Descriptor Distillation for Efficient Multi-Robot SLAM

Performing accurate localization while maintaining the low-level communication bandwidth is an essential challenge of multi-robot simultaneous localization and mapping (MR-SLAM). In this paper, we tackle this problem by generating a compact yet discriminative feature descriptor with minimum inference time. We propose descriptor distillation that formulates the descriptor generation into a learning problem under the teacher-student framework. To achieve real-time descriptor generation, we design a compact student network and learn it by transferring the knowledge from a pre-trained large teacher model. To reduce the descriptor dimensions from the teacher to the student, we propose a novel loss function that enables the knowledge transfer between two different dimensional descriptors. The experimental results demonstrate that our model is 30% lighter than the state-of-the-art model and produces better descriptors in patch matching. Moreover, we build a MR-SLAM system based on the proposed method and show that our descriptor distillation can achieve higher localization performance for MR-SLAM with lower bandwidth.

Lifelong-MonoDepth: Lifelong Learning for Multi-Domain Monocular Metric Depth Estimation

In recent years, monocular depth estimation (MDE) has gained significant progress in a data-driven learning fashion. Previous methods can infer depth maps for specific domains based on the paradigm of single-domain or joint-domain training with mixed data. However, they suffer from low scalability to new domains. In reality, target domains often dynamically change or increase, raising the requirement of incremental multi-domain/task learning. In this paper, we seek to enable lifelong learning for MDE, which performs cross-domain depth learning sequentially, to achieve high plasticity on a new domain and maintain good stability on original domains. To overcome significant domain gaps and enable scale-aware depth prediction, we design a lightweight multi-head framework that consists of a domain-shared encoder for feature extraction and domain-specific predictors for metric depth estimation. Moreover, given an input image, we propose an efficient predictor selection approach that automatically identifies the corresponding predictor for depth inference. Through extensive numerical studies, we show that the proposed method can achieve good efficiency, stability, and plasticity, leading the benchmarks by 8% to 15%.

ConTEXTual Net: A Multimodal Vision-Language Model for Segmentation of Pneumothorax

Clinical imaging databases contain not only medical images but also text reports generated by physicians. These narrative reports often describe the location, size, and shape of the disease, but using descriptive text to guide medical image analysis has been understudied. Vision-language models are increasingly used for multimodal tasks like image generation, image captioning, and visual question answering but have been scarcely used in medical imaging. In this work, we develop a vision-language model for the task of pneumothorax segmentation. Our model, ConTEXTual Net, detects and segments pneumothorax in chest radiographs guided by free-form radiology reports. ConTEXTual Net achieved a Dice score of 0.72 $\pm$ 0.02, which was similar to the level of agreement between the primary physician annotator and the other physician annotators (0.71 $\pm$ 0.04). ConTEXTual Net also outperformed a U-Net. We demonstrate that descriptive language can be incorporated into a segmentation model for improved performance. Through an ablative study, we show that it is the text information that is responsible for the performance gains. Additionally, we show that certain augmentation methods worsen ConTEXTual Net's segmentation performance by breaking the image-text concordance. We propose a set of augmentations that maintain this concordance and improve segmentation training.

Domain-adapted large language models for classifying nuclear medicine reports

With the growing use of transformer-based language models in medicine, it is unclear how well these models generalize to nuclear medicine which has domain-specific vocabulary and unique reporting styles. In this study, we evaluated the value of domain adaptation in nuclear medicine by adapting language models for the purpose of 5-point Deauville score prediction based on clinical 18F-fluorodeoxyglucose (FDG) PET/CT reports. We retrospectively retrieved 4542 text reports and 1664 images for FDG PET/CT lymphoma exams from 2008-2018 in our clinical imaging database. Deauville scores were removed from the reports and then the remaining text in the reports was used as the model input. Multiple general-purpose transformer language models were used to classify the reports into Deauville scores 1-5. We then adapted the models to the nuclear medicine domain using masked language modeling and assessed its impact on classification performance. The language models were compared against vision models, a multimodal vision language model, and a nuclear medicine physician with seven-fold Monte Carlo cross validation, reported are the mean and standard deviations. Domain adaption improved all language models. For example, BERT improved from 61.3% five-class accuracy to 65.7% following domain adaptation. The best performing model (domain-adapted RoBERTa) achieved a five-class accuracy of 77.4%, which was better than the physician's performance (66%), the best vision model's performance (48.1), and was similar to the multimodal model's performance (77.2). Domain adaptation improved the performance of large language models in interpreting nuclear medicine text reports.

Peer Learning for Unbiased Scene Graph Generation

In this paper, we propose a novel framework dubbed peer learning to deal with the problem of biased scene graph generation (SGG). This framework uses predicate sampling and consensus voting (PSCV) to encourage different peers to learn from each other, improving model diversity and mitigating bias in SGG. To address the heavily long-tailed distribution of predicate classes, we propose to use predicate sampling to divide and conquer this issue. As a result, the model is less biased and makes more balanced predicate predictions. Specifically, one peer may not be sufficiently diverse to discriminate between different levels of predicate distributions. Therefore, we sample the data distribution based on frequency of predicates into sub-distributions, selecting head, body, and tail classes to combine and feed to different peers as complementary predicate knowledge during the training process. The complementary predicate knowledge of these peers is then ensembled utilizing a consensus voting strategy, which simulates a civilized voting process in our society that emphasizes the majority opinion and diminishes the minority opinion. This approach ensures that the learned representations of each peer are optimally adapted to the various data distributions. Extensive experiments on the Visual Genome dataset demonstrate that PSCV outperforms previous methods. We have established a new state-of-the-art (SOTA) on the SGCls task by achieving a mean of \textbf{31.6}.

Attentional Graph Convolutional Network for Structure-aware Audio-Visual Scene Classification

Audio-Visual scene understanding is a challenging problem due to the unstructured spatial-temporal relations that exist in the audio signals and spatial layouts of different objects and various texture patterns in the visual images. Recently, many studies have focused on abstracting features from convolutional neural networks while the learning of explicit semantically relevant frames of sound signals and visual images has been overlooked. To this end, we present an end-to-end framework, namely attentional graph convolutional network (AGCN), for structure-aware audio-visual scene representation. First, the spectrogram of sound and input image is processed by a backbone network for feature extraction. Then, to build multi-scale hierarchical information of input features, we utilize an attention fusion mechanism to aggregate features from multiple layers of the backbone network. Notably, to well represent the salient regions and contextual information of audio-visual inputs, the salient acoustic graph (SAG) and contextual acoustic graph (CAG), salient visual graph (SVG), and contextual visual graph (CVG) are constructed for the audio-visual scene representation. Finally, the constructed graphs pass through a graph convolutional network for structure-aware audio-visual scene recognition. Extensive experimental results on the audio, visual and audio-visual scene recognition datasets show that promising results have been achieved by the AGCN methods. Visualizing graphs on the spectrograms and images have been presented to show the effectiveness of proposed CAG/SAG and CVG/SVG that could focus on the salient and semantic relevant regions.

Beyond Counting Datasets: A Survey of Multilingual Dataset Construction and Necessary Resources

While the NLP community is generally aware of resource disparities among languages, we lack research that quantifies the extent and types of such disparity. Prior surveys estimating the availability of resources based on the number of datasets can be misleading as dataset quality varies: many datasets are automatically induced or translated from English data. To provide a more comprehensive picture of language resources, we examine the characteristics of 156 publicly available NLP datasets. We manually annotate how they are created, including input text and label sources and tools used to build them, and what they study, tasks they address and motivations for their creation. After quantifying the qualitative NLP resource gap across languages, we discuss how to improve data collection in low-resource languages. We survey language-proficient NLP researchers and crowd workers per language, finding that their estimated availability correlates with dataset availability. Through crowdsourcing experiments, we identify strategies for collecting high-quality multilingual data on the Mechanical Turk platform. We conclude by making macro and micro-level suggestions to the NLP community and individual researchers for future multilingual data development.

MultiRoboLearn: An open-source Framework for Multi-robot Deep Reinforcement Learning

It is well known that it is difficult to have a reliable and robust framework to link multi-agent deep reinforcement learning algorithms with practical multi-robot applications. To fill this gap, we propose and build an open-source framework for multi-robot systems called MultiRoboLearn1. This framework builds a unified setup of simulation and real-world applications. It aims to provide standard, easy-to-use simulated scenarios that can also be easily deployed to real-world multi-robot environments. Also, the framework provides researchers with a benchmark system for comparing the performance of different reinforcement learning algorithms. We demonstrate the generality, scalability, and capability of the framework with two real-world scenarios2 using different types of multi-agent deep reinforcement learning algorithms in discrete and continuous action spaces.

Progressive Self-Distillation for Ground-to-Aerial Perception Knowledge Transfer

We study a practical yet hasn't been explored problem: how a drone can perceive in an environment from viewpoints of different flight heights. Unlike autonomous driving where the perception is always conducted from a ground viewpoint, a flying drone may flexibly change its flight height due to specific tasks, requiring capability for viewpoint invariant perception. To reduce the effort of annotation of flight data, we consider a ground-to-aerial knowledge distillation method while using only labeled data of ground viewpoint and unlabeled data of flying viewpoints. To this end, we propose a progressive semi-supervised learning framework which has four core components: a dense viewpoint sampling strategy that splits the range of vertical flight height into a set of small pieces with evenly-distributed intervals, and at each height we sample data from that viewpoint; the nearest neighbor pseudo-labeling that infers labels of the nearest neighbor viewpoint with a model learned on the preceding viewpoint; MixView that generates augmented images among different viewpoints to alleviate viewpoint difference; and a progressive distillation strategy to gradually learn until reaching the maximum flying height. We collect a synthesized dataset and a real-world dataset, and we perform extensive experiments to show that our method yields promising results for different flight heights.

Data-free Dense Depth Distillation

We study data-free knowledge distillation (KD) for monocular depth estimation (MDE), which learns a lightweight network for real-world depth perception by compressing from a trained expert model under the teacher-student framework while lacking training data in the target domain. Owing to the essential difference between dense regression and image recognition, previous methods of data-free KD are not applicable to MDE. To strengthen the applicability in the real world, in this paper, we seek to apply KD with out-of-distribution simulated images. The major challenges are i) lacking prior information about object distribution of the original training data; ii) the domain shift between the real world and the simulation. To cope with the first difficulty, we apply object-wise image mixing to generate new training samples for maximally covering distributed patterns of objects in the target domain. To tackle the second difficulty, we propose to utilize a transformation network that efficiently learns to fit the simulated data to the feature distribution of the teacher model. We evaluate the proposed approach for various depth estimation models and two different datasets. As a result, our method outperforms the baseline KD by a good margin and even achieves slightly better performance with as few as $1/6$ images, demonstrating a clear superiority.