We present a flexible and high-performance framework, named Pyramid R-CNN, for two-stage 3D object detection from point clouds. Current approaches generally rely on the points or voxels of interest for RoI feature extraction on the second stage, but cannot effectively handle the sparsity and non-uniform distribution of those points, and this may result in failures in detecting objects that are far away. To resolve the problems, we propose a novel second-stage module, named pyramid RoI head, to adaptively learn the features from the sparse points of interest. The pyramid RoI head consists of three key components. Firstly, we propose the RoI-grid Pyramid, which mitigates the sparsity problem by extensively collecting points of interest for each RoI in a pyramid manner. Secondly, we propose RoI-grid Attention, a new operation that can encode richer information from sparse points by incorporating conventional attention-based and graph-based point operators into a unified formulation. Thirdly, we propose the Density-Aware Radius Prediction (DARP) module, which can adapt to different point density levels by dynamically adjusting the focusing range of RoIs. Combining the three components, our pyramid RoI head is robust to the sparse and imbalanced circumstances, and can be applied upon various 3D backbones to consistently boost the detection performance. Extensive experiments show that Pyramid R-CNN outperforms the state-of-the-art 3D detection models by a large margin on both the KITTI dataset and the Waymo Open dataset.
In this paper, we present a toolchain for a comprehensive audio/video analysis by leveraging deep learning based multimodal approach. To this end, different specific tasks of Speech to Text (S2T), Acoustic Scene Classification (ASC), Acoustic Event Detection (AED), Visual Object Detection (VOD), Image Captioning (IC), and Video Captioning (VC) are conducted and integrated into the toolchain. By combining individual tasks and analyzing both audio \& visual data extracted from input video, the toolchain offers various audio/video-based applications: Two general applications of audio/video clustering, comprehensive audio/video summary and a specific application of riot or violent context detection. Furthermore, the toolchain presents a flexible and adaptable architecture that is effective to integrate new models for further audio/video-based applications.
Vision-and-Language Navigation in Continuous Environments (VLN-CE) is a navigation task that requires an agent to follow a language instruction in a realistic environment. The understanding of environments is a crucial part of the VLN-CE task, but existing methods are relatively simple and direct in understanding the environment, without delving into the relationship between language instructions and visual environments. Therefore, we propose a new environment representation in order to solve the above problems. First, we propose an Environment Representation Graph (ERG) through object detection to express the environment in semantic level. This operation enhances the relationship between language and environment. Then, the relational representations of object-object, object-agent in ERG are learned through GCN, so as to obtain a continuous expression about ERG. Sequentially, we combine the ERG expression with object label embeddings to obtain the environment representation. Finally, a new cross-modal attention navigation framework is proposed, incorporating our environment representation and a special loss function dedicated to training ERG. Experimental result shows that our method achieves satisfactory performance in terms of success rate on VLN-CE tasks. Further analysis explains that our method attains better cross-modal matching and strong generalization ability.
We study the problem of symmetry detection of 3D shapes from single-view RGB-D images, where severely missing data renders geometric detection approach infeasible. We propose an end-to-end deep neural network which is able to predict both reflectional and rotational symmetries of 3D objects present in the input RGB-D image. Directly training a deep model for symmetry prediction, however, can quickly run into the issue of overfitting. We adopt a multi-task learning approach. Aside from symmetry axis prediction, our network is also trained to predict symmetry correspondences. In particular, given the 3D points present in the RGB-D image, our network outputs for each 3D point its symmetric counterpart corresponding to a specific predicted symmetry. In addition, our network is able to detect for a given shape multiple symmetries of different types. We also contribute a benchmark of 3D symmetry detection based on single-view RGB-D images. Extensive evaluation on the benchmark demonstrates the strong generalization ability of our method, in terms of high accuracy of both symmetry axis prediction and counterpart estimation. In particular, our method is robust in handling unseen object instances with large variation in shape, multi-symmetry composition, as well as novel object categories.
Based on multiple instance detection networks (MIDN), plenty of works have contributed tremendous efforts to weakly supervised object detection (WSOD). However, most methods neglect the fact that the overwhelming negative instances exist in each image during the training phase, which would mislead the training and make the network fall into local minima. To tackle this problem, an online progressive instance-balanced sampling (OPIS) algorithm based on hard sampling and soft sampling is proposed in this paper. The algorithm includes two modules: a progressive instance balance (PIB) module and a progressive instance reweighting (PIR) module. The PIB module combining random sampling and IoU-balanced sampling progressively mines hard negative instances while balancing positive instances and negative instances. The PIR module further utilizes classifier scores and IoUs of adjacent refinements to reweight the weights of positive instances for making the network focus on positive instances. Extensive experimental results on the PASCAL VOC 2007 and 2012 datasets demonstrate the proposed method can significantly improve the baseline, which is also comparable to many existing state-of-the-art results. In addition, compared to the baseline, the proposed method requires no extra network parameters and the supplementary training overheads are small, which could be easily integrated into other methods based on the instance classifier refinement paradigm.
Accurately detecting objects at long distances remains a critical challenge in 3D object detection when relying solely on LiDAR sensors due to the inherent limitations of data sparsity. To address this issue, we propose the LiDAR-Camera Augmentation Network (LCANet), a novel framework that reconstructs LiDAR point cloud data by fusing 2D image features, which contain rich semantic information, generating additional points to improve detection accuracy. LCANet fuses data from LiDAR sensors and cameras by projecting image features into the 3D space, integrating semantic information into the point cloud data. This fused data is then encoded to produce 3D features that contain both semantic and spatial information, which are further refined to reconstruct final points before bounding box prediction. This fusion effectively compensates for LiDAR's weakness in detecting objects at long distances, which are often represented by sparse points. Additionally, due to the sparsity of many objects in the original dataset, which makes effective supervision for point generation challenging, we employ a point cloud completion network to create a complete point cloud dataset that supervises the generation of dense point clouds in our network. Extensive experiments on the KITTI and Waymo datasets demonstrate that LCANet significantly outperforms existing models, particularly in detecting sparse and distant objects.
Underwater object detection is critical for oceanic research and industrial safety inspections. However, the complex optical environment and the limited resources of underwater equipment pose significant challenges to achieving high accuracy and low power consumption. To address these issues, we propose Spiking Underwater YOLO (SU-YOLO), a Spiking Neural Network (SNN) model. Leveraging the lightweight and energy-efficient properties of SNNs, SU-YOLO incorporates a novel spike-based underwater image denoising method based solely on integer addition, which enhances the quality of feature maps with minimal computational overhead. In addition, we introduce Separated Batch Normalization (SeBN), a technique that normalizes feature maps independently across multiple time steps and is optimized for integration with residual structures to capture the temporal dynamics of SNNs more effectively. The redesigned spiking residual blocks integrate the Cross Stage Partial Network (CSPNet) with the YOLO architecture to mitigate spike degradation and enhance the model's feature extraction capabilities. Experimental results on URPC2019 underwater dataset demonstrate that SU-YOLO achieves mAP of 78.8% with 6.97M parameters and an energy consumption of 2.98 mJ, surpassing mainstream SNN models in both detection accuracy and computational efficiency. These results underscore the potential of SNNs for engineering applications. The code is available in https://github.com/lwxfight/snn-underwater.
In this paper, we present DAT, a Depth-Aware Transformer framework designed for camera-based 3D detection. Our model is based on observing two major issues in existing methods: large depth translation errors and duplicate predictions along depth axes. To mitigate these issues, we propose two key solutions within DAT. To address the first issue, we introduce a Depth-Aware Spatial Cross-Attention (DA-SCA) module that incorporates depth information into spatial cross-attention when lifting image features to 3D space. To address the second issue, we introduce an auxiliary learning task called Depth-aware Negative Suppression loss. First, based on their reference points, we organize features as a Bird's-Eye-View (BEV) feature map. Then, we sample positive and negative features along each object ray that connects an object and a camera and train the model to distinguish between them. The proposed DA-SCA and DNS methods effectively alleviate these two problems. We show that DAT is a versatile method that enhances the performance of all three popular models, BEVFormer, DETR3D, and PETR. Our evaluation on BEVFormer demonstrates that DAT achieves a significant improvement of +2.8 NDS on nuScenes val under the same settings. Moreover, when using pre-trained VoVNet-99 as the backbone, DAT achieves strong results of 60.0 NDS and 51.5 mAP on nuScenes test. Our code will be soon.
Point cloud sequences are commonly used to accurately detect 3D objects in applications such as autonomous driving. Current top-performing multi-frame detectors mostly follow a Detect-and-Fuse framework, which extracts features from each frame of the sequence and fuses them to detect the objects in the current frame. However, this inevitably leads to redundant computation since adjacent frames are highly correlated. In this paper, we propose an efficient Motion-guided Sequential Fusion (MSF) method, which exploits the continuity of object motion to mine useful sequential contexts for object detection in the current frame. We first generate 3D proposals on the current frame and propagate them to preceding frames based on the estimated velocities. The points-of-interest are then pooled from the sequence and encoded as proposal features. A novel Bidirectional Feature Aggregation (BiFA) module is further proposed to facilitate the interactions of proposal features across frames. Besides, we optimize the point cloud pooling by a voxel-based sampling technique so that millions of points can be processed in several milliseconds. The proposed MSF method achieves not only better efficiency than other multi-frame detectors but also leading accuracy, with 83.12% and 78.30% mAP on the LEVEL1 and LEVEL2 test sets of Waymo Open Dataset, respectively. Codes can be found at \url{https://github.com/skyhehe123/MSF}.
퓨샷 객체 검출(Few-shot object detection, FSOD)은 제한된 수의 레이블된 학습 샘플만으로 새로운 인스턴스를 검출하는 것을 목표로 하며, 이는 멸종 위기종 모니터링이나 재난 평가와 같은 수많은 원격 탐사 응용에서 특히 두드러지는 과제이다. 원격 탐사 영상(RSI)을 위한 기존 FSOD 방법들은 유망한 진전을 이루었으나, 인스턴스의 다양성이 제한적이라는 한계에서 여전히 벗어나지 못하고 있다. 이 문제를 해결하기 위해, 본 논문에서는 대규모 자연 이미지로 사전학습된 확산 모델(diffusion model)을 활용하여 다양한 원격 탐사 인스턴스를 합성함으로써 퓨샷 객체 검출기의 성능을 향상시킬 수 있는 새로운 프레임워크를 제안한다. 완전한 원격 탐사 이미지를 직접 합성하는 대신, 먼저 특화된 슬라이스-투-슬라이스(slice-to-slice) 모듈을 통해 인스턴스 수준의 슬라이스를 생성한 다음, 이 슬라이스를 전체 크기의 영상에 삽입하여 향상된 데이터 증강을 수행한다. 확산 모델을 원격 탐사 시나리오에 더욱 적합하게 적응시키기 위해, 원격 탐사 인스턴스 슬라이스를 의미 공간(semantic space)으로 역변환할 수 있는 클래스 비의존적(class-agnostic) 이미지 인버전(inversion) 모듈을 개발한다. 또한 합성된 이미지를 해당 클래스와 의미적으로 정렬하기 위해 대조 손실(contrastive loss)을 도입한다. 실험 결과, 제안한 방법은 여러 데이터셋과 다양한 접근법에 걸쳐 평균 4.4%의 성능 향상을 달성하였다. 어블레이션 실험은 정교하게 설계된 인버전 모듈이 FSOD 방법의 성능을 효과적으로 향상시킬 수 있으며, 의미적 대조 손실이 성능을 추가로 높일 수 있음을 보여준다.
Increasing the semantic understanding and contextual awareness of machine learning models is important for improving robustness and reducing susceptibility to data shifts. In this work, we leverage contextual awareness for the anomaly detection problem. Although graphed-based anomaly detection has been widely studied, context-dependent anomaly detection is an open problem and without much current research. We develop a general framework for converting a context-dependent anomaly detection problem to a link prediction problem, allowing well-established techniques from this domain to be applied. We implement a system based on our framework that utilizes knowledge graph embedding models and demonstrates the ability to detect outliers using context provided by a semantic knowledge base. We show that our method can detect context-dependent anomalies with a high degree of accuracy and show that current object detectors can detect enough classes to provide the needed context for good performance within our example domain.
This paper implements and analyzes multiple networks with the goal of understanding their suitability for edge device applications such as X-ray threat detection. In this study, we use the state-of-the-art YOLO object detection model to solve this task of detecting threats in security baggage screening images. We designed and studied three models - Tiny YOLO, QCFS Tiny YOLO, and SNN Tiny YOLO. We utilize an alternative activation function calculated to have zero expected conversion error with the activation of a spiking activation function in our Tiny YOLOv7 model. This \textit{QCFS} version of the Tiny YOLO replicates the activation function from ultra-low latency and high-efficiency SNN architecture. It achieves state-of-the-art performance on CLCXray, an open-source X-ray threat Detection dataset. In addition, we also study the behavior of a Spiking Tiny YOLO on the same X-ray threat Detection dataset.
Despite the commercial abundance of UAVs, aerial data acquisition remains challenging, and the existing Asia and North America-centric open-source UAV datasets are small-scale or low-resolution and lack diversity in scene contextuality. Additionally, the color content of the scenes, solar-zenith angle, and population density of different geographies influence the data diversity. These two factors conjointly render suboptimal aerial-visual perception of the deep neural network (DNN) models trained primarily on the ground-view data, including the open-world foundational models. To pave the way for a transformative era of aerial detection, we present Multiview Aerial Visual RECognition or MAVREC, a video dataset where we record synchronized scenes from different perspectives -- ground camera and drone-mounted camera. MAVREC consists of around 2.5 hours of industry-standard 2.7K resolution video sequences, more than 0.5 million frames, and 1.1 million annotated bounding boxes. This makes MAVREC the largest ground and aerial-view dataset, and the fourth largest among all drone-based datasets across all modalities and tasks. Through our extensive benchmarking on MAVREC, we recognize that augmenting object detectors with ground-view images from the corresponding geographical location is a superior pre-training strategy for aerial detection. Building on this strategy, we benchmark MAVREC with a curriculum-based semi-supervised object detection approach that leverages labeled (ground and aerial) and unlabeled (only aerial) images to enhance the aerial detection. We publicly release the MAVREC dataset: https://mavrec.github.io.
A key component of understanding hand-object interactions is the ability to identify the active object -- the object that is being manipulated by the human hand. In order to accurately localize the active object, any method must reason using information encoded by each image pixel, such as whether it belongs to the hand, the object, or the background. To leverage each pixel as evidence to determine the bounding box of the active object, we propose a pixel-wise voting function. Our pixel-wise voting function takes an initial bounding box as input and produces an improved bounding box of the active object as output. The voting function is designed so that each pixel inside of the input bounding box votes for an improved bounding box, and the box with the majority vote is selected as the output. We call the collection of bounding boxes generated inside of the voting function, the Relational Box Field, as it characterizes a field of bounding boxes defined in relationship to the current bounding box. While our voting function is able to improve the bounding box of the active object, one round of voting is typically not enough to accurately localize the active object. Therefore, we repeatedly apply the voting function to sequentially improve the location of the bounding box. However, since it is known that repeatedly applying a one-step predictor (i.e., auto-regressive processing with our voting function) can cause a data distribution shift, we mitigate this issue using reinforcement learning (RL). We adopt standard RL to learn the voting function parameters and show that it provides a meaningful improvement over a standard supervised learning approach. We perform experiments on two large-scale datasets: 100DOH and MECCANO, improving AP50 performance by 8% and 30%, respectively, over the state of the art.
Fine-grained wildlife re-identification remains a challenging area in research. Current state-of-the-art approaches apply a detection and re-identification pipeline. We propose a one-stage end-to-end detection and re-identification model that performs identity searching within the latent space. We adopt DINOv2 for robust spatial geometry and MegaDescriptor for wildlife re-identification. We enhance latent queries with prompt re-identification features. A detection decoder queries the scene latent space to establish object boundaries around the target identity. Preliminary findings reflect a competitive mean average precision score of 30.584% compared to the state-of-the-art two stage approach of 44.89%. Qualitative results depict effective bounding and identification of animal identities.
Semantic boundary and edge detection aims at simultaneously detecting object edge pixels in images and assigning class labels to them. Systematic training of predictors for this task requires the labeling of edges in images which is a particularly tedious task. We propose a novel strategy for solving this task, when pixel-level annotations are not available, performing it in an almost zero-shot manner by relying on conventional whole image neural net classifiers that were trained using large bounding boxes. Our method performs the following two steps at test time. Firstly it predicts the class labels by applying the trained whole image network to the test images. Secondly, it computes pixel-wise scores from the obtained predictions by applying backprop gradients as well as recent visualization algorithms such as deconvolution and layer-wise relevance propagation. We show that high pixel-wise scores are indicative for the location of semantic boundaries, which suggests that the semantic boundary problem can be approached without using edge labels during the training phase.
Contextual information can have a substantial impact on the performance of visual tasks such as semantic segmentation, object detection, and geometric estimation. Data stored in Geographic Information Systems (GIS) offers a rich source of contextual information that has been largely untapped by computer vision. We propose to leverage such information for scene understanding by combining GIS resources with large sets of unorganized photographs using Structure from Motion (SfM) techniques. We present a pipeline to quickly generate strong 3D geometric priors from 2D GIS data using SfM models aligned with minimal user input. Given an image resectioned against this model, we generate robust predictions of depth, surface normals, and semantic labels. We show that the precision of the predicted geometry is substantially more accurate other single-image depth estimation methods. We then demonstrate the utility of these contextual constraints for re-scoring pedestrian detections, and use these GIS contextual features alongside object detection score maps to improve a CRF-based semantic segmentation framework, boosting accuracy over baseline models.
Recent deep learning methods for object detection rely on a large amount of bounding box annotations. Collecting these annotations is laborious and costly, yet supervised models do not generalize well when testing on images from a different distribution. Domain adaptation provides a solution by adapting existing labels to the target testing data. However, a large gap between domains could make adaptation a challenging task, which leads to unstable training processes and sub-optimal results. In this paper, we propose to bridge the domain gap with an intermediate domain and progressively solve easier adaptation subtasks. This intermediate domain is constructed by translating the source images to mimic the ones in the target domain. To tackle the domain-shift problem, we adopt adversarial learning to align distributions at the feature level. In addition, a weighted task loss is applied to deal with unbalanced image quality in the intermediate domain. Experimental results show that our method performs favorably against the state-of-the-art method in terms of the performance on the target domain.
We demonstrate a successful navigation and docking control system for the John Deere Tango autonomous mower, using only a single camera as the input. This vision-only system is of interest because it is inexpensive, simple for production, and requires no external sensing. This is in contrast to existing systems that rely on integrated position sensors and global positioning system (GPS) technologies. To produce our system we combined a state-of-the-art object detection architecture, You Only Look Once (YOLO), with a reinforcement learning (RL) architecture, Double Deep QNetworks (Double DQN). The object detection network identifies features on the mower and passes its output to the RL network, providing it with a low-dimensional representation that enables rapid and robust training. Finally, the RL network learns how to navigate the machine to the desired spot in a custom simulation environment. When tested on mower hardware, the system is able to dock with centimeter-level accuracy from arbitrary initial locations and orientations.
For Domain Generalizable Object Detection (DGOD), Disentangled Representation Learning (DRL) helps a lot by explicitly disentangling Domain-Invariant Representations (DIR) from Domain-Specific Representations (DSR). Considering the domain category is an attribute of input data, it should be feasible for networks to fit a specific mapping which projects DSR into feature channels exclusive to domain-specific information, and thus much cleaner disentanglement of DIR from DSR can be achieved simply on channel dimension. Inspired by this idea, we propose a novel DRL method for DGOD, which is termed Gated Domain-Invariant Feature Disentanglement (GDIFD). In GDIFD, a Channel Gate Module (CGM) learns to output channel gate signals close to either 0 or 1, which can mask out the channels exclusive to domain-specific information helpful for domain recognition. With the proposed GDIFD, the backbone in our framework can fit the desired mapping easily, which enables the channel-wise disentanglement. In experiments, we demonstrate that our approach is highly effective and achieves state-of-the-art DGOD performance.