All models are multi-class and open-source. Code is available at https://github.com/benjaminrwilson/range-view-3d-detection.
The state-of-the-art object detection method is complicated with various modules such as backbone, feature fusion neck, RPN and RCNN head, where each module may have different designs and structures. How to leverage the computational cost and accuracy trade-off for the structural combination as well as the modular selection of multiple modules? Neural architecture search (NAS) has shown great potential in finding an optimal solution. Existing NAS works for object detection only focus on searching better design of a single module such as backbone or feature fusion neck, while neglecting the balance of the whole system. In this paper, we present a two-stage coarse-to-fine searching strategy named Structural-to-Modular NAS (SM-NAS) for searching a GPU-friendly design of both an efficient combination of modules and better modular-level architecture for object detection. Specifically, Structural-level searching stage first aims to find an efficient combination of different modules; Modular-level searching stage then evolves each specific module and pushes the Pareto front forward to a faster task-specific network. We consider a multi-objective search where the search space covers many popular designs of detection methods. We directly search a detection backbone without pre-trained models or any proxy task by exploring a fast training from scratch strategy. The resulting architectures dominate state-of-the-art object detection systems in both inference time and accuracy and demonstrate the effectiveness on multiple detection datasets, e.g. halving the inference time with additional 1% mAP improvement compared to FPN and reaching 46% mAP with the similar inference time of MaskRCNN.
One object class may show large variations due to diverse illuminations, backgrounds and camera viewpoints. Traditional object detection methods often perform worse under unconstrained video environments. To address this problem, many modern approaches model deep hierarchical appearance representations for object detection. Most of these methods require a timeconsuming training process on large manual labelling sample set. In this paper, the proposed framework takes a remarkably different direction to resolve the multi-scene detection problem in a bottom-up fashion. First, a scene-specific objector is obtained from a fully autonomous learning process triggered by marking several bounding boxes around the object in the first video frame via a mouse. Here the human labeled training data or a generic detector are not needed. Second, this learning process is conveniently replicated many times in different surveillance scenes and results in particular detectors under various camera viewpoints. Thus, the proposed framework can be employed in multi-scene object detection applications with minimal supervision. Obviously, the initial scene-specific detector, initialized by several bounding boxes, exhibits poor detection performance and is difficult to improve with traditional online learning algorithm. Consequently, we propose Generative-Discriminative model to partition detection response space and assign each partition an individual descriptor that progressively achieves high classification accuracy. A novel online gradual optimized process is proposed to optimize the Generative-Discriminative model and focus on the hard samples.Experimental results on six video datasets show our approach achieves comparable performance to robust supervised methods, and outperforms the state of the art self-learning methods under varying imaging conditions.
Machine-learning algorithms offer immense possibilities in the development of several cognitive applications. In fact, large scale machine-learning classifiers now represent the state-of-the-art in a wide range of object detection/classification problems. However, the network complexities of large-scale classifiers present them as one of the most challenging and energy intensive workloads across the computing spectrum. In this paper, we present a new approach to optimize energy efficiency of object detection tasks using semantic decomposition to build a hierarchical classification framework. We observe that certain semantic information like color/texture are common across various images in real-world datasets for object detection applications. We exploit these common semantic features to distinguish the objects of interest from the remaining inputs (non-objects of interest) in a dataset at a lower computational effort. We propose a 2-stage hierarchical classification framework, with increasing levels of complexity, wherein the first stage is trained to recognize the broad representative semantic features relevant to the object of interest. The first stage rejects the input instances that do not have the representative features and passes only the relevant instances to the second stage. Our methodology thus allows us to reject certain information at lower complexity and utilize the full computational effort of a network only on a smaller fraction of inputs to perform detection. We use color and texture as distinctive traits to carry out several experiments for object detection. Our experiments on the Caltech101/CIFAR10 dataset show that the proposed method yields 1.93x/1.46x improvement in average energy, respectively, over the traditional single classifier model.
Object detection is a challenging task in remote sensing because objects only occupy a few pixels in the images, and the models are required to simultaneously learn object locations and detection. Even though the established approaches well perform for the objects of regular sizes, they achieve weak performance when analyzing small ones or getting stuck in the local minima (e.g. false object parts). Two possible issues stand in their way. First, the existing methods struggle to perform stably on the detection of small objects because of the complicated background. Second, most of the standard methods used hand-crafted features, and do not work well on the detection of objects parts of which are missing. We here address the above issues and propose a new architecture with a multiple patch feature pyramid network (MPFP-Net). Different from the current models that during training only pursue the most discriminative patches, in MPFPNet the patches are divided into class-affiliated subsets, in which the patches are related and based on the primary loss function, a sequence of smooth loss functions are determined for the subsets to improve the model for collecting small object parts. To enhance the feature representation for patch selection, we introduce an effective method to regularize the residual values and make the fusion transition layers strictly norm-preserving. The network contains bottom-up and crosswise connections to fuse the features of different scales to achieve better accuracy, compared to several state-of-the-art object detection models. Also, the developed architecture is more efficient than the baselines.
In this paper we study the problem of object detection for RGB-D images using semantically rich image and depth features. We propose a new geocentric embedding for depth images that encodes height above ground and angle with gravity for each pixel in addition to the horizontal disparity. We demonstrate that this geocentric embedding works better than using raw depth images for learning feature representations with convolutional neural networks. Our final object detection system achieves an average precision of 37.3%, which is a 56% relative improvement over existing methods. We then focus on the task of instance segmentation where we label pixels belonging to object instances found by our detector. For this task, we propose a decision forest approach that classifies pixels in the detection window as foreground or background using a family of unary and binary tests that query shape and geocentric pose features. Finally, we use the output from our object detectors in an existing superpixel classification framework for semantic scene segmentation and achieve a 24% relative improvement over current state-of-the-art for the object categories that we study. We believe advances such as those represented in this paper will facilitate the use of perception in fields like robotics.
Region-based Convolutional Neural Networks (R-CNNs) have achieved great success in the field of object detection. The existing R-CNNs usually divide a Region-of-Interest (ROI) into grids, and then localize objects by utilizing the spatial information reflected by the relative position of each grid in the ROI. In this paper, we propose a novel feature-encoding approach, where spatial information is represented through the spatial distributions of visual patterns. In particular, we design a Mask Weight Network (MWN) to learn a set of masks and then apply channel-wise masking operations to ROI feature map, followed by a global pooling and a cheap fully-connected layer. We integrate the newly designed feature encoder into the Faster R-CNN architecture. The resulting new Faster R-CNNs can preserve the object-detection accuracy of the standard Faster R-CNNs by using substantially fewer parameters. Compared to R-FCNs using state-of-art PS ROI pooling and deformable PS ROI pooling, the new Faster R-CNNs can produce higher object-detection accuracy with good run-time efficiency. We also show that a specifically designed and learned MWN can capture global contextual information and further improve the object-detection accuracy. Validation experiments are conducted on both PASCAL VOC and MS COCO datasets.
Video Camouflaged Object Detection (VCOD) is a challenging task which aims to identify objects that seamlessly concealed within the background in videos. The dynamic properties of video enable detection of camouflaged objects through motion cues or varied perspectives. Previous VCOD datasets primarily contain animal objects, limiting the scope of research to wildlife scenarios. However, the applications of VCOD extend beyond wildlife and have significant implications in security, art, and medical fields. Addressing this problem, we construct a new large-scale multi-domain VCOD dataset MSVCOD. To achieve high-quality annotations, we design a semi-automatic iterative annotation pipeline that reduces costs while maintaining annotation accuracy. Our MSVCOD is the largest VCOD dataset to date, introducing multiple object categories including human, animal, medical, and vehicle objects for the first time, while also expanding background diversity across various environments. This expanded scope increases the practical applicability of the VCOD task in camouflaged object detection. Alongside this dataset, we introduce a one-steam video camouflage object detection model that performs both feature extraction and information fusion without additional motion feature fusion modules. Our framework achieves state-of-the-art results on the existing VCOD animal dataset and the proposed MSVCOD. The dataset and code will be made publicly available.
Although Faster R-CNN and its variants have shown promising performance in object detection, they only exploit simple first-order representation of object proposals for final classification and regression. Recent classification methods demonstrate that the integration of high-order statistics into deep convolutional neural networks can achieve impressive improvement, but their goal is to model whole images by discarding location information so that they cannot be directly adopted to object detection. In this paper, we make an attempt to exploit high-order statistics in object detection, aiming at generating more discriminative representations for proposals to enhance the performance of detectors. To this end, we propose a novel Multi-scale Location-aware Kernel Representation (MLKP) to capture high-order statistics of deep features in proposals. Our MLKP can be efficiently computed on a modified multi-scale feature map using a low-dimensional polynomial kernel approximation.Moreover, different from existing orderless global representations based on high-order statistics, our proposed MLKP is location retentive and sensitive so that it can be flexibly adopted to object detection. Through integrating into Faster R-CNN schema, the proposed MLKP achieves very competitive performance with state-of-the-art methods, and improves Faster R-CNN by 4.9% (mAP), 4.7% (mAP) and 5.0% (AP at IOU=[0.5:0.05:0.95]) on PASCAL VOC 2007, VOC 2012 and MS COCO benchmarks, respectively. Code is available at: https://github.com/Hwang64/MLKP.
Object detection with deep neural networks is often performed by passing a few thousand candidate bounding boxes through a deep neural network for each image. These bounding boxes are highly correlated since they originate from the same image. In this paper we investigate how to exploit feature occurrence at the image scale to prune the neural network which is subsequently applied to all bounding boxes. We show that removing units which have near-zero activation in the image allows us to significantly reduce the number of parameters in the network. Results on the PASCAL 2007 Object Detection Challenge demonstrate that up to 40% of units in some fully-connected layers can be entirely eliminated with little change in the detection result.
This paper presents a framework designed for the multi-object detection purposes and adjusted for the application of product search on the market shelves. The framework uses a single feedback loop and a pattern resizing mechanism to demonstrate the top effectiveness of the state-of-the-art local features. A high detection rate with a low false detection chance can be achieved with use of only one pattern per object and no manual parameters adjustments. The method incorporates well known local features and a basic matching process to create a reliable voting space. Further steps comprise of metric transformations, graphical vote space representation, two-phase vote aggregation process and a cascade of verifying filters.
Recent state-of-the-art methods for HOI detection typically build on transformer architectures with two decoder branches, one for human-object pair detection and the other for interaction classification. Such disentangled transformers, however, may suffer from insufficient context exchange between the branches and lead to a lack of context information for relational reasoning, which is critical in discovering HOI instances. In this work, we propose the multiplex relation network (MUREN) that performs rich context exchange between three decoder branches using unary, pairwise, and ternary relations of human, object, and interaction tokens. The proposed method learns comprehensive relational contexts for discovering HOI instances, achieving state-of-the-art performance on two standard benchmarks for HOI detection, HICO-DET and V-COCO.
Dropout Variational Inference, or Dropout Sampling, has been recently proposed as an approximation technique for Bayesian Deep Learning and evaluated for image classification and regression tasks. This paper investigates the utility of Dropout Sampling for object detection for the first time. We demonstrate how label uncertainty can be extracted from a state-of-the-art object detection system via Dropout Sampling. We evaluate this approach on a large synthetic dataset of 30,000 images, and a real-world dataset captured by a mobile robot in a versatile campus environment. We show that this uncertainty can be utilized to increase object detection performance under the open-set conditions that are typically encountered in robotic vision. A Dropout Sampling network is shown to achieve a 12.3% increase in recall (for the same precision score as a standard network) and a 15.1% increase in precision (for the same recall score as the standard network).
Recent works on salient object detection have made use of multi-scale features in a way such that high-level features and low-level features can collaborate in locating salient objects. Many of the previous methods have achieved great performance in salient object detection. By merging the high-level and low-level features, a large number of feature information can be extracted. Generally, they are doing these in a one-way framework, and interweaving the variable features all the way to the final feature output. Which may cause some blurring or inaccurate localization of saliency maps. To overcome these difficulties, we introduce a multistep feature aggregation (MSFA) framework for salient object detection, which is composed of three modules, including the Diverse Reception (DR) module, multiscale interaction (MSI) module and Feature Enhancement (FE) module to accomplish better multi-level feature fusion. Experimental results on six benchmark datasets demonstrate that MSFA achieves state-of-the-art performance.
Single-branch object detection methods use shared features for localization and classification, yet the shared features are not fit for the two different tasks simultaneously. Multi-branch object detection methods usually use different features for localization and classification separately, ignoring the relevance between different tasks. Therefore, we propose multi-semantic interactive learning (MSIL) to mine the semantic relevance between different branches and extract multi-semantic enhanced features of objects. MSIL first performs semantic alignment of regression and classification branches, then merges the features of different branches by semantic fusion, finally extracts relevant information by semantic separation and passes it back to the regression and classification branches respectively. More importantly, MSIL can be integrated into existing object detection nets as a plug-and-play component. Experiments on the MS COCO, and Pascal VOC datasets show that the integration of MSIL with existing algorithms can utilize the relevant information between semantics of different tasks and achieve better performance.
We examine how the saccade mechanism from biological vision can be used to make deep neural networks more efficient for classification and object detection problems. Our proposed approach is based on the ideas of attention-driven visual processing and saccades, miniature eye movements influenced by attention. We conduct experiments by analyzing: i) the robustness of different deep neural network (DNN) feature extractors to partially-sensed images for image classification and object detection, and ii) the utility of saccades in masking image patches for image classification and object tracking. Experiments with convolutional nets (ResNet-18) and transformer-based models (ViT, DETR, TransTrack) are conducted on several datasets (CIFAR-10, DAVSOD, MSCOCO, and MOT17). Our experiments show intelligent data reduction via learning to mimic human saccades when used in conjunction with state-of-the-art DNNs for classification, detection, and tracking tasks. We observed minimal drop in performance for the classification and detection tasks while only using about 30\% of the original sensor data. We discuss how the saccade mechanism can inform hardware design via ``in-pixel'' processing.
We present a method to populate an unknown environment with models of previously seen objects, placed in a Euclidean reference frame that is inferred causally and on-line using monocular video along with inertial sensors. The system we implement returns a sparse point cloud for the regions of the scene that are visible but not recognized as a previously seen object, and a detailed object model and its pose in the Euclidean frame otherwise. The system includes bottom-up and top-down components, whereby deep networks trained for detection provide likelihood scores for object hypotheses provided by a nonlinear filter, whose state serves as memory. Additional networks provide likelihood scores for edges, which complements detection networks trained to be invariant to small deformations. We test our algorithm on existing datasets, and also introduce the VISMA dataset, that provides ground truth pose, point-cloud map, and object models, along with time-stamped inertial measurements.
We propose ST-DETR, a Spatio-Temporal Transformer-based architecture for object detection from a sequence of temporal frames. We treat the temporal frames as sequences in both space and time and employ the full attention mechanisms to take advantage of the features correlations over both dimensions. This treatment enables us to deal with frames sequence as temporal object features traces over every location in the space. We explore two possible approaches; the early spatial features aggregation over the temporal dimension, and the late temporal aggregation of object query spatial features. Moreover, we propose a novel Temporal Positional Embedding technique to encode the time sequence information. To evaluate our approach, we choose the Moving Object Detection (MOD)task, since it is a perfect candidate to showcase the importance of the temporal dimension. Results show a significant 5% mAP improvement on the KITTI MOD dataset over the 1-step spatial baseline.