Visual navigation, a foundational aspect of Embodied AI (E-AI), has been significantly studied in the past few years. While many 3D simulators have been introduced to support visual navigation tasks, scarcely works have been directed towards combining human dynamics, creating the gap between simulation and real-world applications. Furthermore, current 3D simulators incorporating human dynamics have several limitations, particularly in terms of computational efficiency, which is a promise of E-AI simulators. To overcome these shortcomings, we introduce HabiCrowd, the first standard benchmark for crowd-aware visual navigation that integrates a crowd dynamics model with diverse human settings into photorealistic environments. Empirical evaluations demonstrate that our proposed human dynamics model achieves state-of-the-art performance in collision avoidance, while exhibiting superior computational efficiency compared to its counterparts. We leverage HabiCrowd to conduct several comprehensive studies on crowd-aware visual navigation tasks and human-robot interactions. The source code and data can be found at https://habicrowd.github.io/.
This paper presents a solution to the cross-domain adaptation problem for 2D surgical image segmentation, explicitly considering the privacy protection of distributed datasets belonging to different centers. Deep learning architectures in medical image analysis necessitate extensive training data for better generalization. However, obtaining sufficient diagnostic and surgical data is still challenging, mainly due to the inherent cost of data curation and the need of experts for data annotation. Moreover, increased privacy and legal compliance concerns can make data sharing across clinical sites or regions difficult. Another ubiquitous challenge the medical datasets face is inevitable domain shifts among the collected data at the different centers. To this end, we propose a Client-server deep federated architecture for cross-domain adaptation. A server hosts a set of immutable parameters common to both the source and target domains. The clients consist of the respective domain-specific parameters and make requests to the server while learning their parameters and inferencing. We evaluate our framework in two benchmark datasets, demonstrating applicability in computer-assisted interventions for endoscopic polyp segmentation and diagnostic skin lesion detection and analysis. Our extensive quantitative and qualitative experiments demonstrate the superiority of the proposed method compared to competitive baseline and state-of-the-art methods. Codes are available at: https://github.com/thetna/distributed-da
3D point clouds are a crucial type of data collected by LiDAR sensors and widely used in transportation applications due to its concise descriptions and accurate localization. Deep neural networks (DNNs) have achieved remarkable success in processing large amount of disordered and sparse 3D point clouds, especially in various computer vision tasks, such as pedestrian detection and vehicle recognition. Among all the learning paradigms, Self-Supervised Learning (SSL), an unsupervised training paradigm that mines effective information from the data itself, is considered as an essential solution to solve the time-consuming and labor-intensive data labelling problems via smart pre-training task design. This paper provides a comprehensive survey of recent advances on SSL for point clouds. We first present an innovative taxonomy, categorizing the existing SSL methods into four broad categories based on the pretexts' characteristics. Under each category, we then further categorize the methods into more fine-grained groups and summarize the strength and limitations of the representative methods. We also compare the performance of the notable SSL methods in literature on multiple downstream tasks on benchmark datasets both quantitatively and qualitatively. Finally, we propose a number of future research directions based on the identified limitations of existing SSL research on point clouds.
Endovascular intervention training is increasingly being conducted in virtual simulators. However, transferring the experience from endovascular simulators to the real world remains an open problem. The key challenge is the virtual environments are usually not realistically simulated, especially the simulation images. In this paper, we propose a new method to translate simulation images from an endovascular simulator to X-ray images. Previous image-to-image translation methods often focus on visual effects and neglect structure information, which is critical for medical images. To address this gap, we propose a new method that utilizes multi-scale semantic matching. We apply self-domain semantic matching to ensure that the input image and the generated image have the same positional semantic relationships. We further apply cross-domain matching to eliminate the effects of different styles. The intensive experiment shows that our method generates realistic X-ray images and outperforms other state-of-the-art approaches by a large margin. We also collect a new large-scale dataset to serve as the new benchmark for this task. Our source code and dataset will be made publicly available.
Image classifiers are information-discarding machines, by design. Yet, how these models discard information remains mysterious. We hypothesize that one way for image classifiers to reach high accuracy is to first zoom to the most discriminative region in the image and then extract features from there to predict image labels. We study six popular networks ranging from AlexNet to CLIP and find that proper framing of the input image can lead to the correct classification of 98.91% of ImageNet images. Furthermore, we explore the potential and limits of zoom transforms in image classification and uncover positional biases in various datasets, especially a strong center bias in two popular datasets: ImageNet-A and ObjectNet. Finally, leveraging our insights into the potential of zoom, we propose a state-of-the-art test-time augmentation (TTA) technique that improves classification accuracy by forcing models to explicitly perform zoom-in operations before making predictions. Our method is more interpretable, accurate, and faster than MEMO, a state-of-the-art TTA method. Additionally, we propose ImageNet-Hard, a new benchmark where zooming in alone often does not help state-of-the-art models better label images.
Music-driven choreography is a challenging problem with a wide variety of industrial applications. Recently, many methods have been proposed to synthesize dance motions from music for a single dancer. However, generating dance motion for a group remains an open problem. In this paper, we present $\rm AIOZ-GDANCE$, a new large-scale dataset for music-driven group dance generation. Unlike existing datasets that only support single dance, our new dataset contains group dance videos, hence supporting the study of group choreography. We propose a semi-autonomous labeling method with humans in the loop to obtain the 3D ground truth for our dataset. The proposed dataset consists of 16.7 hours of paired music and 3D motion from in-the-wild videos, covering 7 dance styles and 16 music genres. We show that naively applying single dance generation technique to creating group dance motion may lead to unsatisfactory results, such as inconsistent movements and collisions between dancers. Based on our new dataset, we propose a new method that takes an input music sequence and a set of 3D positions of dancers to efficiently produce multiple group-coherent choreographies. We propose new evaluation metrics for measuring group dance quality and perform intensive experiments to demonstrate the effectiveness of our method. Our project facilitates future research on group dance generation and is available at: https://aioz-ai.github.io/AIOZ-GDANCE/
Audio-driven talking head animation is a challenging research topic with many real-world applications. Recent works have focused on creating photo-realistic 2D animation, while learning different talking or singing styles remains an open problem. In this paper, we present a new method to generate talking head animation with learnable style references. Given a set of style reference frames, our framework can reconstruct 2D talking head animation based on a single input image and an audio stream. Our method first produces facial landmarks motion from the audio stream and constructs the intermediate style patterns from the style reference images. We then feed both outputs into a style-aware image generator to generate the photo-realistic and fidelity 2D animation. In practice, our framework can extract the style information of a specific character and transfer it to any new static image for talking head animation. The intensive experimental results show that our method achieves better results than recent state-of-the-art approaches qualitatively and quantitatively.
Most language models (LMs) are trained and applied in an autoregressive left-to-right fashion, assuming that the next token only depends on the preceding ones. However, this assumption ignores the potential benefits of using the full sequence information during training, and the possibility of having context from both sides during inference. In this paper, we propose a new pre-training paradigm with techniques that jointly improve the training data efficiency and the capabilities of the LMs in the infilling task. The first is a training objective that aligns the predictions of a left-to-right LM with those of a right-to-left LM, trained on the same data but in reverse order. The second is a bidirectional inference procedure that enables both LMs to meet in the middle. We show the effectiveness of our pre-training paradigm with extensive experiments on both programming and natural language models, outperforming strong baselines.
Federated learning has been widely applied in autonomous driving since it enables training a learning model among vehicles without sharing users' data. However, data from autonomous vehicles usually suffer from the non-independent-and-identically-distributed (non-IID) problem, which may cause negative effects on the convergence of the learning process. In this paper, we propose a new contrastive divergence loss to address the non-IID problem in autonomous driving by reducing the impact of divergence factors from transmitted models during the local learning process of each silo. We also analyze the effects of contrastive divergence in various autonomous driving scenarios, under multiple network infrastructures, and with different centralized/distributed learning schemes. Our intensive experiments on three datasets demonstrate that our proposed contrastive divergence loss further improves the performance over current state-of-the-art approaches.