Modern virtual assistants use internal semantic parsing engines to convert user utterances to actionable commands. However, prior work has demonstrated that semantic parsing is a difficult multilingual transfer task with low transfer efficiency compared to other tasks. In global markets such as India and Latin America, this is a critical issue as switching between languages is prevalent for bilingual users. In this work we dramatically improve the zero-shot performance of a multilingual and codeswitched semantic parsing system using two stages of multilingual alignment. First, we show that constrastive alignment pretraining improves both English performance and transfer efficiency. We then introduce a constrained optimization approach for hyperparameter-free adversarial alignment during finetuning. Our Doubly Aligned Multilingual Parser (DAMP) improves mBERT transfer performance by 3x, 6x, and 81x on the Spanglish, Hinglish and Multilingual Task Oriented Parsing benchmarks respectively and outperforms XLM-R and mT5-Large using 3.2x fewer parameters.
This paper reviews vision-based localization methods in GPS-denied environments and classifies the mainstream methods into Relative Vision Localization (RVL) and Absolute Vision Localization (AVL). For RVL, we discuss the broad application of optical flow in feature extraction-based Visual Odometry (VO) solutions and introduce advanced optical flow estimation methods. For AVL, we review recent advances in Visual Simultaneous Localization and Mapping (VSLAM) techniques, from optimization-based methods to Extended Kalman Filter (EKF) based methods. We also introduce the application of offline map registration and lane vision detection schemes to achieve Absolute Visual Localization. This paper compares the performance and applications of mainstream methods for visual localization and provides suggestions for future studies.
Text segmentation is important for signaling a document's structure. Without segmenting a long document into topically coherent sections, it is difficult for readers to comprehend the text, let alone find important information. The problem is only exacerbated by a lack of segmentation in transcripts of audio/video recordings. In this paper, we explore the role that section segmentation plays in extractive summarization of written and spoken documents. Our approach learns robust sentence representations by performing summarization and segmentation simultaneously, which is further enhanced by an optimization-based regularizer to promote selection of diverse summary sentences. We conduct experiments on multiple datasets ranging from scientific articles to spoken transcripts to evaluate the model's performance. Our findings suggest that the model can not only achieve state-of-the-art performance on publicly available benchmarks, but demonstrate better cross-genre transferability when equipped with text segmentation. We perform a series of analyses to quantify the impact of section segmentation on summarizing written and spoken documents of substantial length and complexity.
Automating the process of manipulating and delivering sutures during robotic surgery is a prominent problem at the frontier of surgical robotics, as automating this task can significantly reduce surgeons' fatigue during tele-operated surgery and allow them to spend more time addressing higher-level clinical decision making. Accomplishing autonomous suturing and suture manipulation in the real world requires accurate suture thread localization and reconstruction, the process of creating a 3D shape representation of suture thread from 2D stereo camera surgical image pairs. This is a very challenging problem due to how limited pixel information is available for the threads, as well as their sensitivity to lighting and specular reflection. We present a suture thread reconstruction work that uses reliable keypoints and a Minimum Variation Spline (MVS) smoothing optimization to construct a 3D centerline from a segmented surgical image pair. This method is comparable to previous suture thread reconstruction works, with the possible benefit of increased accuracy of grasping point estimation. Our code and datasets will be available at: https://github.com/ucsdarclab/thread-reconstruction.
Monocular depth estimation and defocus estimation are two fundamental tasks in computer vision. Most existing methods treat depth estimation and defocus estimation as two separate tasks, ignoring the strong connection between them. In this work, we propose a multi-task learning network consisting of an encoder with two decoders to estimate the depth and defocus map from a single focused image. Through the multi-task network, the depth estimation facilitates the defocus estimation to get better results in the weak texture region and the defocus estimation facilitates the depth estimation by the strong physical connection between the two maps. We set up a dataset (named ALL-in-3D dataset) which is the first all-real image dataset consisting of 100K sets of all-in-focus images, focused images with focus depth, depth maps, and defocus maps. It enables the network to learn features and solid physical connections between the depth and real defocus images. Experiments demonstrate that the network learns more solid features from the real focused images than the synthetic focused images. Benefiting from this multi-task structure where different tasks facilitate each other, our depth and defocus estimations achieve significantly better performance than other state-of-art algorithms. The code and dataset will be publicly available at https://github.com/cubhe/MDDNet.
We propose novel AI-empowered chat bots for learning as conversation where a user does not read a passage but gains information and knowledge through conversation with a teacher bot. Our information-acquisition-oriented dialogue system employs a novel adaptation of reinforced self-play so that the system can be transferred to various domains without in-domain dialogue data, and can carry out conversations both informative and attentive to users. Our extensive subjective and objective evaluations on three large public data corpora demonstrate the effectiveness of our system to deliver knowledge-intensive and attentive conversations and help end users substantially gain knowledge without reading passages. Our code and datasets are publicly available for follow-up research.
Text-to-image synthesis aims to generate natural images conditioned on text descriptions. The main difficulty of this task lies in effectively fusing text information into the image synthesis process. Existing methods usually adaptively fuse suitable text information into the synthesis process with multiple isolated fusion blocks (e.g., Conditional Batch Normalization and Instance Normalization). However, isolated fusion blocks not only conflict with each other but also increase the difficulty of training (see first page of the supplementary). To address these issues, we propose a Recurrent Affine Transformation (RAT) for Generative Adversarial Networks that connects all the fusion blocks with a recurrent neural network to model their long-term dependency. Besides, to improve semantic consistency between texts and synthesized images, we incorporate a spatial attention model in the discriminator. Being aware of matching image regions, text descriptions supervise the generator to synthesize more relevant image contents. Extensive experiments on the CUB, Oxford-102 and COCO datasets demonstrate the superiority of the proposed model in comparison to state-of-the-art models \footnote{https://github.com/senmaoy/Recurrent-Affine-Transformation-for-Text-to-image-Synthesis.git}
Retraining modern deep learning systems can lead to variations in model performance even when trained using the same data and hyper-parameters by simply using different random seeds. We call this phenomenon model jitter. This issue is often exacerbated in production settings, where models are retrained on noisy data. In this work we tackle the problem of stable retraining with a focus on conversational semantic parsers. We first quantify the model jitter problem by introducing the model agreement metric and showing the variation with dataset noise and model sizes. We then demonstrate the effectiveness of various jitter reduction techniques such as ensembling and distillation. Lastly, we discuss practical trade-offs between such techniques and show that co-distillation provides a sweet spot in terms of jitter reduction for semantic parsing systems with only a modest increase in resource usage.
Podcasts have recently shown a rapid rise in popularity. Summarization of podcast transcripts is of practical benefit to both content providers and consumers. It helps consumers to quickly decide whether they will listen to the podcasts and reduces the cognitive load of content providers to write summaries. Nevertheless, podcast summarization faces significant challenges including factual inconsistencies with respect to the inputs. The problem is exacerbated by speech disfluencies and recognition errors in transcripts of spoken language. In this paper, we explore a novel abstractive summarization method to alleviate these challenges. Specifically, our approach learns to produce an abstractive summary while grounding summary segments in specific portions of the transcript to allow for full inspection of summary details. We conduct a series of analyses of the proposed approach on a large podcast dataset and show that the approach can achieve promising results. Grounded summaries bring clear benefits in locating the summary and transcript segments that contain inconsistent information, and hence significantly improve summarization quality in both automatic and human evaluation metrics.
Point spread function (PSF) plays a crucial role in many fields, such as shape from focus/defocus, depth estimation, and imaging process in fluorescence microscopy. However, the mathematical model of the defocus process is still unclear because several variables in the point spread function are hard to measure accurately, such as the f-number of cameras, the physical size of a pixel, the focus depth, etc. In this work, we develop a precise mathematical model of the camera's point spread function to describe the defocus process. We first derive the mathematical algorithm for the PSF and extract two parameters A and e. A is the composite of camera's f-number, pixel-size, output scale, and scaling factor of the circle of confusion; e is the deviation of the focus depth. We design a novel metric based on the defocus histogram to evaluate the difference between the simulated focused image and the actual focused image to obtain optimal A and e. We also construct a hardware system consisting of a focusing system and a structured light system to acquire the all-in-focus image, the focused image with corresponding focus depth, and the depth map in the same view. The three types of images, as a dataset, are used to obtain the precise PSF. Our experiments on standard planes and actual objects show that the proposed algorithm can accurately describe the defocus process. The accuracy of our algorithm is further proved by evaluating the difference among the actual focused images, the focused image generated by our algorithm, the focused image generated by others. The results show that the loss of our algorithm is 40% less than others on average. The dataset, code, and model are available on GitHub: https://github.com/cubhe/ precise-point-spread-function-estimation.