In this paper, we point out that the essential differences between CNN-based and Transformer-based detectors, which cause the worse performance of small objects in Transformer-based methods, are the gap between local information and global dependencies in feature extraction and propagation. To address these differences, we propose a new vision Transformer, called Hybrid Network Transformer (Hyneter), after pre-experiments that indicate the gap causes CNN-based and Transformer-based methods to increase size-different objects result unevenly. Different from the divide and conquer strategy in previous methods, Hyneters consist of Hybrid Network Backbone (HNB) and Dual Switching module (DS), which integrate local information and global dependencies, and transfer them simultaneously. Based on the balance strategy, HNB extends the range of local information by embedding convolution layers into Transformer blocks, and DS adjusts excessive reliance on global dependencies outside the patch.
State-of-the-art object detectors usually progressively downsample the input image until it is represented by small feature maps, which loses the spatial information and compromises the representation of small objects. In this article, we propose a context-aware block net (CAB Net) to improve small object detection by building high-resolution and strong semantic feature maps. To internally enhance the representation capacity of feature maps with high spatial resolution, we delicately design the context-aware block (CAB). CAB exploits pyramidal dilated convolutions to incorporate multilevel contextual information without losing the original resolution of feature maps. Then, we assemble CAB to the end of the truncated backbone network (e.g., VGG16) with a relatively small downsampling factor (e.g., 8) and cast off all following layers. CAB Net can capture both basic visual patterns as well as semantical information of small objects, thus improving the performance of small object detection. Experiments conducted on the benchmark Tsinghua-Tencent 100K and the Airport dataset show that CAB Net outperforms other top-performing detectors by a large margin while keeping real-time speed, which demonstrates the effectiveness of CAB Net for small object detection.
Self-supervised feature learning enables perception systems to benefit from the vast raw data recorded by vehicle fleets worldwide. While video-level self-supervised learning approaches have shown strong generalizability on classification tasks, the potential to learn dense representations from sequential data has been relatively unexplored. In this work, we propose TempO, a temporal ordering pretext task for pre-training region-level feature representations for perception tasks. We embed each frame by an unordered set of proposal feature vectors, a representation that is natural for object detection or tracking systems, and formulate the sequential ordering by predicting frame transition probabilities in a transformer-based multi-frame architecture whose complexity scales less than quadratic with respect to the sequence length. Extensive evaluations on the BDD100K, nuImages, and MOT17 datasets show that our TempO pre-training approach outperforms single-frame self-supervised learning methods as well as supervised transfer learning initialization strategies, achieving an improvement of +0.7% in mAP for object detection and +2.0% in the HOTA score for multi-object tracking.
Computer vision-based object detection is a key modality for advanced Detect-And-Avoid systems that allow for autonomous flight missions of UAVs. While standard object detection frameworks do not predict the actual depth of an object, this information is crucial to avoid collisions. In this paper, we propose several novel extensions to state-of-the-art methods for monocular object detection from images at long range. Firstly, we propose Sigmoid and ReLU-like encodings when modeling depth estimation as a regression task. Secondly, we frame the depth estimation as a classification problem and introduce a Soft-Argmax function in the calculation of the training loss. The extensions are exemplarily applied to the YOLOX object detection framework. We evaluate the performance using the Amazon Airborne Object Tracking dataset. In addition, we introduce the Fitness score as a new metric that jointly assesses both object detection and depth estimation performance. Our results show that the proposed methods outperform state-of-the-art approaches w.r.t. existing, as well as the proposed metrics.
Reconstructing a 3D object from a 2D image is a well-researched vision problem, with many kinds of deep learning techniques having been tried. Most commonly, 3D convolutional approaches are used, though previous work has shown state-of-the-art methods using 2D convolutions that are also significantly more efficient to train. With the recent rise of transformers for vision tasks, often outperforming convolutional methods, along with some earlier attempts to use transformers for 3D object reconstruction, we set out to use visual transformers in place of convolutions in existing efficient, high-performing techniques for 3D object reconstruction in order to achieve superior results on the task. Using a transformer-based encoder and decoder to predict 3D structure from 2D images, we achieve accuracy similar or superior to the baseline approach. This study serves as evidence for the potential of visual transformers in the task of 3D object reconstruction.
3D visual perception tasks based on multi-camera images are essential for autonomous driving systems. Latest work in this field performs 3D object detection by leveraging multi-view images as an input and iteratively enhancing object queries (object proposals) by cross-attending multi-view features. However, individual backbone features are not updated with multi-view features and it stays as a mere collection of the output of the single-image backbone network. Therefore we propose 3M3D: A Multi-view, Multi-path, Multi-representation for 3D Object Detection where we update both multi-view features and query features to enhance the representation of the scene in both fine panoramic view and coarse global view. Firstly, we update multi-view features by multi-view axis self-attention. It will incorporate panoramic information in the multi-view features and enhance understanding of the global scene. Secondly, we update multi-view features by self-attention of the ROI (Region of Interest) windows which encodes local finer details in the features. It will help exchange the information not only along the multi-view axis but also along the other spatial dimension. Lastly, we leverage the fact of multi-representation of queries in different domains to further boost the performance. Here we use sparse floating queries along with dense BEV (Bird's Eye View) queries, which are later post-processed to filter duplicate detections. Moreover, we show performance improvements on nuScenes benchmark dataset on top of our baselines.
Road object detection is an important branch of automatic driving technology, The model with higher detection accuracy is more conducive to the safe driving of vehicles. In road object detection, the omission of small objects and occluded objects is an important problem. therefore, reducing the missed rate of the object is of great significance for safe driving. In the work of this paper, based on the YOLOX object detection algorithm to improve, proposes DecIoU boundary box regression loss function to improve the shape consistency of the predicted and real box, and Push Loss is introduced to further optimize the boundary box regression loss function, in order to detect more occluded objects. In addition, the dynamic anchor box mechanism is also used to improve the accuracy of the confidence label, improve the label inaccuracy of object detection model without anchor box. A large number of experiments on KITTI dataset demonstrate the effectiveness of the proposed method, the improved YOLOX-s achieved 88.9% mAP and 91.0% mAR on the KITTI dataset, compared to the baseline version improvements of 2.77% and 4.24%; the improved YOLOX-m achieved 89.1% mAP and 91.4% mAR, compared to the baseline version improvements of 2.30% and 4.10%.
The study of emergent communication has been dedicated to interactive artificial intelligence. While existing work focuses on communication about single objects or complex image scenes, we argue that communicating relationships between multiple objects is important in more realistic tasks, but understudied. In this paper, we try to fill this gap and focus on emergent communication about positional relationships between two objects. We train agents in the referential game where observations contain two objects, and find that generalization is the major problem when the positional relationship is involved. The key factor affecting the generalization ability of the emergent language is the input variation between Speaker and Listener, which is realized by a random image generator in our work. Further, we find that the learned language can generalize well in a new multi-step MDP task where the positional relationship describes the goal, and performs better than raw-pixel images as well as pre-trained image features, verifying the strong generalization ability of discrete sequences. We also show that language transfer from the referential game performs better in the new task than learning language directly in this task, implying the potential benefits of pre-training in referential games. All in all, our experiments demonstrate the viability and merit of having agents learn to communicate positional relationships between multiple objects through emergent communication.
Cross-view multi-object tracking aims to link objects between frames and camera views with substantial overlaps. Although cross-view multi-object tracking has received increased attention in recent years, existing datasets still have several issues, including 1) missing real-world scenarios, 2) lacking diverse scenes, 3) owning a limited number of tracks, 4) comprising only static cameras, and 5) lacking standard benchmarks, which hinder the investigation and comparison of cross-view tracking methods. To solve the aforementioned issues, we introduce DIVOTrack: a new cross-view multi-object tracking dataset for DIVerse Open scenes with dense tracking pedestrians in realistic and non-experimental environments. Our DIVOTrack has fifteen distinct scenarios and 953 cross-view tracks, surpassing all cross-view multi-object tracking datasets currently available. Furthermore, we provide a novel baseline cross-view tracking method with a unified joint detection and cross-view tracking framework named CrossMOT, which learns object detection, single-view association, and cross-view matching with an all-in-one embedding model. Finally, we present a summary of current methodologies and a set of standard benchmarks with our DIVOTrack to provide a fair comparison and conduct a comprehensive analysis of current approaches and our proposed CrossMOT. The dataset and code are available at https://github.com/shengyuhao/DIVOTrack.
Semi-Supervised Object Detection (SSOD) has been successful in improving the performance of both R-CNN series and anchor-free detectors. However, one-stage anchor-based detectors lack the structure to generate high-quality or flexible pseudo labels, leading to serious inconsistency problems in SSOD. In this paper, we propose the Efficient Teacher framework for scalable and effective one-stage anchor-based SSOD training, consisting of Dense Detector, Pseudo Label Assigner, and Epoch Adaptor. Dense Detector is a baseline model that extends RetinaNet with dense sampling techniques inspired by YOLOv5. The Efficient Teacher framework introduces a novel pseudo label assignment mechanism, named Pseudo Label Assigner, which makes more refined use of pseudo labels from Dense Detector. Epoch Adaptor is a method that enables a stable and efficient end-to-end semi-supervised training schedule for Dense Detector. The Pseudo Label Assigner prevents the occurrence of bias caused by a large number of low-quality pseudo labels that may interfere with the Dense Detector during the student-teacher mutual learning mechanism, and the Epoch Adaptor utilizes domain and distribution adaptation to allow Dense Detector to learn globally distributed consistent features, making the training independent of the proportion of labeled data. Our experiments show that the Efficient Teacher framework achieves state-of-the-art results on VOC, COCO-standard, and COCO-additional using fewer FLOPs than previous methods. To the best of our knowledge, this is the first attempt to apply Semi-Supervised Object Detection to YOLOv5.Code is available: https://github.com/AlibabaResearch/efficientteacher
This paper proposes an efficient, low-complexity and anchor-free object detector based on the state-of-the-art YOLO framework, which can be implemented in real time on edge computing platforms. We develop an enhanced data augmentation method to effectively suppress overfitting during training, and design a hybrid random loss function to improve the detection accuracy of small objects. Inspired by FCOS, a lighter and more efficient decoupled head is proposed, and its inference speed can be improved with little loss of precision. Our baseline model can reach the accuracy of 50.6% AP50:95 and 69.8% AP50 in MS COCO2017 dataset, 26.4% AP50:95 and 44.8% AP50 in VisDrone2019-DET dataset, and it meets real-time requirements (FPS>=30) on edge-computing device Nvidia Jetson AGX Xavier. We also designed lighter models with less parameters for edge computing devices with lower computing power, which also show better performances. Our source code, hyper-parameters and model weights are all available at https://github.com/LSH9832/edgeyolo.
Methods for object detection and segmentation often require abundant instance-level annotations for training, which are time-consuming and expensive to collect. To address this, the task of zero-shot object detection (or segmentation) aims at learning effective methods for identifying and localizing object instances for the categories that have no supervision available. Constructing architectures for these tasks requires choosing from a myriad of design options, ranging from the form of the class encoding used to transfer information from seen to unseen categories, to the nature of the function being optimized for learning. In this work, we extensively study these design choices, and carefully construct a simple yet extremely effective zero-shot recognition method. Through extensive experiments on the MSCOCO dataset on object detection and segmentation, we highlight that our proposed method outperforms existing, considerably more complex, architectures. Our findings and method, which we propose as a competitive future baseline, point towards the need to revisit some of the recent design trends in zero-shot detection / segmentation.
Object pose estimation underwater allows an autonomous system to perform tracking and intervention tasks. Nonetheless, underwater target pose estimation is remarkably challenging due to, among many factors, limited visibility, light scattering, cluttered environments, and constantly varying water conditions. An approach is to employ sonar or laser sensing to acquire 3D data, however, the data is not clear and the sensors expensive. For this reason, the community has focused on extracting pose estimates from RGB input. In this work, we propose an approach that leverages 2D object detection to reliably compute 6D pose estimates in different underwater scenarios. We test our proposal with 4 objects with symmetrical shapes and poor texture spanning across 33,920 synthetic and 10 real scenes. All objects and scenes are made available in an open-source dataset that includes annotations for object detection and pose estimation. When benchmarking against similar end-to-end methodologies for 6D object pose estimation, our pipeline provides estimates that are 8% more accurate. We also demonstrate the real world usability of our pose estimation pipeline on an underwater robotic manipulator in a reaching task.
Digital twin is a problem of augmenting real objects with their digital counterparts. It can underpin a wide range of applications in augmented reality (AR), autonomy, and UI/UX. A critical component in a good digital-twin system is real-time, accurate 3D object tracking. Most existing works solve 3D object tracking through the lens of robotic grasping, employ older generations of depth sensors, and measure performance metrics that may not apply to other digital-twin applications such as in AR. In this work, we create a novel RGB-D dataset, called Digital Twin Tracking Dataset (DTTD), to enable further research of the problem and extend potential solutions towards longer ranges and mm localization accuracy. To reduce point cloud noise from the input source, we select the latest Microsoft Azure Kinect as the state-of-the-art time-of-flight (ToF) camera. In total, 103 scenes of 10 common off-the-shelf objects with rich textures are recorded, with each frame annotated with a per-pixel semantic segmentation and ground-truth object poses provided by a commercial motion capturing system. Through extensive experiments with model-level and dataset-level analysis, we demonstrate that DTTD can help researchers develop future object tracking methods and analyze new challenges. The dataset, data generation, annotation, and model evaluation pipeline are made publicly available as open source code at: https://github.com/augcog/DTTDv1.
Autonomous driving needs to rely on high-quality 3D object detection to ensure safe navigation in the world. Uncertainty estimation is an effective tool to provide statistically accurate predictions, while the associated detection uncertainty can be used to implement a more safe navigation protocol or include the user in the loop. In this paper, we propose a Variational Neural Network-based TANet 3D object detector to generate 3D object detections with uncertainty and introduce these detections to an uncertainty-aware AB3DMOT tracker. This is done by applying a linear transformation to the estimated uncertainty matrix, which is subsequently used as a measurement noise for the adopted Kalman filter. We implement two ways to estimate output uncertainty, i.e., internally, by computing the variance of the CNN outputs and then propagating the uncertainty through the post-processing, and externally, by associating the final predictions of different samples and computing the covariance of each predicted box. In experiments, we show that the external uncertainty estimation leads to better results, outperforming both internal uncertainty estimation and classical tracking approaches. Furthermore, we propose a method to initialize the Variational 3D object detector with a pretrained TANet model, which leads to the best performing models.
Knowledge distillation is an effective method for model compression. However, it is still a challenging topic to apply knowledge distillation to detection tasks. There are two key points resulting in poor distillation performance for detection tasks. One is the serious imbalance between foreground and background features, another one is that small object lacks enough feature representation. To solve the above issues, we propose a new distillation method named dual relation knowledge distillation (DRKD), including pixel-wise relation distillation and instance-wise relation distillation. The pixel-wise relation distillation embeds pixel-wise features in the graph space and applies graph convolution to capture the global pixel relation. By distilling the global pixel relation, the student detector can learn the relation between foreground and background features, and avoid the difficulty of distilling features directly for the feature imbalance issue. Besides, we find that instance-wise relation supplements valuable knowledge beyond independent features for small objects. Thus, the instance-wise relation distillation is designed, which calculates the similarity of different instances to obtain a relation matrix. More importantly, a relation filter module is designed to highlight valuable instance relations. The proposed dual relation knowledge distillation is general and can be easily applied for both one-stage and two-stage detectors. Our method achieves state-of-the-art performance, which improves Faster R-CNN based on ResNet50 from 38.4% to 41.6% mAP and improves RetinaNet based on ResNet50 from 37.4% to 40.3% mAP on COCO 2017.
Indoor 3D object detection is an essential task in single image scene understanding, impacting spatial cognition fundamentally in visual reasoning. Existing works on 3D object detection from a single image either pursue this goal through independent predictions of each object or implicitly reason over all possible objects, failing to harness relational geometric information between objects. To address this problem, we propose a dynamic sparse graph pipeline named Explicit3D based on object geometry and semantics features. Taking the efficiency into consideration, we further define a relatedness score and design a novel dynamic pruning algorithm followed by a cluster sampling method for sparse scene graph generation and updating. Furthermore, our Explicit3D introduces homogeneous matrices and defines new relative loss and corner loss to model the spatial difference between target pairs explicitly. Instead of using ground-truth labels as direct supervision, our relative and corner loss are derived from the homogeneous transformation, which renders the model to learn the geometric consistency between objects. The experimental results on the SUN RGB-D dataset demonstrate that our Explicit3D achieves better performance balance than the-state-of-the-art.
This paper addresses the problem of anticipating the next-active-object location in the future, for a given egocentric video clip where the contact might happen, before any action takes place. The problem is considerably hard, as we aim at estimating the position of such objects in a scenario where the observed clip and the action segment are separated by the so-called ``time to contact'' (TTC) segment. Many methods have been proposed to anticipate the action of a person based on previous hand movements and interactions with the surroundings. However, there have been no attempts to investigate the next possible interactable object, and its future location with respect to the first-person's motion and the field-of-view drift during the TTC window. We define this as the task of Anticipating the Next ACTive Object (ANACTO). To this end, we propose a transformer-based self-attention framework to identify and locate the next-active-object in an egocentric clip. We benchmark our method on three datasets: EpicKitchens-100, EGTEA+ and Ego4D. We also provide annotations for the first two datasets. Our approach performs best compared to relevant baseline methods. We also conduct ablation studies to understand the effectiveness of the proposed and baseline methods on varying conditions. Code and ANACTO task annotations will be made available upon paper acceptance.
Object detection in 3D point clouds is a crucial task in a range of computer vision applications including robotics, autonomous cars, and augmented reality. This work addresses the object detection task in 3D point clouds using a highly efficient, surface-biased, feature extraction method (wang2022rbgnet), that also captures contextual cues on multiple levels. We propose a 3D object detector that extracts accurate feature representations of object candidates and leverages self-attention on point patches, object candidates, and on the global scene in 3D scene. Self-attention is proven to be effective in encoding correlation information in 3D point clouds by (xie2020mlcvnet). While other 3D detectors focus on enhancing point cloud feature extraction by selectively obtaining more meaningful local features (wang2022rbgnet) where contextual information is overlooked. To this end, the proposed architecture uses ray-based surface-biased feature extraction and multi-level context encoding to outperform the state-of-the-art 3D object detector. In this work, 3D detection experiments are performed on scenes from the ScanNet dataset whereby the self-attention modules are introduced one after the other to isolate the effect of self-attention at each level.
Advanced Patch Attacks (PAs) on object detection in natural images have pointed out the great safety vulnerability in methods based on deep neural networks. However, little attention has been paid to this topic in Optical Remote Sensing Images (O-RSIs). To this end, we focus on this research, i.e., PAs on object detection in O-RSIs, and propose a more Threatening PA without the scarification of the visual quality, dubbed TPA. Specifically, to address the problem of inconsistency between local and global landscapes in existing patch selection schemes, we propose leveraging the First-Order Difference (FOD) of the objective function before and after masking to select the sub-patches to be attacked. Further, considering the problem of gradient inundation when applying existing coordinate-based loss to PAs directly, we design an IoU-based objective function specific for PAs, dubbed Bounding box Drifting Loss (BDL), which pushes the detected bounding boxes far from the initial ones until there are no intersections between them. Finally, on two widely used benchmarks, i.e., DIOR and DOTA, comprehensive evaluations of our TPA with four typical detectors (Faster R-CNN, FCOS, RetinaNet, and YOLO-v4) witness its remarkable effectiveness. To the best of our knowledge, this is the first attempt to study the PAs on object detection in O-RSIs, and we hope this work can get our readers interested in studying this topic.