Single frame data contains finite information which limits the performance of the existing vision-based multi-camera 3D object detection paradigms. For fundamentally pushing the performance boundary in this area, BEVDet4D is proposed to lift the scalable BEVDet paradigm from the spatial-only 3D space to the spatial-temporal 4D space. We upgrade the framework with a few modifications just for fusing the feature from the previous frame with the corresponding one in the current frame. In this way, with negligible extra computing budget, we enable the algorithm to access the temporal cues by querying and comparing the two candidate features. Beyond this, we also simplify the velocity learning task by removing the factors of ego-motion and time, which equips BEVDet4D with robust generalization performance and reduces the velocity error by 52.8%. This makes vision-based methods, for the first time, become comparable with those relied on LiDAR or radar in this aspect. On challenge benchmark nuScenes, we report a new record of 51.5% NDS with the high-performance configuration dubbed BEVDet4D-Base, which surpasses the previous leading method BEVDet by +4.3% NDS.
Dataset condensation aims at reducing the network training effort through condensing a cumbersome training set into a compact synthetic one. State-of-the-art approaches largely rely on learning the synthetic data by matching the gradients between the real and synthetic data batches. Despite the intuitive motivation and promising results, such gradient-based methods, by nature, easily overfit to a biased set of samples that produce dominant gradients, and thus lack global supervision of data distribution. In this paper, we propose a novel scheme to Condense dataset by Aligning FEatures (CAFE), which explicitly attempts to preserve the real-feature distribution as well as the discriminant power of the resulting synthetic set, lending itself to strong generalization capability to various architectures. At the heart of our approach is an effective strategy to align features from the real and synthetic data across various scales, while accounting for the classification of real samples. Our scheme is further backed up by a novel dynamic bi-level optimization, which adaptively adjusts parameter updates to prevent over-/under-fitting. We validate the proposed CAFE across various datasets, and demonstrate that it generally outperforms the state of the art: on the SVHN dataset, for example, the performance gain is up to 11%. Extensive experiments and analyses verify the effectiveness and necessity of proposed designs.
Bike sharing is an increasingly popular part of urban transportation systems. Accurate demand prediction is the key to support timely re-balancing and ensure service efficiency. Most existing models of bike-sharing demand prediction are solely based on its own historical demand variation, essentially regarding bike sharing as a closed system and neglecting the interaction between different transport modes. This is particularly important because bike sharing is often used to complement travel through other modes (e.g., public transit). Despite some recent efforts, there is no existing method capable of leveraging spatiotemporal information from multiple modes with heterogeneous spatial units. To address this research gap, this study proposes a graph-based deep learning approach for bike sharing demand prediction (B-MRGNN) with multimodal historical data as input. The spatial dependencies across modes are encoded with multiple intra- and inter-modal graphs. A multi-relational graph neural network (MRGNN) is introduced to capture correlations between spatial units across modes, such as bike sharing stations, subway stations, or ride-hailing zones. Extensive experiments are conducted using real-world bike sharing, subway and ride-hailing data from New York City, and the results demonstrate the superior performance of our proposed approach compared to existing methods.
Autonomous driving perceives the surrounding environment for decision making, which is one of the most complicated scenes for visual perception. The great power of paradigm innovation in solving the 2D object detection task inspires us to seek an elegant, feasible, and scalable paradigm for pushing the performance boundary in this area. To this end, we contribute the BEVDet paradigm in this paper. BEVDet is developed by following the principle of detecting the 3D objects in Bird-Eye-View (BEV), where route planning can be handily performed. In this paradigm, four kinds of modules are conducted in succession with different roles: an image-view encoder for encoding feature in image view, a view transformer for feature transformation from image view to BEV, a BEV encoder for further encoding feature in BEV, and a task-specific head for predicting the targets in BEV. We merely reuse the existing modules for constructing BEVDet and make it feasible for multi-camera 3D object detection by constructing an exclusive data augmentation strategy. The proposed paradigm works well in multi-camera 3D object detection and offers a good trade-off between computing budget and performance. BEVDet with 704x256 (1/8 of the competitors) image size scores 29.4% mAP and 38.4% NDS on the nuScenes val set, which is comparable with FCOS3D (i.e., 2008.2 GFLOPs, 1.7 FPS, 29.5% mAP and 37.2% NDS), while requires merely 12% computing budget of 239.4 GFLOPs and runs 4.3 times faster. Scaling up the input size to 1408x512, BEVDet scores 34.9% mAP, and 41.7% NDS, which requires just 601.4 GFLOPs and significantly suppresses FCOS3D by 5.4% mAP and 4.5% NDS. The superior performance of BEVDet tells the magic of paradigm innovation.
Dynamic demand prediction is crucial for the efficient operation and management of urban transportation systems. Extensive research has been conducted on single-mode demand prediction, ignoring the fact that the demands for different transportation modes can be correlated with each other. Despite some recent efforts, existing approaches to multimodal demand prediction are generally not flexible enough to account for multiplex networks with diverse spatial units and heterogeneous spatiotemporal correlations across different modes. To tackle these issues, this study proposes a multi-relational spatiotemporal graph neural network (ST-MRGNN) for multimodal demand prediction. Specifically, the spatial dependencies across modes are encoded with multiple intra- and inter-modal relation graphs. A multi-relational graph neural network (MRGNN) is introduced to capture cross-mode heterogeneous spatial dependencies, consisting of generalized graph convolution networks to learn the message passing mechanisms within relation graphs and an attention-based aggregation module to summarize different relations. We further integrate MRGNNs with temporal gated convolution layers to jointly model heterogeneous spatiotemporal correlations. Extensive experiments are conducted using real-world subway and ride-hailing datasets from New York City, and the results verify the improved performance of our proposed approach over existing methods across modes. The improvement is particularly large for demand-sparse locations. Further analysis of the attention mechanisms of ST-MRGNN also demonstrates its good interpretability for understanding cross-mode interactions.
Recent progress has shown that large-scale pre-training using contrastive image-text pairs can be a promising alternative for high-quality visual representation learning from natural language supervision. Benefiting from a broader source of supervision, this new paradigm exhibits impressive transferability to downstream classification tasks and datasets. However, the problem of transferring the knowledge learned from image-text pairs to more complex dense prediction tasks has barely been visited. In this work, we present a new framework for dense prediction by implicitly and explicitly leveraging the pre-trained knowledge from CLIP. Specifically, we convert the original image-text matching problem in CLIP to a pixel-text matching problem and use the pixel-text score maps to guide the learning of dense prediction models. By further using the contextual information from the image to prompt the language model, we are able to facilitate our model to better exploit the pre-trained knowledge. Our method is model-agnostic, which can be applied to arbitrary dense prediction systems and various pre-trained visual backbones including both CLIP models and ImageNet pre-trained models. Extensive experiments demonstrate the superior performance of our methods on semantic segmentation, object detection, and instance segmentation tasks. Code is available at https://github.com/raoyongming/DenseCLIP
Our team are developing a new online test that analyses hand movement features associated with ageing that can be completed remotely from the research centre. To obtain hand movement features, participants will be asked to perform a variety of hand gestures using their own computer cameras. However, it is challenging to collect high quality hand movement video data, especially for older participants, many of whom have no IT background. During the data collection process, one of the key steps is to detect whether the participants are following the test instructions correctly and also to detect similar gestures from different devices. Furthermore, we need this process to be automated and accurate as we expect many thousands of participants to complete the test. We have implemented a hand gesture detector to detect the gestures in the hand movement tests and our detection mAP is 0.782 which is better than the state-of-the-art. In this research, we have processed 20,000 images collected from hand movement tests and labelled 6,450 images to detect different hand gestures in the hand movement tests. This paper has the following three contributions. Firstly, we compared and analysed the performance of different network structures for hand gesture detection. Secondly, we have made many attempts to improve the accuracy of the model and have succeeded in improving the classification accuracy for similar gestures by implementing attention layers. Thirdly, we have created two datasets and included 20 percent of blurred images in the dataset to investigate how different network structures were impacted by noisy data, our experiments have also shown our network has better performance on the noisy dataset.
Recently, face recognition in the wild has achieved remarkable success and one key engine is the increasing size of training data. For example, the largest face dataset, WebFace42M contains about 2 million identities and 42 million faces. However, a massive number of faces raise the constraints in training time, computing resources, and memory cost. The current research on this problem mainly focuses on designing an efficient Fully-connected layer (FC) to reduce GPU memory consumption caused by a large number of identities. In this work, we relax these constraints by resolving the redundancy problem of the up-to-date face datasets caused by the greedily collecting operation (i.e. the core-set selection perspective). As the first attempt in this perspective on the face recognition problem, we find that existing methods are limited in both performance and efficiency. For superior cost-efficiency, we contribute a novel filtering strategy dubbed Face-NMS. Face-NMS works on feature space and simultaneously considers the local and global sparsity in generating core sets. In practice, Face-NMS is analogous to Non-Maximum Suppression (NMS) in the object detection community. It ranks the faces by their potential contribution to the overall sparsity and filters out the superfluous face in the pairs with high similarity for local sparsity. With respect to the efficiency aspect, Face-NMS accelerates the whole pipeline by applying a smaller but sufficient proxy dataset in training the proxy model. As a result, with Face-NMS, we successfully scale down the WebFace42M dataset to 60% while retaining its performance on the main benchmarks, offering a 40% resource-saving and 1.64 times acceleration. The code is publicly available for reference at https://github.com/HuangJunJie2017/Face-NMS.
According to WHO statistics, there are more than 204,617,027 confirmed COVID-19 cases including 4,323,247 deaths worldwide till August 12, 2021. During the coronavirus epidemic, almost everyone wears a facial mask. Traditionally, face recognition approaches process mostly non-occluded faces, which include primary facial features such as the eyes, nose, and mouth. Removing the mask for authentication in airports or laboratories will increase the risk of virus infection, posing a huge challenge to current face recognition systems. Due to the sudden outbreak of the epidemic, there are yet no publicly available real-world masked face recognition (MFR) benchmark. To cope with the above-mentioned issue, we organize the Face Bio-metrics under COVID Workshop and Masked Face Recognition Challenge in ICCV 2021. Enabled by the ultra-large-scale WebFace260M benchmark and the Face Recognition Under Inference Time conStraint (FRUITS) protocol, this challenge (WebFace260M Track) aims to push the frontiers of practical MFR. Since public evaluation sets are mostly saturated or contain noise, a new test set is gathered consisting of elaborated 2,478 celebrities and 60,926 faces. Meanwhile, we collect the world-largest real-world masked test set. In the first phase of WebFace260M Track, 69 teams (total 833 solutions) participate in the challenge and 49 teams exceed the performance of our baseline. There are second phase of the challenge till October 1, 2021 and on-going leaderboard. We will actively update this report in the future.