AV-HuBERT, a multi-modal self-supervised learning model, has been shown to be effective for categorical problems such as automatic speech recognition and lip-reading. This suggests that useful audio-visual speech representations can be obtained via utilizing multi-modal self-supervised embeddings. Nevertheless, it is unclear if such representations can be generalized to solve real-world multi-modal AV regression tasks, such as audio-visual speech enhancement (AVSE) and audio-visual speech separation (AVSS). In this study, we leveraged the pre-trained AV-HuBERT model followed by an SE module for AVSE and AVSS. Comparative experimental results demonstrate that our proposed model performs better than the state-of-the-art AVSE and traditional audio-only SE models. In summary, our results confirm the effectiveness of our proposed model for the AVSS task with proper fine-tuning strategies, demonstrating that multi-modal self-supervised embeddings obtained from AV-HUBERT can be generalized to audio-visual regression tasks.
A spatial AI that can perform complex tasks through visual signals and cooperate with humans is highly anticipated. To achieve this, we need a visual SLAM that easily adapts to new scenes without pre-training and generates dense maps for downstream tasks in real-time. None of the previous learning-based and non-learning-based visual SLAMs satisfy all needs due to the intrinsic limitations of their components. In this work, we develop a visual SLAM named Orbeez-SLAM, which successfully collaborates with implicit neural representation (NeRF) and visual odometry to achieve our goals. Moreover, Orbeez-SLAM can work with the monocular camera since it only needs RGB inputs, making it widely applicable to the real world. We validate its effectiveness on various challenging benchmarks. Results show that our SLAM is up to 800x faster than the strong baseline with superior rendering outcomes.
Deep image prior (DIP) is a recently proposed technique for solving imaging inverse problems by fitting the reconstructed images to the output of an untrained convolutional neural network. Unlike pretrained feedforward neural networks, the same DIP can generalize to arbitrary inverse problems, from denoising to phase retrieval, while offering competitive performance at each task. The central disadvantage of DIP is that, while feedforward neural networks can reconstruct an image in a single pass, DIP must gradually update its weights over hundreds to thousands of iterations, at a significant computational cost. In this work we use meta-learning to massively accelerate DIP-based reconstructions. By learning a proper initialization for the DIP weights, we demonstrate a 10x improvement in runtimes across a range of inverse imaging tasks. Moreover, we demonstrate that a network trained to quickly reconstruct faces also generalizes to reconstructing natural image patches.
Age-related macular degeneration (AMD) is the leading cause of visual impairment among elderly in the world. Early detection of AMD is of great importance as the vision loss caused by AMD is irreversible and permanent. Color fundus photography is the most cost-effective imaging modality to screen for retinal disorders. \textcolor{red}{Recently, some algorithms based on deep learning had been developed for fundus image analysis and automatic AMD detection. However, a comprehensive annotated dataset and a standard evaluation benchmark are still missing.} To deal with this issue, we set up the Automatic Detection challenge on Age-related Macular degeneration (ADAM) for the first time, held as a satellite event of the ISBI 2020 conference. The ADAM challenge consisted of four tasks which cover the main topics in detecting AMD from fundus images, including classification of AMD, detection and segmentation of optic disc, localization of fovea, and detection and segmentation of lesions. The ADAM challenge has released a comprehensive dataset of 1200 fundus images with the category labels of AMD, the pixel-wise segmentation masks of the full optic disc and lesions (drusen, exudate, hemorrhage, scar, and other), as well as the location coordinates of the macular fovea. A uniform evaluation framework has been built to make a fair comparison of different models. During the ADAM challenge, 610 results were submitted for online evaluation, and finally, 11 teams participated in the onsite challenge. This paper introduces the challenge, dataset, and evaluation methods, as well as summarizes the methods and analyzes the results of the participating teams of each task. In particular, we observed that ensembling strategy and clinical prior knowledge can better improve the performances of the deep learning models.
3D object detection plays an important role in autonomous driving and other robotics applications. However, these detectors usually require training on large amounts of annotated data that is expensive and time-consuming to collect. Instead, we propose leveraging large amounts of unlabeled point cloud videos by semi-supervised learning of 3D object detectors via temporal graph neural networks. Our insight is that temporal smoothing can create more accurate detection results on unlabeled data, and these smoothed detections can then be used to retrain the detector. We learn to perform this temporal reasoning with a graph neural network, where edges represent the relationship between candidate detections in different time frames. After semi-supervised learning, our method achieves state-of-the-art detection performance on the challenging nuScenes and H3D benchmarks, compared to baselines trained on the same amount of labeled data. Project and code are released at https://www.jianrenw.com/SOD-TGNN/.
In few-shot imitation learning (FSIL), using behavioral cloning (BC) to solve unseen tasks with few expert demonstrations becomes a popular research direction. The following capabilities are essential in robotics applications: (1) Behaving in compound tasks that contain multiple stages. (2) Retrieving knowledge from few length-variant and misalignment demonstrations. (3) Learning from a different expert. No previous work can achieve these abilities at the same time. In this work, we conduct FSIL problem under the union of above settings and introduce a novel stage conscious attention network (SCAN) to retrieve knowledge from few demonstrations simultaneously. SCAN uses an attention module to identify each stage in length-variant demonstrations. Moreover, it is designed under demonstration-conditioned policy that learns the relationship between experts and agents. Experiment results show that SCAN can learn from different experts without fine-tuning and outperform baselines in complicated compound tasks with explainable visualization.
A massive number of traffic fatalities are due to driver errors. To reduce fatalities, developing intelligent driving systems assisting drivers to identify potential risks is in urgent need. Risky situations are generally defined based on collision prediction in existing research. However, collisions are only one type of risk in traffic scenarios. We believe a more generic definition is required. In this work, we propose a novel driver-centric definition of risk, i.e., risky objects influence driver behavior. Based on this definition, a new task called risk object identification is introduced. We formulate the task as a cause-effect problem and present a novel two-stage risk object identification framework, taking inspiration from models of situation awareness and causal inference. A driver-centric Risk Object Identification (ROI) dataset is curated to evaluate the proposed system. We demonstrate state-of-the-art risk object identification performance compared with strong baselines on the ROI dataset. In addition, we conduct extensive ablative studies to justify our design choices.
In this work, we propose CARLS, a novel framework for augmenting the capacity of existing deep learning frameworks by enabling multiple components -- model trainers, knowledge makers and knowledge banks -- to concertedly work together in an asynchronous fashion across hardware platforms. The proposed CARLS is particularly suitable for learning paradigms where model training benefits from additional knowledge inferred or discovered during training, such as node embeddings for graph neural networks or reliable pseudo labels from model predictions. We also describe three learning paradigms -- semi-supervised learning, curriculum learning and multimodal learning -- as examples that can be scaled up efficiently by CARLS. One version of CARLS has been open-sourced and available for download at: https://github.com/tensorflow/neural-structured-learning/tree/master/research/carls
Object detection with multimodal inputs can improve many safety-critical perception systems such as autonomous vehicles (AVs). Motivated by AVs that operate in both day and night, we study multimodal object detection with RGB and thermal cameras, since the latter can provide much stronger object signatures under poor illumination. We explore strategies for fusing information from different modalities. Our key contribution is a non-learned late-fusion method that fuses together bounding box detections from different modalities via a simple probabilistic model derived from first principles. Our simple approach, which we call Bayesian Fusion, is readily derived from conditional independence assumptions across different modalities. We apply our approach to benchmarks containing both aligned (KAIST) and unaligned (FLIR) multimodal sensor data. Our Bayesian Fusion outperforms prior work by more than 13% in relative performance.