Integrating external knowledge with traditional spoken language understanding (SLU) models can effectively mitigate the ambiguity in user utterances in real-world scenarios. Knowledge graph, as a common source of external knowledge, encapsulates entities enriched with diverse attribute information. Nevertheless, existing models consider all entities as relevant, which introduces significant noise into the input. Additionally, not all attribute information of the entities is essential, resulting in considerable noise and redundancy. In this article, we propose a Noise-Removal of Knowledge-Enhanced (NRKE) framework for SLU, which involves two different types of denoising. The first approach involves hard denoising via entity selection, where we leverage a small clean dataset and introduce a BERT-based auxiliary model to filter out entities unrelated to user utterances, effectively eliminating noisy entities. In addition, we further refine entity selection by incorporating Large Language Models (LLMs) to assist in filtering out entities unrelated to user utterances. The second method involves soft denoising through the selection of entity attribute information. This approach utilizes a keywords-based local semantic selection that gives greater weight to relevant local semantics associated with specific keywords. This allows us to capture task-related information from the chosen entities, thereby minimizing noise and redundancy. To evaluate the generalization capability of existing knowledge-enhanced SLU models, we construct a new dataset named KGCAIS. The experimental results show that our NRKE achieves better performance than the competing models on both the PROSLU and KGCAIS datasets.

We propose a generative agent that augments training datasets with synthetic data for model fine-tuning. Unlike prior work, which uniformly samples synthetic data, our agent iteratively generates relevant samples on-the-fly, aligning with the target distribution. It prioritizes synthetic data that complements difficult training samples, focusing on those with high variance in gradient updates. Experiments across several image classification tasks demonstrate the effectiveness of our approach.

We propose a method for depth estimation under different illumination conditions, i.e., day and night time. As photometry is uninformative in regions under low-illumination, we tackle the problem through a multi-sensor fusion approach, where we take as input an additional synchronized sparse point cloud (i.e., from a LiDAR) projected onto the image plane as a sparse depth map, along with a camera image. The crux of our method lies in the use of the abundantly available synthetic data to first approximate the 3D scene structure by learning a mapping from sparse to (coarse) dense depth maps along with their predictive uncertainty – we term this, SpaDe. In poorly illuminated regions where photometric intensities do not afford the inference of local shape, the coarse approximation of scene depth serves as a prior; the uncertainty map is then used with the image to guide refinement through an uncertainty-driven residual learning (URL) scheme. The resulting depth completion network leverages complementary strengths from both modalities – depth is sparse but insensitive to illumination and in metric scale, and image is dense but sensitive with scale ambiguity. SpaDe can be used in a plug-and-play fashion, which allows for 24% improvement when augmented onto existing methods to preprocess sparse depth. We demonstrate URL on the nuScenes dataset where we improve over all baselines by an average 12.39% in all-day scenarios, 12.02% when tested specifically for daytime, and 14.95% for nighttime scenes. Code available at : https://github.com/ezhovv/all-day-depth

Neural scene representations have achieved great success in parameterizing and reconstructing images, but current state of the art models are not optimized with the preservation of physical quantities in mind. While current architectures can reconstruct color images correctly, they create artifacts when trying to fit maps of polar quantities. We propose polarimetric coordinate networks (pCON), a new model architecture for neural scene representations aimed at preserving polarimetric information while accurately parameterizing the scene. Our model removes artifacts created by current coordinate network architectures when reconstructing three polarimetric quantities of interest. All code and data can be found at this link: http5://visual.ee.ucla.edu/pcon.htm.

We present a method for inferring dense depth from a camera image and a sparse noisy radar point cloud. We first describe the mechanics behind mmWave radar point cloud formation and the challenges that it poses, i.e. ambiguous elevation and noisy depth and azimuth components that yields incorrect positions when projected onto the image, and how existing works have overlooked these nuances in camera-radar fusion. Our approach is motivated by these mechanics, leading to the design of a network that maps each radar point to the possible surfaces that it may project onto in the image plane. Unlike existing works, we do not process the raw radar point cloud as an erroneous depth map, but query each raw point independently to associate it with likely pixels in the image – yielding a semi-dense radar depth map. To fuse radar depth with an image, we propose a gated fusion scheme that accounts for the confidence scores of the correspondence so that we selectively combine radar and camera embeddings to yield a dense depth map. We test our method on the NuScenes benchmark and show a 10.3% improvement in mean absolute error and a 9.1% improvement in root-mean-square error over the best method. Code: https://github.com/nesl/radar-camera-fusion-depth.

Today single image deweathering is arguably more sensitive to the dataset type, rather than the model. We introduce WeatherStream, an automatic pipeline capturing all real-world weather effects (rain, snow, and rain fog degradations), along with their clean image pairs. Previous state-of-the-art methods that have attempted the all-weather removal task train on synthetic pairs, and are thus limited by the Sim2Real domain gap. Recent work has attempted to manually collect time multiplexed pairs, but the use of human labor limits the scale of such a dataset. We introduce a pipeline that uses the power of light-transport physics and a model trained on a small, initial seed dataset to reject approximately 99.6% of unwanted scenes. The pipeline is able to generalize to new scenes and degradations that can, in turn, be used to train existing models just like fully human-labeled data. Training on a dataset collected through this procedure leads to significant improvements on multiple existing weather removal methods on a carefully human-collected test set of real-world weather effects. The dataset and code can be found in the following website: http://visual.ee.ucla.edu/wstream.htm/.

While perspective is a well-studied topic in art, it is generally taken for granted in images. However, for the recent wave of high-quality image synthesis methods such as latent diffusion models, perspective accuracy is not an explicit requirement. Since these methods are capable of outputting a wide gamut of possible images, it is difficult for these synthesized images to adhere to the principles of linear perspective. We introduce a novel geometric constraint in the training process of generative models to enforce perspective accuracy. We show that outputs of models trained with this constraint both appear more realistic and improve performance of downstream models trained on generated images. Subjective human trials show that images generated with latent diffusion models trained with our constraint are preferred over images from the Stable Diffusion V2 model 70% of the time. SOTA monocular depth estimation models such as DPT and PixelFormer, fine-tuned on our images, outperform the original models trained on real images by up to 7.03% in RMSE and 19.3% in SqRel on the KITTI test set for zero-shot transfer.

Accelerated by telemedicine, advances in Remote Photoplethysmography (rPPG) are beginning to offer a viable path toward non-contact physiological measurement. Unfortunately, the datasets for rPPG are limited as they require videos of the human face paired with ground-truth, synchronized heart rate data from a medical-grade health monitor. Also troubling is that the datasets are not inclusive of diverse populations, i.e., current real rPPG facial video datasets are imbalanced in terms of races or skin tones, leading to accuracy disparities on different demographic groups. This paper proposes a scalable biophysical learning based method to generate physio-realistic synthetic rPPG videos given any reference image and target rPPG signal and shows that it could further improve the state-of-the-art physiological measurement and reduce the bias among different groups. We also collect the largest rPPG dataset of its kind (UCLA-rPPG) with a diverse presence of subject skin tones, in the hope that this could serve as a benchmark dataset for different skin tones in this area and ensure that advances of the technique can benefit all people for healthcare equity. The dataset is available at https://visual.ee.ucla.edu/rppg_avatars.htm/.

Data-driven remote vital sign estimation provides an efficient alternative to on-site clinical monitoring, however, its performance can be biased due to the imbalanced training sets. In this work, we take remote photoplethysmography (rPPG) as an example to examine the performance bias from skin tone variations in non-contact heart rate estimation. In rPPG, recent deep learning models have significantly improved the accuracy of the physiological measurement, however, the existing datasets MMSE-HR, AFRL, and UBFC-RPPG only contain roughly 10%, 0%, and 5% of dark-skinned subjects respectively. The imbalanced training sets result in a poor generalization capability of these models and lead to unwanted bias toward different demographic groups. In Western academia, it is regrettably difficult in a university setting to collect data on these dark-skinned subjects. Here we show a first attempt to overcome the lack of dark-skinned subjects by synthetic augmentation. A joint optimization framework is utilized to translate real videos from light-skinned subjects to dark skin tones while retaining their pulsatile signals. In the experiment, our method exhibits around 38% reduction in mean absolute error for the dark-skinned group and 49% improvement on bias mitigation, as compared with the previous work trained with just real samples. Project website: https://visual.ee.ucla.edu/rppg_augmentation.htm/.