Monocular 3D detection has drawn much attention from the community due to its low cost and setup simplicity. It takes an RGB image as input and predicts 3D boxes in the 3D space. The most challenging sub-task lies in the instance depth estimation. Previous works usually use a direct estimation method. However, in this paper we point out that the instance depth on the RGB image is non-intuitive. It is coupled by visual depth clues and instance attribute clues, making it hard to be directly learned in the network. Therefore, we propose to reformulate the instance depth to the combination of the instance visual surface depth (visual depth) and the instance attribute depth (attribute depth). The visual depth is related to objects' appearances and positions on the image. By contrast, the attribute depth relies on objects' inherent attributes, which are invariant to the object affine transformation on the image. Correspondingly, we decouple the 3D location uncertainty into visual depth uncertainty and attribute depth uncertainty. By combining different types of depths and associated uncertainties, we can obtain the final instance depth. Furthermore, data augmentation in monocular 3D detection is usually limited due to the physical nature, hindering the boost of performance. Based on the proposed instance depth disentanglement strategy, we can alleviate this problem. Evaluated on KITTI, our method achieves new state-of-the-art results, and extensive ablation studies validate the effectiveness of each component in our method. The codes are released at https://github.com/SPengLiang/DID-M3D.
The ability to process environment maps across multiple sessions is critical for robots operating over extended periods of time. Specifically, it is desirable for autonomous agents to detect changes amongst maps of different sessions so as to gain a conflict-free understanding of the current environment. In this paper, we look into the problem of change detection based on a novel map representation, dubbed Plane Signed Distance Fields (PlaneSDF), where dense maps are represented as a collection of planes and their associated geometric components in SDF volumes. Given point clouds of the source and target scenes, we propose a three-step PlaneSDF-based change detection approach: (1) PlaneSDF volumes are instantiated within each scene and registered across scenes using plane poses; 2D height maps and object maps are extracted per volume via height projection and connected component analysis. (2) Height maps are compared and intersected with the object map to produce a 2D change location mask for changed object candidates in the source scene. (3) 3D geometric validation is performed using SDF-derived features per object candidate for change mask refinement. We evaluate our approach on both synthetic and real-world datasets and demonstrate its effectiveness via the task of changed object detection. Supplementary video: https://youtu.be/oh-MQPWTwZI
RGB-D salient object detection (SOD) has been in the spotlight recently because it is an important preprocessing operation for various vision tasks. However, despite advances in deep learning-based methods, RGB-D SOD is still challenging due to the large domain gap between an RGB image and the depth map and low-quality depth maps. To solve this problem, we propose a novel superpixel prototype sampling network (SPSN) architecture. The proposed model splits the input RGB image and depth map into component superpixels to generate component prototypes. We design a prototype sampling network so that the network only samples prototypes corresponding to salient objects. In addition, we propose a reliance selection module to recognize the quality of each RGB and depth feature map and adaptively weight them in proportion to their reliability. The proposed method makes the model robust to inconsistencies between RGB images and depth maps and eliminates the influence of non-salient objects. Our method is evaluated on five popular datasets, achieving state-of-the-art performance. We prove the effectiveness of the proposed method through comparative experiments.
Vehicle-to-Everything (V2X) network has enabled collaborative perception in autonomous driving, which is a promising solution to the fundamental defect of stand-alone intelligence including blind zones and long-range perception. However, the lack of datasets has severely blocked the development of collaborative perception algorithms. In this work, we release DOLPHINS: Dataset for cOllaborative Perception enabled Harmonious and INterconnected Self-driving, as a new simulated large-scale various-scenario multi-view multi-modality autonomous driving dataset, which provides a ground-breaking benchmark platform for interconnected autonomous driving. DOLPHINS outperforms current datasets in six dimensions: temporally-aligned images and point clouds from both vehicles and Road Side Units (RSUs) enabling both Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure (V2I) based collaborative perception; 6 typical scenarios with dynamic weather conditions make the most various interconnected autonomous driving dataset; meticulously selected viewpoints providing full coverage of the key areas and every object; 42376 frames and 292549 objects, as well as the corresponding 3D annotations, geo-positions, and calibrations, compose the largest dataset for collaborative perception; Full-HD images and 64-line LiDARs construct high-resolution data with sufficient details; well-organized APIs and open-source codes ensure the extensibility of DOLPHINS. We also construct a benchmark of 2D detection, 3D detection, and multi-view collaborative perception tasks on DOLPHINS. The experiment results show that the raw-level fusion scheme through V2X communication can help to improve the precision as well as to reduce the necessity of expensive LiDAR equipment on vehicles when RSUs exist, which may accelerate the popularity of interconnected self-driving vehicles. DOLPHINS is now available on https://dolphins-dataset.net/.
Standard approaches for adversarial patch generation lead to noisy conspicuous patterns, which are easily recognizable by humans. Recent research has proposed several approaches to generate naturalistic patches using generative adversarial networks (GANs), yet only a few of them were evaluated on the object detection use case. Moreover, the state of the art mostly focuses on suppressing a single large bounding box in input by overlapping it with the patch directly. Suppressing objects near the patch is a different, more complex task. In this work, we have evaluated the existing approaches to generate inconspicuous patches. We have adapted methods, originally developed for different computer vision tasks, to the object detection use case with YOLOv3 and the COCO dataset. We have evaluated two approaches to generate naturalistic patches: by incorporating patch generation into the GAN training process and by using the pretrained GAN. For both cases, we have assessed a trade-off between performance and naturalistic patch appearance. Our experiments have shown, that using a pre-trained GAN helps to gain realistic-looking patches while preserving the performance similar to conventional adversarial patches.
Video salient object detection models trained on pixel-wise dense annotation have achieved excellent performance, yet obtaining pixel-by-pixel annotated datasets is laborious. Several works attempt to use scribble annotations to mitigate this problem, but point supervision as a more labor-saving annotation method (even the most labor-saving method among manual annotation methods for dense prediction), has not been explored. In this paper, we propose a strong baseline model based on point supervision. To infer saliency maps with temporal information, we mine inter-frame complementary information from short-term and long-term perspectives, respectively. Specifically, we propose a hybrid token attention module, which mixes optical flow and image information from orthogonal directions, adaptively highlighting critical optical flow information (channel dimension) and critical token information (spatial dimension). To exploit long-term cues, we develop the Long-term Cross-Frame Attention module (LCFA), which assists the current frame in inferring salient objects based on multi-frame tokens. Furthermore, we label two point-supervised datasets, P-DAVIS and P-DAVSOD, by relabeling the DAVIS and the DAVSOD dataset. Experiments on the six benchmark datasets illustrate our method outperforms the previous state-of-the-art weakly supervised methods and even is comparable with some fully supervised approaches. Source code and datasets are available.
Recent advances in vision transformers (ViTs) have achieved great performance in visual recognition tasks. Convolutional neural networks (CNNs) exploit spatial inductive bias to learn visual representations, but these networks are spatially local. ViTs can learn global representations with their self-attention mechanism, but they are usually heavy-weight and unsuitable for mobile devices. In this paper, we propose cross feature attention (XFA) to bring down computation cost for transformers, and combine efficient mobile CNNs to form a novel efficient light-weight CNN-ViT hybrid model, XFormer, which can serve as a general-purpose backbone to learn both global and local representation. Experimental results show that XFormer outperforms numerous CNN and ViT-based models across different tasks and datasets. On ImageNet1K dataset, XFormer achieves top-1 accuracy of 78.5% with 5.5 million parameters, which is 2.2% and 6.3% more accurate than EfficientNet-B0 (CNN-based) and DeiT (ViT-based) for similar number of parameters. Our model also performs well when transferring to object detection and semantic segmentation tasks. On MS COCO dataset, XFormer exceeds MobileNetV2 by 10.5 AP (22.7 -> 33.2 AP) in YOLOv3 framework with only 6.3M parameters and 3.8G FLOPs. On Cityscapes dataset, with only a simple all-MLP decoder, XFormer achieves mIoU of 78.5 and FPS of 15.3, surpassing state-of-the-art lightweight segmentation networks.
We propose bootstrapped masked autoencoders (BootMAE), a new approach for vision BERT pretraining. BootMAE improves the original masked autoencoders (MAE) with two core designs: 1) momentum encoder that provides online feature as extra BERT prediction targets; 2) target-aware decoder that tries to reduce the pressure on the encoder to memorize target-specific information in BERT pretraining. The first design is motivated by the observation that using a pretrained MAE to extract the features as the BERT prediction target for masked tokens can achieve better pretraining performance. Therefore, we add a momentum encoder in parallel with the original MAE encoder, which bootstraps the pretraining performance by using its own representation as the BERT prediction target. In the second design, we introduce target-specific information (e.g., pixel values of unmasked patches) from the encoder directly to the decoder to reduce the pressure on the encoder of memorizing the target-specific information. Thus, the encoder focuses on semantic modeling, which is the goal of BERT pretraining, and does not need to waste its capacity in memorizing the information of unmasked tokens related to the prediction target. Through extensive experiments, our BootMAE achieves $84.2\%$ Top-1 accuracy on ImageNet-1K with ViT-B backbone, outperforming MAE by $+0.8\%$ under the same pre-training epochs. BootMAE also gets $+1.0$ mIoU improvements on semantic segmentation on ADE20K and $+1.3$ box AP, $+1.4$ mask AP improvement on object detection and segmentation on COCO dataset. Code is released at https://github.com/LightDXY/BootMAE.
We present ObjectBox, a novel single-stage anchor-free and highly generalizable object detection approach. As opposed to both existing anchor-based and anchor-free detectors, which are more biased toward specific object scales in their label assignments, we use only object center locations as positive samples and treat all objects equally in different feature levels regardless of the objects' sizes or shapes. Specifically, our label assignment strategy considers the object center locations as shape- and size-agnostic anchors in an anchor-free fashion, and allows learning to occur at all scales for every object. To support this, we define new regression targets as the distances from two corners of the center cell location to the four sides of the bounding box. Moreover, to handle scale-variant objects, we propose a tailored IoU loss to deal with boxes with different sizes. As a result, our proposed object detector does not need any dataset-dependent hyperparameters to be tuned across datasets. We evaluate our method on MS-COCO 2017 and PASCAL VOC 2012 datasets, and compare our results to state-of-the-art methods. We observe that ObjectBox performs favorably in comparison to prior works. Furthermore, we perform rigorous ablation experiments to evaluate different components of our method. Our code is available at: https://github.com/MohsenZand/ObjectBox.
Most state-of-the-art instance-level human parsing models adopt two-stage anchor-based detectors and, therefore, cannot avoid the heuristic anchor box design and the lack of analysis on a pixel level. To address these two issues, we have designed an instance-level human parsing network which is anchor-free and solvable on a pixel level. It consists of two simple sub-networks: an anchor-free detection head for bounding box predictions and an edge-guided parsing head for human segmentation. The anchor-free detector head inherits the pixel-like merits and effectively avoids the sensitivity of hyper-parameters as proved in object detection applications. By introducing the part-aware boundary clue, the edge-guided parsing head is capable to distinguish adjacent human parts from among each other up to 58 parts in a single human instance, even overlapping instances. Meanwhile, a refinement head integrating box-level score and part-level parsing quality is exploited to improve the quality of the parsing results. Experiments on two multiple human parsing datasets (i.e., CIHP and LV-MHP-v2.0) and one video instance-level human parsing dataset (i.e., VIP) show that our method achieves the best global-level and instance-level performance over state-of-the-art one-stage top-down alternatives.
Object detection using single point supervision has received increasing attention over the years. However, the performance gap between point supervised object detection (PSOD) and bounding box supervised detection remains large. In this paper, we attribute such a large performance gap to the failure of generating high-quality proposal bags which are crucial for multiple instance learning (MIL). To address this problem, we introduce a lightweight alternative to the off-the-shelf proposal (OTSP) method and thereby create the Point-to-Box Network (P2BNet), which can construct an inter-objects balanced proposal bag by generating proposals in an anchor-like way. By fully investigating the accurate position information, P2BNet further constructs an instance-level bag, avoiding the mixture of multiple objects. Finally, a coarse-to-fine policy in a cascade fashion is utilized to improve the IoU between proposals and ground-truth (GT). Benefiting from these strategies, P2BNet is able to produce high-quality instance-level bags for object detection. P2BNet improves the mean average precision (AP) by more than 50% relative to the previous best PSOD method on the MS COCO dataset. It also demonstrates the great potential to bridge the performance gap between point supervised and bounding-box supervised detectors. The code will be released at github.com/ucas-vg/P2BNet.
Existing automatic data augmentation (DA) methods either ignore updating DA's parameters according to the target model's state during training or adopt update strategies that are not effective enough. In this work, we design a novel data augmentation strategy called "Universal Adaptive Data Augmentation" (UADA). Different from existing methods, UADA would adaptively update DA's parameters according to the target model's gradient information during training: given a pre-defined set of DA operations, we randomly decide types and magnitudes of DA operations for every data batch during training, and adaptively update DA's parameters along the gradient direction of the loss concerning DA's parameters. In this way, UADA can increase the training loss of the target networks, and the target networks would learn features from harder samples to improve the generalization. Moreover, UADA is very general and can be utilized in numerous tasks, e.g., image classification, semantic segmentation and object detection. Extensive experiments with various models are conducted on CIFAR-10, CIFAR-100, ImageNet, tiny-ImageNet, Cityscapes, and VOC07+12 to prove the significant performance improvements brought by UADA.
Current object detectors typically have a feature pyramid (FP) module for multi-level feature fusion (MFF) which aims to mitigate the gap between features from different levels and form a comprehensive object representation to achieve better detection performance. However, they usually require heavy cross-level connections or iterative refinement to obtain better MFF result, making them complicated in structure and inefficient in computation. To address these issues, we propose a novel and efficient context modeling mechanism that can help existing FPs deliver better MFF results while reducing the computational costs effectively. In particular, we introduce a novel insight that comprehensive contexts can be decomposed and condensed into two types of representations for higher efficiency. The two representations include a locally concentrated representation and a globally summarized representation, where the former focuses on extracting context cues from nearby areas while the latter extracts key representations of the whole image scene as global context cues. By collecting the condensed contexts, we employ a Transformer decoder to investigate the relations between them and each local feature from the FP and then refine the MFF results accordingly. As a result, we obtain a simple and light-weight Transformer-based Context Condensation (TCC) module, which can boost various FPs and lower their computational costs simultaneously. Extensive experimental results on the challenging MS COCO dataset show that TCC is compatible to four representative FPs and consistently improves their detection accuracy by up to 7.8 % in terms of average precision and reduce their complexities by up to around 20% in terms of GFLOPs, helping them achieve state-of-the-art performance more efficiently. Code will be released.
Moving Object Detection (MOD) is a fundamental step for many computer vision applications. MOD becomes very challenging when a video sequence captured from a static or moving camera suffers from the challenges: camouflage, shadow, dynamic backgrounds, and lighting variations, to name a few. Deep learning methods have been successfully applied to address MOD with competitive performance. However, in order to handle the overfitting problem, deep learning methods require a large amount of labeled data which is a laborious task as exhaustive annotations are always not available. Moreover, some MOD deep learning methods show performance degradation in the presence of unseen video sequences because the testing and training splits of the same sequences are involved during the network learning process. In this work, we pose the problem of MOD as a node classification problem using Graph Convolutional Neural Networks (GCNNs). Our algorithm, dubbed as GraphMOD-Net, encompasses instance segmentation, background initialization, feature extraction, and graph construction. GraphMOD-Net is tested on unseen videos and outperforms state-of-the-art methods in unsupervised, semi-supervised, and supervised learning in several challenges of the Change Detection 2014 (CDNet2014) and UCSD background subtraction datasets.
This work aims at advancing temporal action detection (TAD) using an encoder-decoder framework with action queries, similar to DETR, which has shown great success in object detection. However, the framework suffers from several problems if directly applied to TAD: the insufficient exploration of inter-query relation in the decoder, the inadequate classification training due to a limited number of training samples, and the unreliable classification scores at inference. To this end, we first propose a relational attention mechanism in the decoder, which guides the attention among queries based on their relations. Moreover, we propose two losses to facilitate and stabilize the training of action classification. Lastly, we propose to predict the localization quality of each action query at inference in order to distinguish high-quality queries. The proposed method, named ReAct, achieves the state-of-the-art performance on THUMOS14, with much lower computational costs than previous methods. Besides, extensive ablation studies are conducted to verify the effectiveness of each proposed component. The code is available at https://github.com/sssste/React.
Advances in deep learning have resulted in steady progress in computer vision with improved accuracy on tasks such as object detection and semantic segmentation. Nevertheless, deep neural networks are vulnerable to adversarial attacks, thus presenting a challenge in reliable deployment. Two of the prominent tasks in 3D scene-understanding for robotics and advanced drive assistance systems are monocular depth and pose estimation, often learned together in an unsupervised manner. While studies evaluating the impact of adversarial attacks on monocular depth estimation exist, a systematic demonstration and analysis of adversarial perturbations against pose estimation are lacking. We show how additive imperceptible perturbations can not only change predictions to increase the trajectory drift but also catastrophically alter its geometry. We also study the relation between adversarial perturbations targeting monocular depth and pose estimation networks, as well as the transferability of perturbations to other networks with different architectures and losses. Our experiments show how the generated perturbations lead to notable errors in relative rotation and translation predictions and elucidate vulnerabilities of the networks.
Object detection, as a fundamental computer vision task, has achieved a remarkable progress with the emergence of deep neural networks. Nevertheless, few works explore the adversarial robustness of object detectors to resist adversarial attacks for practical applications in various real-world scenarios. Detectors have been greatly challenged by unnoticeable perturbation, with sharp performance drop on clean images and extremely poor performance on adversarial images. In this work, we empirically explore the model training for adversarial robustness in object detection, which greatly attributes to the conflict between learning clean images and adversarial images. To mitigate this issue, we propose a Robust Detector (RobustDet) based on adversarially-aware convolution to disentangle gradients for model learning on clean and adversarial images. RobustDet also employs the Adversarial Image Discriminator (AID) and Consistent Features with Reconstruction (CFR) to ensure a reliable robustness. Extensive experiments on PASCAL VOC and MS-COCO demonstrate that our model effectively disentangles gradients and significantly enhances the detection robustness with maintaining the detection ability on clean images.
Automatic pseudo-labeling is a powerful tool to tap into large amounts of sequential unlabeled data. It is specially appealing in safety-critical applications of autonomous driving, where performance requirements are extreme, datasets are large, and manual labeling is very challenging. We propose to leverage sequences of point clouds to boost the pseudolabeling technique in a teacher-student setup via training multiple teachers, each with access to different temporal information. This set of teachers, dubbed Concordance, provides higher quality pseudo-labels for student training than standard methods. The output of multiple teachers is combined via a novel pseudo label confidence-guided criterion. Our experimental evaluation focuses on the 3D point cloud domain and urban driving scenarios. We show the performance of our method applied to 3D semantic segmentation and 3D object detection on three benchmark datasets. Our approach, which uses only 20% manual labels, outperforms some fully supervised methods. A notable performance boost is achieved for classes rarely appearing in training data.
Given an image of a white shoe drawn on a blackboard, how are the white pixels deemed (say by human minds) to be informative for recognizing the shoe without any labeling information on the pixels? Here we investigate such a ``white shoe'' recognition problem from the perspective of tensor network (TN) machine learning and quantum entanglement. Utilizing a generative TN that captures the probability distribution of the features as quantum amplitudes, we propose an unsupervised recognition scheme of informative features with the variations of entanglement entropy (EE) caused by designed measurements. In this way, a given sample, where the values of its features are statistically meaningless, is mapped to the variations of EE that statistically characterize the gain of information. We show that the EE variations identify the features that are critical to recognize this specific sample, and the EE itself reveals the information distribution of the probabilities represented by the TN model. The signs of the variations further reveal the entanglement structures among the features. We test the validity of our scheme on a toy dataset of strip images, the MNIST dataset of hand-drawn digits, the fashion-MNIST dataset of the pictures of fashion articles, and the images of brain cells. Our scheme opens the avenue to the quantum-inspired and interpreted unsupervised learning, which can be applied to, e.g., image segmentation and object detection.
Deep Learning-based Unsupervised Salient Object Detection (USOD) mainly relies on the noisy saliency pseudo labels that have been generated from traditional handcraft methods or pre-trained networks. To cope with the noisy labels problem, a class of methods focus on only easy samples with reliable labels but ignore valuable knowledge in hard samples. In this paper, we propose a novel USOD method to mine rich and accurate saliency knowledge from both easy and hard samples. First, we propose a Confidence-aware Saliency Distilling (CSD) strategy that scores samples conditioned on samples' confidences, which guides the model to distill saliency knowledge from easy samples to hard samples progressively. Second, we propose a Boundary-aware Texture Matching (BTM) strategy to refine the boundaries of noisy labels by matching the textures around the predicted boundary. Extensive experiments on RGB, RGB-D, RGB-T, and video SOD benchmarks prove that our method achieves state-of-the-art USOD performance.