3D object detection is receiving increasing attention from both industry and academia thanks to its wide applications in various fields. In this paper, we propose Point-Voxel Region-based Convolution Neural Networks (PV-RCNNs) for 3D object detection on point clouds. First, we propose a novel 3D detector, PV-RCNN, which boosts the 3D detection performance by deeply integrating the feature learning of both point-based set abstraction and voxel-based sparse convolution through two novel steps, i.e., the voxel-to-keypoint scene encoding and the keypoint-to-grid RoI feature abstraction. Second, we propose an advanced framework, PV-RCNN++, for more efficient and accurate 3D object detection. It consists of two major improvements: sectorized proposal-centric sampling for efficiently producing more representative keypoints, and VectorPool aggregation for better aggregating local point features with much less resource consumption. With these two strategies, our PV-RCNN++ is about $3\times$ faster than PV-RCNN, while also achieving better performance. The experiments demonstrate that our proposed PV-RCNN++ framework achieves state-of-the-art 3D detection performance on the large-scale and highly-competitive Waymo Open Dataset with 10 FPS inference speed on the detection range of 150m * 150m.
Attention mechanisms, which enable a neural network to accurately focus on all the relevant elements of the input, have become an essential component to improve the performance of deep neural networks. There are mainly two attention mechanisms widely used in computer vision studies, \textit{spatial attention} and \textit{channel attention}, which aim to capture the pixel-level pairwise relationship and channel dependency, respectively. Although fusing them together may achieve better performance than their individual implementations, it will inevitably increase the computational overhead. In this paper, we propose an efficient Shuffle Attention (SA) module to address this issue, which adopts Shuffle Units to combine two types of attention mechanisms effectively. Specifically, SA first groups channel dimensions into multiple sub-features before processing them in parallel. Then, for each sub-feature, SA utilizes a Shuffle Unit to depict feature dependencies in both spatial and channel dimensions. After that, all sub-features are aggregated and a "channel shuffle" operator is adopted to enable information communication between different sub-features. The proposed SA module is efficient yet effective, e.g., the parameters and computations of SA against the backbone ResNet50 are 300 vs. 25.56M and 2.76e-3 GFLOPs vs. 4.12 GFLOPs, respectively, and the performance boost is more than 1.34% in terms of Top-1 accuracy. Extensive experimental results on common-used benchmarks, including ImageNet-1k for classification, MS COCO for object detection, and instance segmentation, demonstrate that the proposed SA outperforms the current SOTA methods significantly by achieving higher accuracy while having lower model complexity. The code and models are available at https://github.com/wofmanaf/SA-Net.
We train an object detector built from convolutional neural networks to count interference fringes in elliptical antinode regions in frames of high-speed video recordings of transient oscillations in Caribbean steelpan drums illuminated by electronic speckle pattern interferometry (ESPI). The annotations provided by our model aim to contribute to the understanding of time-dependent behavior in such drums by tracking the development of sympathetic vibration modes. The system is trained on a dataset of crowdsourced human-annotated images obtained from the Zooniverse Steelpan Vibrations Project. Due to the small number of human-annotated images and the ambiguity of the annotation task, we also evaluate the model on a large corpus of synthetic images whose properties have been matched to the real images by style transfer using a Generative Adversarial Network. Applying the model to thousands of unlabeled video frames, we measure oscillations consistent with audio recordings of these drum strikes. One unanticipated result is that sympathetic oscillations of higher-octave notes significantly precede the rise in sound intensity of the corresponding second harmonic tones; the mechanism responsible for this remains unidentified. This paper primarily concerns the development of the predictive model; further exploration of the steelpan images and deeper physical insights await its further application.
Existing CNNs-Based RGB-D salient object detection (SOD) networks are all required to be pretrained on the ImageNet to learn the hierarchy features which helps provide a good initialization. However, the collection and annotation of large-scale datasets are time-consuming and expensive. In this paper, we utilize self-supervised representation learning (SSL) to design two pretext tasks: the cross-modal auto-encoder and the depth-contour estimation. Our pretext tasks require only a few and unlabeled RGB-D datasets to perform pretraining, which makes the network capture rich semantic contexts and reduce the gap between two modalities, thereby providing an effective initialization for the downstream task. In addition, for the inherent problem of cross-modal fusion in RGB-D SOD, we propose a consistency-difference aggregation (CDA) module that splits a single feature fusion into multi-path fusion to achieve an adequate perception of consistent and differential information. The CDA module is general and suitable for cross-modal and cross-level feature fusion. Extensive experiments on six benchmark datasets show that our self-supervised pretrained model performs favorably against most state-of-the-art methods pretrained on ImageNet. The source code will be publicly available at \textcolor{red}{\url{https://github.com/Xiaoqi-Zhao-DLUT/SSLSOD}}.
Boundary discontinuity and its inconsistency to the final detection metric have been the bottleneck for rotating detection regression loss design. In this paper, we propose a novel regression loss based on Gaussian Wasserstein distance as a fundamental approach to solve the problem. Specifically, the rotated bounding box is converted to a 2-D Gaussian distribution, which enables to approximate the indifferentiable rotational IoU induced loss by the Gaussian Wasserstein distance (GWD) which can be learned efficiently by gradient back-propagation. GWD can still be informative for learning even there is no overlapping between two rotating bounding boxes which is often the case for small object detection. Thanks to its three unique properties, GWD can also elegantly solve the boundary discontinuity and square-like problem regardless how the bounding box is defined. Experiments on five datasets using different detectors show the effectiveness of our approach. Codes are available at https://github.com/yangxue0827/RotationDetection and https://github.com/open-mmlab/mmrotate.
RGB-D salient object detection (SOD) recently has attracted increasing research interest and many deep learning methods based on encoder-decoder architectures have emerged. However, most existing RGB-D SOD models conduct feature fusion either in the single encoder or the decoder stage, which hardly guarantees sufficient cross-modal fusion ability. In this paper, we make the first attempt in addressing RGB-D SOD through 3D convolutional neural networks. The proposed model, named RD3D, aims at pre-fusion in the encoder stage and in-depth fusion in the decoder stage to effectively promote the full integration of RGB and depth streams. Specifically, RD3D first conducts pre-fusion across RGB and depth modalities through an inflated 3D encoder, and later provides in-depth feature fusion by designing a 3D decoder equipped with rich back-projection paths (RBPP) for leveraging the extensive aggregation ability of 3D convolutions. With such a progressive fusion strategy involving both the encoder and decoder, effective and thorough interaction between the two modalities can be exploited and boost the detection accuracy. Extensive experiments on six widely used benchmark datasets demonstrate that RD3D performs favorably against 14 state-of-the-art RGB-D SOD approaches in terms of four key evaluation metrics. Our code will be made publicly available: https://github.com/PPOLYpubki/RD3D.
In this paper, we describe how the electronic rolling shutter in CMOS image sensors can be exploited using a bright, modulated light source (e.g., an inexpensive, off-the-shelf laser), to inject fine-grained image disruptions. We demonstrate the attack on seven different CMOS cameras, ranging from cheap IoT to semi-professional surveillance cameras, to highlight the wide applicability of the rolling shutter attack. We model the fundamental factors affecting a rolling shutter attack in an uncontrolled setting. We then perform an exhaustive evaluation of the attack's effect on the task of object detection, investigating the effect of attack parameters. We validate our model against empirical data collected on two separate cameras, showing that by simply using information from the camera's datasheet the adversary can accurately predict the injected distortion size and optimize their attack accordingly. We find that an adversary can hide up to 75% of objects perceived by state-of-the-art detectors by selecting appropriate attack parameters. We also investigate the stealthiness of the attack in comparison to a na\"{i}ve camera blinding attack, showing that common image distortion metrics can not detect the attack presence. Therefore, we present a new, accurate and lightweight enhancement to the backbone network of an object detector to recognize rolling shutter attacks. Overall, our results indicate that rolling shutter attacks can substantially reduce the performance and reliability of vision-based intelligent systems.
One of the challenges of computer vision is that it needs to adapt to color deviations in changeable environments. Therefore, minimizing the adverse effects of color deviation on the prediction is one of the main goals of vision task. Current solutions focus on using generative models to augment training data to enhance the invariance of input variation. However, such methods often introduce new noise, which limits the gain from generated data. To this end, this paper proposes a strategy eliminate deviation with deviation, which is named Random Color Dropout (RCD). Our hypothesis is that if there are color deviation between the query image and the gallery image, the retrieval results of some examples will be better after ignoring the color information. Specifically, this strategy balances the weights between color features and color-independent features in the neural network by dropouting partial color information in the training data, so as to overcome the effect of color devitaion. The proposed RCD can be combined with various existing ReID models without changing the learning strategy, and can be applied to other computer vision fields, such as object detection. Experiments on several ReID baselines and three common large-scale datasets such as Market1501, DukeMTMC, and MSMT17 have verified the effectiveness of this method. Experiments on Cross-domain tests have shown that this strategy is significant eliminating the domain gap. Furthermore, in order to understand the working mechanism of RCD, we analyzed the effectiveness of this strategy from the perspective of classification, which reveals that it may be better to utilize many instead of all of color information in visual tasks with strong domain variations.
Although current salient object detection (SOD) works have achieved significant progress, they are limited when it comes to the integrity of the predicted salient regions. We define the concept of integrity at both a micro and macro level. Specifically, at the micro level, the model should highlight all parts that belong to a certain salient object. Meanwhile, at the macro level, the model needs to discover all salient objects in a given image. To facilitate integrity learning for SOD, we design a novel Integrity Cognition Network (ICON), which explores three important components for learning strong integrity features. 1) Unlike existing models, which focus more on feature discriminability, we introduce a diverse feature aggregation (DFA) component to aggregate features with various receptive fields (i.e., kernel shape and context) and increase feature diversity. Such diversity is the foundation for mining the integral salient objects. 2) Based on the DFA features, we introduce an integrity channel enhancement (ICE) component with the goal of enhancing feature channels that highlight the integral salient objects, while suppressing the other distracting ones. 3) After extracting the enhanced features, the part-whole verification (PWV) method is employed to determine whether the part and whole object features have strong agreement. Such part-whole agreements can further improve the micro-level integrity for each salient object. To demonstrate the effectiveness of our ICON, comprehensive experiments are conducted on seven challenging benchmarks. Our ICON outperforms the baseline methods in terms of a wide range of metrics. Notably, our ICON achieves about 10% relative improvement over the previous best model in terms of average false negative ratio (FNR), on six datasets. Codes and results are available at: https://github.com/mczhuge/ICON.
The recently proposed Detection Transformer (DETR) model successfully applies Transformer to objects detection and achieves comparable performance with two-stage object detection frameworks, such as Faster-RCNN. However, DETR suffers from its slow convergence. Training DETR \cite{carion2020end} from scratch needs 500 epochs to achieve a high accuracy. To accelerate its convergence, we propose a simple yet effective scheme for improving the DETR framework, namely Spatially Modulated Co-Attention (SMCA) mechanism. The core idea of SMCA is to conduct regression-aware co-attention in DETR by constraining co-attention responses to be high near initially estimated bounding box locations. Our proposed SMCA increases DETR's convergence speed by replacing the original co-attention mechanism in the decoder while keeping other operations in DETR unchanged. Furthermore, by integrating multi-head and scale-selection attention designs into SMCA, our fully-fledged SMCA can achieve better performance compared to DETR with a dilated convolution-based backbone (45.6 mAP at 108 epochs vs. 43.3 mAP at 500 epochs). We perform extensive ablation studies on COCO dataset to validate the effectiveness of the proposed SMCA.
In recent times, object detection and pose estimation have gained significant attention in the context of robotic vision applications. Both the identification of objects of interest as well as the estimation of their pose remain important capabilities in order for robots to provide effective assistance for numerous robotic applications ranging from household tasks to industrial manipulation. This problem is particularly challenging because of the heterogeneity of objects having different and potentially complex shapes, and the difficulties arising due to background clutter and partial occlusions between objects. As the main contribution of this work, we propose a system that performs real-time object detection and pose estimation, for the purpose of dynamic robot grasping. The robot has been pre-trained to perform a small set of canonical grasps from a few fixed poses for each object. When presented with an unknown object in an arbitrary pose, the proposed approach allows the robot to detect the object identity and its actual pose, and then adapt a canonical grasp in order to be used with the new pose. For training, the system defines a canonical grasp by capturing the relative pose of an object with respect to the gripper attached to the robot's wrist. During testing, once a new pose is detected, a canonical grasp for the object is identified and then dynamically adapted by adjusting the robot arm's joint angles, so that the gripper can grasp the object in its new pose. We conducted experiments using a humanoid PR2 robot and showed that the proposed framework can detect well-textured objects, and provide accurate pose estimation in the presence of tolerable amounts of out-of-plane rotation. The performance is also illustrated by the robot successfully grasping objects from a wide range of arbitrary poses.
Descriptive region features extracted by object detection networks have played an important role in the recent advancements of image captioning. However, they are still criticized for the lack of contextual information and fine-grained details, which in contrast are the merits of traditional grid features. In this paper, we introduce a novel Dual-Level Collaborative Transformer (DLCT) network to realize the complementary advantages of the two features. Concretely, in DLCT, these two features are first processed by a novelDual-way Self Attenion (DWSA) to mine their intrinsic properties, where a Comprehensive Relation Attention component is also introduced to embed the geometric information. In addition, we propose a Locality-Constrained Cross Attention module to address the semantic noises caused by the direct fusion of these two features, where a geometric alignment graph is constructed to accurately align and reinforce region and grid features. To validate our model, we conduct extensive experiments on the highly competitive MS-COCO dataset, and achieve new state-of-the-art performance on both local and online test sets, i.e., 133.8% CIDEr-D on Karpathy split and 135.4% CIDEr on the official split. Code is available at https://github.com/luo3300612/image-captioning-DLCT.
Object detection in optical remote sensing images is an important and challenging task. In recent years, the methods based on convolutional neural networks have made good progress. However, due to the large variation in object scale, aspect ratio, and arbitrary orientation, the detection performance is difficult to be further improved. In this paper, we discuss the role of discriminative features in object detection, and then propose a Critical Feature Capturing Network (CFC-Net) to improve detection accuracy from three aspects: building powerful feature representation, refining preset anchors, and optimizing label assignment. Specifically, we first decouple the classification and regression features, and then construct robust critical features adapted to the respective tasks through the Polarization Attention Module (PAM). With the extracted discriminative regression features, the Rotation Anchor Refinement Module (R-ARM) performs localization refinement on preset horizontal anchors to obtain superior rotation anchors. Next, the Dynamic Anchor Learning (DAL) strategy is given to adaptively select high-quality anchors based on their ability to capture critical features. The proposed framework creates more powerful semantic representations for objects in remote sensing images and achieves high-performance real-time object detection. Experimental results on three remote sensing datasets including HRSC2016, DOTA, and UCAS-AOD show that our method achieves superior detection performance compared with many state-of-the-art approaches. Code and models are available at https://github.com/ming71/CFC-Net.
We propose a new convolution neural network called HarDNet-MSEG for polyp segmentation. It achieves SOTA in both accuracy and inference speed on five popular datasets. For Kvasir-SEG, HarDNet-MSEG delivers 0.904 mean Dice running at 86.7 FPS on a GeForce RTX 2080 Ti GPU. It consists of a backbone and a decoder. The backbone is a low memory traffic CNN called HarDNet68, which has been successfully applied to various CV tasks including image classification, object detection, multi-object tracking and semantic segmentation, etc. The decoder part is inspired by the Cascaded Partial Decoder, known for fast and accurate salient object detection. We have evaluated HarDNet-MSEG using those five popular datasets. The code and all experiment details are available at Github. https://github.com/james128333/HarDNet-MSEG
We propose a semi-automatic bounding box annotation method for visual object tracking by utilizing temporal information with a tracking-by-detection approach. For detection, we use an off-the-shelf object detector which is trained iteratively with the annotations generated by the proposed method, and we perform object detection on each frame independently. We employ Multiple Hypothesis Tracking (MHT) to exploit temporal information and to reduce the number of false-positives which makes it possible to use lower objectness thresholds for detection to increase recall. The tracklets formed by MHT are evaluated by human operators to enlarge the training set. This novel incremental learning approach helps to perform annotation iteratively. The experiments performed on AUTH Multidrone Dataset reveal that the annotation workload can be reduced up to 96% by the proposed approach.
Predictive uncertainty estimation is an essential next step for the reliable deployment of deep object detectors in safety-critical tasks. In this work, we focus on estimating predictive distributions for bounding box regression output with variance networks. We show that in the context of object detection, training variance networks with negative log likelihood (NLL) can lead to high entropy predictive distributions regardless of the correctness of the output mean. We propose to use the energy score as a non-local proper scoring rule and find that when used for training, the energy score leads to better calibrated and lower entropy predictive distributions than NLL. We also address the widespread use of non-proper scoring metrics for evaluating predictive distributions from deep object detectors by proposing an alternate evaluation approach founded on proper scoring rules. Using the proposed evaluation tools, we show that although variance networks can be used to produce high quality predictive distributions, ad-hoc approaches used by seminal object detectors for choosing regression targets during training do not provide wide enough data support for reliable variance learning. We hope that our work helps shift evaluation in probabilistic object detection to better align with predictive uncertainty evaluation in other machine learning domains. Code for all models, evaluation, and datasets is available at: https://github.com/asharakeh/probdet.git.
ImageNet has been arguably the most popular image classification benchmark, but it is also the one with a significant level of label noise. Recent studies have shown that many samples contain multiple classes, despite being assumed to be a single-label benchmark. They have thus proposed to turn ImageNet evaluation into a multi-label task, with exhaustive multi-label annotations per image. However, they have not fixed the training set, presumably because of a formidable annotation cost. We argue that the mismatch between single-label annotations and effectively multi-label images is equally, if not more, problematic in the training setup, where random crops are applied. With the single-label annotations, a random crop of an image may contain an entirely different object from the ground truth, introducing noisy or even incorrect supervision during training. We thus re-label the ImageNet training set with multi-labels. We address the annotation cost barrier by letting a strong image classifier, trained on an extra source of data, generate the multi-labels. We utilize the pixel-wise multi-label predictions before the final pooling layer, in order to exploit the additional location-specific supervision signals. Training on the re-labeled samples results in improved model performances across the board. ResNet-50 attains the top-1 classification accuracy of 78.9% on ImageNet with our localized multi-labels, which can be further boosted to 80.2% with the CutMix regularization. We show that the models trained with localized multi-labels also outperforms the baselines on transfer learning to object detection and instance segmentation tasks, and various robustness benchmarks. The re-labeled ImageNet training set, pre-trained weights, and the source code are available at {https://github.com/naver-ai/relabel_imagenet}.
Mixup linearly interpolates pairs of examples to form new samples, which is easy to implement and has been shown to be effective in image classification tasks. However, there are two drawbacks in mixup: one is that more training epochs are needed to obtain a well-trained model; the other is that mixup requires tuning a hyper-parameter to gain appropriate capacity but that is a difficult task. In this paper, we find that mixup constantly explores the representation space, and inspired by the exploration-exploitation dilemma in reinforcement learning, we propose mixup Without hesitation (mWh), a concise, effective, and easy-to-use training algorithm. We show that mWh strikes a good balance between exploration and exploitation by gradually replacing mixup with basic data augmentation. It can achieve a strong baseline with less training time than original mixup and without searching for optimal hyper-parameter, i.e., mWh acts as mixup without hesitation. mWh can also transfer to CutMix, and gain consistent improvement on other machine learning and computer vision tasks such as object detection. Our code is open-source and available at https://github.com/yuhao318/mwh
Label assignment has been widely studied in general object detection because of its great impact on detectors' performance. However, none of these works focus on label assignment in dense pedestrian detection. In this paper, we propose a simple yet effective assigning strategy called Loss-aware Label Assignment (LLA) to boost the performance of pedestrian detectors in crowd scenarios. LLA first calculates classification (cls) and regression (reg) losses between each anchor and ground-truth (GT) pair. A joint loss is then defined as the weighted summation of cls and reg losses as the assigning indicator. Finally, anchors with top K minimum joint losses for a certain GT box are assigned as its positive anchors. Anchors that are not assigned to any GT box are considered negative. Loss-aware label assignment is based on an observation that anchors with lower joint loss usually contain richer semantic information and thus can better represent their corresponding GT boxes. Experiments on CrowdHuman and CityPersons show that such a simple label assigning strategy can boost MR by 9.53% and 5.47% on two famous one-stage detectors - RetinaNet and FCOS, respectively, demonstrating the effectiveness of LLA.
The main topic of this paper is a brief overview of the field of Artificial Intelligence. The core of this paper is a practical implementation of an algorithm for object detection and tracking. The ability to detect and track fast-moving objects is crucial for various applications of Artificial Intelligence like autonomous driving, ball tracking in sports, robotics or object counting. As part of this paper the Fully Convolutional Neural Network "CueNet" was developed. It detects and tracks the cueball on a labyrinth game robustly and reliably. While CueNet V1 has a single input image, the approach with CueNet V2 was to take three consecutive 240 x 180-pixel images as an input and transform them into a probability heatmap for the cueball's location. The network was tested with a separate video that contained all sorts of distractions to test its robustness. When confronted with our testing data, CueNet V1 predicted the correct cueball location in 99.6% of all frames, while CueNet V2 had 99.8% accuracy.