The traffic driving environment is a complex and dynamic changing scene in which drivers have to pay close attention to salient and important targets or regions for safe driving. Modeling drivers’ eye movements and attention allocation in traffic driving can also help guiding unmanned intelligent vehicles. However, until now, few studies have modeled drivers’ true fixations and allocations while driving. To this end, we collect an eye tracking dataset from a total of 28 experienced drivers viewing 16 traffic driving videos. Based on the multiple drivers’ attention allocation dataset, we propose a convolutional-deconvolutional neural network (CDNN) to predict the drivers’ eye fixations. The experimental results indicate that the proposed CDNN outperforms the state-of-the-art saliency models and predicts drivers’ attentional locations more accurately. The proposed CDNN can predict the major fixation location and shows excellent detection of secondary important information or regions that cannot be ignored during driving if they exist. Compared with the present object detection models in autonomous and assisted driving systems, our human-like driving model does not detect all of the objects appearing in the driving scenes, but it provides the most relevant regions or targets, which can largely reduce the interference of irrelevant scene information.
Despite the recent advances of deep neural networks, object detection for adverse weather remains challenging due to the poor perception of some sensors in adverse weather. Instead of relying on one single sensor, multimodal fusion has been one promising approach to provide redundant detection information based on multiple sensors. However, most existing multimodal fusion approaches are ineffective in adjusting the focus of different sensors under varying detection environments in dynamic adverse weather conditions. Moreover, it is critical to simultaneously observe local and global information under complex weather conditions, which has been neglected in most early or late-stage multimodal fusion works. In view of these, this paper proposes a Global-Local Attention (GLA) framework to adaptively fuse the multi-modality sensing streams, i.e., camera, gated camera, and lidar data, at two fusion stages. Specifically, GLA integrates an early-stage fusion via a local attention network and a late-stage fusion via a global attention network to deal with both local and global information, which automatically allocates higher weights to the modality with better detection features at the late-stage fusion to cope with the specific weather condition adaptively. Experimental results demonstrate the superior performance of the proposed GLA compared with state-of-the-art fusion approaches under various adverse weather conditions, such as light fog, dense fog, and snow.
Image classification, which classifies images by pre-defined categories, has been the dominant approach to visual representation learning over the last decade. Visual learning through image-text alignment, however, has emerged to show promising performance, especially for zero-shot recognition. We believe that these two learning tasks are complementary, and suggest combining them for better visual learning. We propose a deep fusion method with three adaptations that effectively bridge two learning tasks, rather than shallow fusion through naive multi-task learning. First, we modify the previous common practice in image classification, a linear classifier, with a cosine classifier which shows comparable performance. Second, we convert the image classification problem from learning parametric category classifier weights to learning a text encoder as a meta network to generate category classifier weights. The learnt text encoder is shared between image classification and image-text alignment. Third, we enrich each class name with a description to avoid confusion between classes and make the classification method closer to the image-text alignment. We prove that this deep fusion approach performs better on a variety of visual recognition tasks and setups than the individual learning or shallow fusion approach, from zero-shot/few-shot image classification, such as the Kornblith 12-dataset benchmark, to downstream tasks of action recognition, semantic segmentation, and object detection in fine-tuning and open-vocabulary settings. The code will be available at https://github.com/weiyx16/iCAR.
We propose the task Future Object Detection, in which the goal is to predict the bounding boxes for all visible objects in a future video frame. While this task involves recognizing temporal and kinematic patterns, in addition to the semantic and geometric ones, it only requires annotations in the standard form for individual, single (future) frames, in contrast to expensive full sequence annotations. We propose to tackle this task with an end-to-end method, in which a detection transformer is trained to directly output the future objects. In order to make accurate predictions about the future, it is necessary to capture the dynamics in the scene, both object motion and the movement of the ego-camera. To this end, we extend existing detection transformers in two ways. First, we experiment with three different mechanisms that enable the network to spatiotemporally process multiple frames. Second, we provide ego-motion information to the model in a learnable manner. We show that both of these extensions improve the future object detection performance substantially. Our final approach learns to capture the dynamics and makes predictions on par with an oracle for prediction horizons up to 100 ms, and outperforms all baselines for longer prediction horizons. By visualizing the attention maps, we observe that a form of tracking emerges within the network. Code is available at github.com/atonderski/future-object-detection.
Weakly supervised object detection (WSOD) is a challenging task, in which image-level labels (e.g., categories of the instances in the whole image) are used to train an object detector. Many existing methods follow the standard multiple instance learning (MIL) paradigm and have achieved promising performance. However, the lack of deterministic information leads to part domination and missing instances. To address these issues, this paper focuses on identifying and fully exploiting the deterministic information in WSOD. We discover that negative instances (i.e. absolutely wrong instances), ignored in most of the previous studies, normally contain valuable deterministic information. Based on this observation, we here propose a negative deterministic information (NDI) based method for improving WSOD, namely NDI-WSOD. Specifically, our method consists of two stages: NDI collecting and exploiting. In the collecting stage, we design several processes to identify and distill the NDI from negative instances online. In the exploiting stage, we utilize the extracted NDI to construct a novel negative contrastive learning mechanism and a negative guided instance selection strategy for dealing with the issues of part domination and missing instances, respectively. Experimental results on several public benchmarks including VOC 2007, VOC 2012 and MS COCO show that our method achieves satisfactory performance.
In order to make autonomous driving a reality, artificial neural networks have to work reliably in the open-world. However, the open-world is vast and continuously changing, so it is not technically feasible to collect and annotate training datasets which accurately represent this domain. Therefore, there are always domain gaps between training datasets and the open-world which must be understood. In this work, we investigate the domain gaps between high-resolution and low-resolution LiDAR sensors in object detection networks. Using a unique dataset, which enables us to study sensor resolution domain gaps independent of other effects, we show two distinct domain gaps - an inference domain gap and a training domain gap. The inference domain gap is characterised by a strong dependence on the number of LiDAR points per object, while the training gap shows no such dependence. These fndings show that different approaches are required to close these inference and training domain gaps.
To achieve accurate and robust object detection in the real-world scenario, various forms of images are incorporated, such as color, thermal, and depth. However, multimodal data often suffer from the position shift problem, i.e., the image pair is not strictly aligned, making one object has different positions in different modalities. For the deep learning method, this problem makes it difficult to fuse multimodal features and puzzles the convolutional neural network (CNN) training. In this article, we propose a general multimodal detector named aligned region CNN (AR-CNN) to tackle the position shift problem. First, a region feature (RF) alignment module with adjacent similarity constraint is designed to consistently predict the position shift between two modalities and adaptively align the cross-modal RFs. Second, we propose a novel region of interest (RoI) jitter strategy to improve the robustness to unexpected shift patterns. Third, we present a new multimodal feature fusion method that selects the more reliable feature and suppresses the less useful one via feature reweighting. In addition, by locating bounding boxes in both modalities and building their relationships, we provide novel multimodal labeling named KAIST-Paired. Extensive experiments on 2-D and 3-D object detection, RGB-T, and RGB-D datasets demonstrate the effectiveness and robustness of our method.
Adversarial Propagation (AdvProp) is an effective way to improve recognition models, leveraging adversarial examples. Nonetheless, AdvProp suffers from the extremely slow training speed, mainly because: a) extra forward and backward passes are required for generating adversarial examples; b) both original samples and their adversarial counterparts are used for training (i.e., 2$\times$ data). In this paper, we introduce Fast AdvProp, which aggressively revamps AdvProp's costly training components, rendering the method nearly as cheap as the vanilla training. Specifically, our modifications in Fast AdvProp are guided by the hypothesis that disentangled learning with adversarial examples is the key for performance improvements, while other training recipes (e.g., paired clean and adversarial training samples, multi-step adversarial attackers) could be largely simplified. Our empirical results show that, compared to the vanilla training baseline, Fast AdvProp is able to further model performance on a spectrum of visual benchmarks, without incurring extra training cost. Additionally, our ablations find Fast AdvProp scales better if larger models are used, is compatible with existing data augmentation methods (i.e., Mixup and CutMix), and can be easily adapted to other recognition tasks like object detection. The code is available here: https://github.com/meijieru/fast_advprop.
Background modeling is widely used for intelligent surveillance systems to detect moving targets by subtracting the static background components. Most roadside LiDAR object detection methods filter out foreground points by comparing new data points to pre-trained background references based on descriptive statistics over many frames (e.g., voxel density, number of neighbors, maximum distance). However, these solutions are inefficient under heavy traffic, and parameter values are hard to transfer from one scenario to another. In early studies, the probabilistic background modeling methods widely used for the video-based system were considered unsuitable for roadside LiDAR surveillance systems due to the sparse and unstructured point cloud data. In this paper, the raw LiDAR data were transformed into a structured representation based on the elevation and azimuth value of each LiDAR point. With this high-order tensor representation, we break the barrier to allow efficient high-dimensional multivariate analysis for roadside LiDAR background modeling. The Bayesian Nonparametric (BNP) approach integrates the intensity value and 3D measurements to exploit the measurement data using 3D and intensity info entirely. The proposed method was compared against two state-of-the-art roadside LiDAR background models, computer vision benchmark, and deep learning baselines, evaluated at point, object, and path levels under heavy traffic and challenging weather. This multimodal Weighted Bayesian Gaussian Mixture Model (GMM) can handle dynamic backgrounds with noisy measurements and substantially enhances the infrastructure-based LiDAR object detection, whereby various 3D modeling for smart city applications could be created.
In recent years, supervised learning has been widely used in various tasks of optical remote sensing image understanding, including remote sensing image classification, pixel-wise segmentation, change detection, and object detection. The methods based on supervised learning need a large amount of high-quality training data and their performance highly depends on the quality of the labels. However, in practical remote sensing applications, it is often expensive and time-consuming to obtain large-scale data sets with high-quality labels, which leads to a lack of sufficient supervised information. In some cases, only coarse-grained labels can be obtained, resulting in the lack of exact supervision. In addition, the supervised information obtained manually may be wrong, resulting in a lack of accurate supervision. Therefore, remote sensing image understanding often faces the problems of incomplete, inexact, and inaccurate supervised information, which will affect the breadth and depth of remote sensing applications. In order to solve the above-mentioned problems, researchers have explored various tasks in remote sensing image understanding under weak supervision. This paper summarizes the research progress of weakly supervised learning in the field of remote sensing, including three typical weakly supervised paradigms: 1) Incomplete supervision, where only a subset of training data is labeled; 2) Inexact supervision, where only coarse-grained labels of training data are given; 3) Inaccurate supervision, where the labels given are not always true on the ground.
Mixture of Experts (MoE) is able to scale up vision transformers effectively. However, it requires prohibiting computation resources to train a large MoE transformer. In this paper, we propose Residual Mixture of Experts (RMoE), an efficient training pipeline for MoE vision transformers on downstream tasks, such as segmentation and detection. RMoE achieves comparable results with the upper-bound MoE training, while only introducing minor additional training cost than the lower-bound non-MoE training pipelines. The efficiency is supported by our key observation: the weights of an MoE transformer can be factored into an input-independent core and an input-dependent residual. Compared with the weight core, the weight residual can be efficiently trained with much less computation resource, e.g., finetuning on the downstream data. We show that, compared with the current MoE training pipeline, we get comparable results while saving over 30% training cost. When compared with state-of-the-art non- MoE transformers, such as Swin-T / CvT-13 / Swin-L, we get +1.1 / 0.9 / 1.0 mIoU gain on ADE20K segmentation and +1.4 / 1.6 / 0.6 AP gain on MS-COCO object detection task with less than 3% additional training cost.
This paper addresses the problem of copying an unknown assembly of primitives with known shape and appearance using information extracted from a single photograph by an off-the-shelf procedure for object detection and pose estimation. The proposed algorithm uses a simple combination of physical stability constraints, convex optimization and Monte Carlo tree search to plan assemblies as sequences of pick-and-place operations represented by STRIPS operators. It is efficient and, most importantly, robust to the errors in object detection and pose estimation unavoidable in any real robotic system. The proposed approach is demonstrated with thorough experiments on a UR5 manipulator.
Video prediction aims to predict future frames by modeling the complex spatiotemporal dynamics in videos. However, most of the existing methods only model the temporal information and the spatial information for videos in an independent manner but haven't fully explored the correlations between both terms. In this paper, we propose a SpatioTemporal-Aware Unit (STAU) for video prediction and beyond by exploring the significant spatiotemporal correlations in videos. On the one hand, the motion-aware attention weights are learned from the spatial states to help aggregate the temporal states in the temporal domain. On the other hand, the appearance-aware attention weights are learned from the temporal states to help aggregate the spatial states in the spatial domain. In this way, the temporal information and the spatial information can be greatly aware of each other in both domains, during which, the spatiotemporal receptive field can also be greatly broadened for more reliable spatiotemporal modeling. Experiments are not only conducted on traditional video prediction tasks but also other tasks beyond video prediction, including the early action recognition and object detection tasks. Experimental results show that our STAU can outperform other methods on all tasks in terms of performance and computation efficiency.
Point cloud has drawn more and more research attention as well as real-world applications. However, many of these applications (e.g. autonomous driving and robotic manipulation) are actually based on sequential point clouds (i.e. four dimensions) because the information of the static point cloud data could provide is still limited. Recently, researchers put more and more effort into sequential point clouds. This paper presents an extensive review of the deep learning-based methods for sequential point cloud research including dynamic flow estimation, object detection \& tracking, point cloud segmentation, and point cloud forecasting. This paper further summarizes and compares the quantitative results of the reviewed methods over the public benchmark datasets. Finally, this paper is concluded by discussing the challenges in the current sequential point cloud research and pointing out insightful potential future research directions.
The new generation of state-of-the-art computer vision systems are trained from natural language supervision, ranging from simple object category names to descriptive captions. This form of supervision ensures high generality and usability of the learned visual models, due to the broad concept coverage achieved via large-scale data collection process. Alternatively, we argue that learning with external knowledge is a promising way which leverages a much more structured source of supervision and offers sample efficiency. We propose K-LITE, a simple strategy to leverage external knowledge for building transferable visual systems: In training, it enriches entities in text with WordNet and Wiktionary knowledge, leading to an efficient and scalable approach to learning image representations that uses knowledge about the visual concepts. In evaluation, the text is also augmented with external knowledge and then used to reference learned visual concepts (or describe new ones) to enable zero-shot and few-shot transfer of the pre-trained models. We study the performance of K-LITE on two important computer vision problems, image classification and object detection, benchmarking on 20 and 13 different existing datasets, respectively. The proposed knowledge-augmented models show significant improvement in transfer learning performance over existing methods. Our code is available at https://github.com/microsoft/klite.
The development of autonomous vehicles provides an opportunity to have a complete set of camera sensors capturing the environment around the car. Thus, it is important for object detection and tracking to address new challenges, such as achieving consistent results across views of cameras. To address these challenges, this work presents a new Global Association Graph Model with Link Prediction approach to predict existing tracklets location and link detections with tracklets via cross-attention motion modeling and appearance re-identification. This approach aims at solving issues caused by inconsistent 3D object detection. Moreover, our model exploits to improve the detection accuracy of a standard 3D object detector in the nuScenes detection challenge. The experimental results on the nuScenes dataset demonstrate the benefits of the proposed method to produce SOTA performance on the existing vision-based tracking dataset.
The goal of co-salient object detection (CoSOD) is to discover salient objects that commonly appear in a query group containing two or more relevant images. Therefore, how to effectively extract inter-image correspondence is crucial for the CoSOD task. In this paper, we propose a global-and-local collaborative learning architecture, which includes a global correspondence modeling (GCM) and a local correspondence modeling (LCM) to capture comprehensive inter-image corresponding relationship among different images from the global and local perspectives. Firstly, we treat different images as different time slices and use 3D convolution to integrate all intra features intuitively, which can more fully extract the global group semantics. Secondly, we design a pairwise correlation transformation (PCT) to explore similarity correspondence between pairwise images and combine the multiple local pairwise correspondences to generate the local inter-image relationship. Thirdly, the inter-image relationships of the GCM and LCM are integrated through a global-and-local correspondence aggregation (GLA) module to explore more comprehensive inter-image collaboration cues. Finally, the intra- and inter-features are adaptively integrated by an intra-and-inter weighting fusion (AEWF) module to learn co-saliency features and predict the co-saliency map. The proposed GLNet is evaluated on three prevailing CoSOD benchmark datasets, demonstrating that our model trained on a small dataset (about 3k images) still outperforms eleven state-of-the-art competitors trained on some large datasets (about 8k-200k images).
Traditional object detection answers two questions; "what" (what the object is?) and "where" (where the object is?). "what" part of the object detection can be fine-grained further i.e. "what type", "what shape" and "what material" etc. This results in the shifting of the object detection tasks to the object description paradigm. Describing an object provides additional detail that enables us to understand the characteristics and attributes of the object ("plastic boat" not just boat, "glass bottle" not just bottle). This additional information can implicitly be used to gain insight into unseen objects (e.g. unknown object is "metallic", "has wheels"), which is not possible in traditional object detection. In this paper, we present a new approach to simultaneously detect objects and infer their attributes, we call it Detect and Describe (DaD) framework. DaD is a deep learning-based approach that extends object detection to object attribute prediction as well. We train our model on aPascal train set and evaluate our approach on aPascal test set. We achieve 97.0% in Area Under the Receiver Operating Characteristic Curve (AUC) for object attributes prediction on aPascal test set. We also show qualitative results for object attribute prediction on unseen objects, which demonstrate the effectiveness of our approach for describing unknown objects.
Although deep neural networks enable impressive visual perception performance for autonomous driving, their robustness to varying weather conditions still requires attention. When adapting these models for changed environments, such as different weather conditions, they are prone to forgetting previously learned information. This catastrophic forgetting is typically addressed via incremental learning approaches which usually re-train the model by either keeping a memory bank of training samples or keeping a copy of the entire model or model parameters for each scenario. While these approaches show impressive results, they can be prone to scalability issues and their applicability for autonomous driving in all weather conditions has not been shown. In this paper we propose DISC -- Domain Incremental through Statistical Correction -- a simple online zero-forgetting approach which can incrementally learn new tasks (i.e weather conditions) without requiring re-training or expensive memory banks. The only information we store for each task are the statistical parameters as we categorize each domain by the change in first and second order statistics. Thus, as each task arrives, we simply 'plug and play' the statistical vectors for the corresponding task into the model and it immediately starts to perform well on that task. We show the efficacy of our approach by testing it for object detection in a challenging domain-incremental autonomous driving scenario where we encounter different adverse weather conditions, such as heavy rain, fog, and snow.
We propose a novel generative saliency prediction framework that adopts an informative energy-based model as a prior distribution. The energy-based prior model is defined on the latent space of a saliency generator network that generates the saliency map based on a continuous latent variables and an observed image. Both the parameters of saliency generator and the energy-based prior are jointly trained via Markov chain Monte Carlo-based maximum likelihood estimation, in which the sampling from the intractable posterior and prior distributions of the latent variables are performed by Langevin dynamics. With the generative saliency model, we can obtain a pixel-wise uncertainty map from an image, indicating model confidence in the saliency prediction. Different from existing generative models, which define the prior distribution of the latent variables as a simple isotropic Gaussian distribution, our model uses an energy-based informative prior which can be more expressive in capturing the latent space of the data. With the informative energy-based prior, we extend the Gaussian distribution assumption of generative models to achieve a more representative distribution of the latent space, leading to more reliable uncertainty estimation. We apply the proposed frameworks to both RGB and RGB-D salient object detection tasks with both transformer and convolutional neural network backbones. We further propose an adversarial learning algorithm and a variational inference algorithm as alternatives to train the proposed generative framework. Experimental results show that our generative saliency model with an energy-based prior can achieve not only accurate saliency predictions but also reliable uncertainty maps that are consistent with human perception. Results and code are available at \url{https://github.com/JingZhang617/EBMGSOD}.