The Latest Papers about AI
-
Divide and Contrast: Self-supervised Learning from Uncurated Data
2021-05-17 17:59:03Yonglong Tian, Olivier J. Henaff, Aaron van den OordAbstract
tract: Self-supervised learning holds promise in leveraging large amounts of unlabeled data, however much of its progress has thus far been limited to highly curated pre-training data such as ImageNet. We explore the effects of contrastive learning from larger, less-curated image datasets such as YFCC, and find there is indeed a large difference in the resulting representation quality. We hypothesize that this curation gap is due to a shift in the distribution of image classes -- which is more diverse and heavy-tailed -- resulting in less relevant negative samples to learn from. We test this hypothesis with a new approach, Divide and Contrast (DnC), which alternates between contrastive learning and clustering-based hard negative mining. When pretrained on less curated datasets, DnC greatly improves the performance of self-supervised learning on downstream tasks, while remaining competitive with the current state-of-the-art on curated datasets.
Abstract (translated)
URL
https://arxiv.org/abs/2105.08054
PDF
-
The Boombox: Visual Reconstruction from Acoustic Vibrations
2021-05-17 17:58:41Boyuan Chen, Mia Chiquier, Hod Lipson, Carl VondrickAbstract
tract: We introduce The Boombox, a container that uses acoustic vibrations to reconstruct an image of its inside contents. When an object interacts with the container, they produce small acoustic vibrations. The exact vibration characteristics depend on the physical properties of the box and the object. We demonstrate how to use this incidental signal in order to predict visual structure. After learning, our approach remains effective even when a camera cannot view inside the box. Although we use low-cost and low-power contact microphones to detect the vibrations, our results show that learning from multi-modal data enables us to transform cheap acoustic sensors into rich visual sensors. Due to the ubiquity of containers, we believe integrating perception capabilities into them will enable new applications in human-computer interaction and robotics. Our project website is at: this http URL
Abstract (translated)
URL
https://arxiv.org/abs/2105.08052
PDF
-
A Light Stage on Every Desk
2021-05-17 17:56:24Soumyadip Sengupta, Brian Curless, Ira Kemelmacher-Shlizerman, Steve SeitzAbstract
tract: Every time you sit in front of a TV or monitor, your face is actively illuminated by time-varying patterns of light. This paper proposes to use this time-varying illumination for synthetic relighting of your face with any new illumination condition. In doing so, we take inspiration from the light stage work of Debevec et al., who first demonstrated the ability to relight people captured in a controlled lighting environment. Whereas existing light stages require expensive, room-scale spherical capture gantries and exist in only a few labs in the world, we demonstrate how to acquire useful data from a normal TV or desktop monitor. Instead of subjecting the user to uncomfortable rapidly flashing light patterns, we operate on images of the user watching a YouTube video or other standard content. We train a deep network on images plus monitor patterns of a given user and learn to predict images of that user under any target illumination (monitor pattern). Experimental evaluation shows that our method produces realistic relighting results. Video results are available at this http URL.
Abstract (translated)
URL
https://arxiv.org/abs/2105.08051
PDF
-
Pay Attention to MLPs
2021-05-17 17:55:04Hanxiao Liu, Zihang Dai, David R. So, Quoc V. LeAbstract
tract: Transformers have become one of the most important architectural innovations in deep learning and have enabled many breakthroughs over the past few years. Here we propose a simple attention-free network architecture, gMLP, based solely on MLPs with gating, and show that it can perform as well as Transformers in key language and vision applications. Our comparisons show that self-attention is not critical for Vision Transformers, as gMLP can achieve the same accuracy. For BERT, our model achieves parity with Transformers on pretraining perplexity and is better on some downstream tasks. On finetuning tasks where gMLP performs worse, making the gMLP model substantially larger can close the gap with Transformers. In general, our experiments show that gMLP can scale as well as Transformers over increased data and compute.
Abstract (translated)
URL
https://arxiv.org/abs/2105.08050
PDF
-
SGD-QA: Fast Schema-Guided Dialogue State Tracking for Unseen Services
2021-05-17 17:54:32Yang Zhang, Vahid Noroozi, Evelina Bakhturina, Boris GinsburgAbstract
tract: Dialogue state tracking is an essential part of goal-oriented dialogue systems, while most of these state tracking models often fail to handle unseen services. In this paper, we propose SGD-QA, a simple and extensible model for schema-guided dialogue state tracking based on a question answering approach. The proposed multi-pass model shares a single encoder between the domain information and dialogue utterance. The domain's description represents the query and the dialogue utterance serves as the context. The model improves performance on unseen services by at least 1.6x compared to single-pass baseline models on the SGD dataset. SGD-QA shows competitive performance compared to state-of-the-art multi-pass models while being significantly more efficient in terms of memory consumption and training performance. We provide a thorough discussion on the model with ablation study and error analysis.
Abstract (translated)
URL
https://arxiv.org/abs/2105.08049
PDF
-
Unsupervised Deep Learning Methods for Biological Image Reconstruction
2021-05-17 17:43:46Mehmet Akçakaya, Burhaneddin Yaman, Hyungjin Chung, Jong Chul YeAbstract
tract: Recently, deep learning approaches have become the main research frontier for biological image reconstruction problems thanks to their high performance, along with their ultra-fast reconstruction times. However, due to the difficulty of obtaining matched reference data for supervised learning, there has been increasing interest in unsupervised learning approaches that do not need paired reference data. In particular, self-supervised learning and generative models have been successfully used for various biological imaging applications. In this paper, we overview these approaches from a coherent perspective in the context of classical inverse problems, and discuss their applications to biological imaging.
Abstract (translated)
URL
https://arxiv.org/abs/2105.08040
PDF
-
Fine-grained Interpretation and Causation Analysis in Deep NLP Models
Abstract
tract: This paper is a write-up for the tutorial on "Fine-grained Interpretation and Causation Analysis in Deep NLP Models" that we are presenting at NAACL 2021. We present and discuss the research work on interpreting fine-grained components of a model from two perspectives, i) fine-grained interpretation, ii) causation analysis. The former introduces methods to analyze individual neurons and a group of neurons with respect to a language property or a task. The latter studies the role of neurons and input features in explaining decisions made by the model. We also discuss application of neuron analysis such as network manipulation and domain adaptation. Moreover, we present two toolkits namely NeuroX and Captum, that support functionalities discussed in this tutorial.
Abstract (translated)
URL
https://arxiv.org/abs/2105.08039
PDF
-
Koopman NMPC: Koopman-based Learning and Nonlinear Model Predictive Control of Control-affine Systems
Abstract
tract: Koopman-based learning methods can potentially be practical and powerful tools for dynamical robotic systems. However, common methods to construct Koopman representations seek to learn lifted linear models that cannot capture nonlinear actuation effects inherent in many robotic systems. This paper presents a learning and control methodology that is a first step towards overcoming this limitation. Using the Koopman canonical transform, control-affine dynamics can be expressed by a lifted bilinear model. The learned model is used for nonlinear model predictive control (NMPC) design where the bilinear structure can be exploited to improve computational efficiency. The benefits for control-affine dynamics compared to existing Koopman-based methods are highlighted through an example of a simulated planar quadrotor. Prediction error is greatly reduced and closed loop performance similar to NMPC with full model knowledge is achieved.
Abstract (translated)
URL
https://arxiv.org/abs/2105.08036
PDF
-
Room to Grow: Understanding Personal Characteristics Behind Self Improvement Using Social Media
2021-05-17 17:30:30MeiXing Dong, Xueming Xu, Yiwei Zhang, Ian Stewart, Rada MihalceaAbstract
tract: Many people aim for change, but not everyone succeeds. While there are a number of social psychology theories that propose motivation-related characteristics of those who persist with change, few computational studies have explored the motivational stage of personal change. In this paper, we investigate a new dataset consisting of the writings of people who manifest intention to change, some of whom persist while others do not. Using a variety of linguistic analysis techniques, we first examine the writing patterns that distinguish the two groups of people. Persistent people tend to reference more topics related to long-term self-improvement and use a more complicated writing style. Drawing on these consistent differences, we build a classifier that can reliably identify the people more likely to persist, based on their language. Our experiments provide new insights into the motivation-related behavior of people who persist with their intention to change.
Abstract (translated)
URL
https://arxiv.org/abs/2105.08031
PDF
-
Stage-wise Fine-tuning for Graph-to-Text Generation
2021-05-17 17:15:29Qingyun Wang, Semih Yavuz, Victoria Lin, Heng Ji, Nazneen RajaniAbstract
tract: Graph-to-text generation has benefited from pre-trained language models (PLMs) in achieving better performance than structured graph encoders. However, they fail to fully utilize the structure information of the input graph. In this paper, we aim to further improve the performance of the pre-trained language model by proposing a structured graph-to-text model with a two-step fine-tuning mechanism which first fine-tunes model on Wikipedia before adapting to the graph-to-text generation. In addition to using the traditional token and position embeddings to encode the knowledge graph (KG), we propose a novel tree-level embedding method to capture the inter-dependency structures of the input graph. This new approach has significantly improved the performance of all text generation metrics for the English WebNLG 2017 dataset.
Abstract (translated)
URL
https://arxiv.org/abs/2105.08021
PDF
-
StrobeNet: Category-Level Multiview Reconstruction of Articulated Objects
2021-05-17 17:05:42Ge Zhang, Or Litany, Srinath Sridhar, Leonidas GuibasAbstract
tract: We present StrobeNet, a method for category-level 3D reconstruction of articulating objects from one or more unposed RGB images. Reconstructing general articulating object categories % has important applications, but is challenging since objects can have wide variation in shape, articulation, appearance and topology. We address this by building on the idea of category-level articulation canonicalization -- mapping observations to a canonical articulation which enables correspondence-free multiview aggregation. Our end-to-end trainable neural network estimates feature-enriched canonical 3D point clouds, articulation joints, and part segmentation from one or more unposed images of an object. These intermediate estimates are used to generate a final implicit 3D reconstruction.Our approach reconstructs objects even when they are observed in different articulations in images with large baselines, and animation of reconstructed shapes. Quantitative and qualitative evaluations on different object categories show that our method is able to achieve high reconstruction accuracy, especially as more views are added.
Abstract (translated)
URL
https://arxiv.org/abs/2105.08016
PDF
-
Supporting Context Monotonicity Abstractions in Neural NLI Models
2021-05-17 16:43:43Julia Rozanova, Deborah Ferreira, Mokanarangan Thayaparan, Marco Valentino, André FreitasAbstract
tract: Natural language contexts display logical regularities with respect to substitutions of related concepts: these are captured in a functional order-theoretic property called monotonicity. For a certain class of NLI problems where the resulting entailment label depends only on the context monotonicity and the relation between the substituted concepts, we build on previous techniques that aim to improve the performance of NLI models for these problems, as consistent performance across both upward and downward monotone contexts still seems difficult to attain even for state-of-the-art models. To this end, we reframe the problem of context monotonicity classification to make it compatible with transformer-based pre-trained NLI models and add this task to the training pipeline. Furthermore, we introduce a sound and complete simplified monotonicity logic formalism which describes our treatment of contexts as abstract units. Using the notions in our formalism, we adapt targeted challenge sets to investigate whether an intermediate context monotonicity classification task can aid NLI models' performance on examples exhibiting monotonicity reasoning.
Abstract (translated)
URL
https://arxiv.org/abs/2105.08008
PDF
-
Controlling an Inverted Pendulum with Policy Gradient Methods-A Tutorial
Abstract
tract: This paper provides the details of implementing two important policy gradient methods to solve the inverted pendulum problem. These are namely the Deep Deterministic Policy Gradient (DDPG) and the Proximal Policy Optimization (PPO) algorithm. The problem is solved by using an actor-critic model where an actor-network is used to learn the policy function and a critic network is to evaluate the actor-network by learning to estimate the Q function. Apart from briefly explaining the mathematics behind these two algorithms, the details of python implementation are provided which helps in demystifying the underlying complexity of the algorithm. In the process, the readers will be introduced to OpenAI/Gym, Tensorflow 2.x and Keras utilities used for implementing the above concepts.
Abstract (translated)
URL
https://arxiv.org/abs/2105.07998
PDF
-
Compacting Squares
2021-05-17 16:28:25Irina Kostitsyna, Irene Parada, Willem Sonke, Bettina Speckmann, Jules WulmsAbstract
tract: Edge-connected configurations of squares are a common model for modular robots in two dimensions. A well-established way to reconfigure such modular robots are so-called sliding moves. Dumitrescu and Pach [Graphs and Combinatorics, 2006] proved that it is always possible to reconfigure one edge-connected configuration of $n$ squares into any other using at most $O(n^2)$ sliding moves, while keeping the configuration connected at all times. For certain configurations $\Omega(n^2)$ sliding moves are necessary. However, significantly fewer moves may be sufficient. In this paper we present a novel input-sensitive in-place algorithm which requires only $O(\bar{P} n)$ sliding moves to transform one configuration into the other, where $\bar{P}$ is the maximum perimeter of the respective bounding boxes. Our Gather&Compact algorithm is built on the basic principle that well-connected components of modular robots can be transformed efficiently. Hence we iteratively increase the connectivity within a configuration, to finally arrive at a single solid $xy$-monotone component. We implemented Gather&Compact and compared it experimentally to the in-place modification by Moreno and Sacristán [EuroCG 2020] of the Dumitrescu and Pach algorithm (MSDP). Our experiments show that Gather&Compact consistently outperforms MSDP by a significant margin, on all types of square configurations.
Abstract (translated)
URL
https://arxiv.org/abs/2105.07997
PDF
-
Learning User Embeddings from Temporal Social Media Data: A Survey
2021-05-17 16:22:43Fatema Hasan, Kevin S. Xu, James R. Foulds, Shimei PanAbstract
tract: User-generated data on social media contain rich information about who we are, what we like and how we make decisions. In this paper, we survey representative work on learning a concise latent user representation (a.k.a. user embedding) that can capture the main characteristics of a social media user. The learned user embeddings can later be used to support different downstream user analysis tasks such as personality modeling, suicidal risk assessment and purchase decision prediction. The temporal nature of user-generated data on social media has largely been overlooked in much of the existing user embedding literature. In this survey, we focus on research that bridges the gap by incorporating temporal/sequential information in user representation learning. We categorize relevant papers along several key dimensions, identify limitations in the current work and suggest future research directions.
Abstract (translated)
URL
https://arxiv.org/abs/2105.07996
PDF
-
Learning to Automatically Catch Potholes in Worldwide Road Scene Images
2021-05-17 16:10:58J. Javier Yebes, David Montero, Ignacio ArriolaAbstract
tract: Among several road hazards that are present in any paved way in the world, potholes are one of the most annoying and also involving higher maintenance costs. There exists an increasing interest on the automated detection of these hazards enabled by technological and research progress. Our research work tackled the challenge of pothole detection from images of real world road scenes. The main novelty resides on the application of the latest progress in AI to learn the visual appearance of potholes. We built a large dataset of images with pothole annotations. They contained road scenes from different cities in the world, taken with different cameras, vehicles and viewpoints under varied environmental conditions. Then, we fine-tuned four different object detection models based on Faster R-CNN and SSD deep neural networks. We achieved high average precision and the pothole detector was tested on the Nvidia DrivePX2 platform with GPGPU capability, which can be embedded on vehicles. Moreover, it was deployed on a real vehicle to notify the detected potholes to a given IoT platform as part of AUTOPILOT H2020 project.
Abstract (translated)
URL
https://arxiv.org/abs/2105.07986
PDF
-
Gradient Masking and the Underestimated Robustness Threats of Differential Privacy in Deep Learning
2021-05-17 16:10:54Franziska Boenisch, Philip Sperl, Konstantin BöttingerAbstract
tract: An important problem in deep learning is the privacy and security of neural networks (NNs). Both aspects have long been considered separately. To date, it is still poorly understood how privacy enhancing training affects the robustness of NNs. This paper experimentally evaluates the impact of training with Differential Privacy (DP), a standard method for privacy preservation, on model vulnerability against a broad range of adversarial attacks. The results suggest that private models are less robust than their non-private counterparts, and that adversarial examples transfer better among DP models than between non-private and private ones. Furthermore, detailed analyses of DP and non-DP models suggest significant differences between their gradients. Additionally, this work is the first to observe that an unfavorable choice of parameters in DP training can lead to gradient masking, and, thereby, results in a wrong sense of security.
Abstract (translated)
URL
https://arxiv.org/abs/2105.07985
PDF
-
Unknown-box Approximation to Improve Optical Character Recognition Performance
2021-05-17 16:09:15Ayantha Randika, Nilanjan Ray, Xiao Xiao, Allegra LatimerAbstract
tract: Optical character recognition (OCR) is a widely used pattern recognition application in numerous domains. There are several feature-rich, general-purpose OCR solutions available for consumers, which can provide moderate to excellent accuracy levels. However, accuracy can diminish with difficult and uncommon document domains. Preprocessing of document images can be used to minimize the effect of domain shift. In this paper, a novel approach is presented for creating a customized preprocessor for a given OCR engine. Unlike the previous OCR agnostic preprocessing techniques, the proposed approach approximates the gradient of a particular OCR engine to train a preprocessor module. Experiments with two datasets and two OCR engines show that the presented preprocessor is able to improve the accuracy of the OCR up to 46% from the baseline by applying pixel-level manipulations to the document image. The implementation of the proposed method and the enhanced public datasets are available for download.
Abstract (translated)
URL
https://arxiv.org/abs/2105.07983
PDF
-
Learn to Intervene: An Adaptive Learning Policy for Restless Bandits in Application to Preventive Healthcare
2021-05-17 15:44:55Arpita Biswas, Gaurav Aggarwal, Pradeep Varakantham, Milind TambeAbstract
tract: In many public health settings, it is important for patients to adhere to health programs, such as taking medications and periodic health checks. Unfortunately, beneficiaries may gradually disengage from such programs, which is detrimental to their health. A concrete example of gradual disengagement has been observed by an organization that carries out a free automated call-based program for spreading preventive care information among pregnant women. Many women stop picking up calls after being enrolled for a few months. To avoid such disengagements, it is important to provide timely interventions. Such interventions are often expensive and can be provided to only a small fraction of the beneficiaries. We model this scenario as a restless multi-armed bandit (RMAB) problem, where each beneficiary is assumed to transition from one state to another depending on the intervention. Moreover, since the transition probabilities are unknown a priori, we propose a Whittle index based Q-Learning mechanism and show that it converges to the optimal solution. Our method improves over existing learning-based methods for RMABs on multiple benchmarks from literature and also on the maternal healthcare dataset.
Abstract (translated)
URL
https://arxiv.org/abs/2105.07965
PDF
-
DFENet: A Novel Dimension Fusion Edge Guided Network for Brain MRI Segmentation
2021-05-17 15:43:59Hritam Basak, Rukhshanda Hussain, Ajay RanaAbstract
tract: The rapid increment of morbidity of brain stroke in the last few years have been a driving force towards fast and accurate segmentation of stroke lesions from brain MRI images. With the recent development of deep-learning, computer-aided and segmentation methods of ischemic stroke lesions have been useful for clinicians in early diagnosis and treatment planning. However, most of these methods suffer from inaccurate and unreliable segmentation results because of their inability to capture sufficient contextual features from the MRI volumes. To meet these requirements, 3D convolutional neural networks have been proposed, which, however, suffer from huge computational requirements. To mitigate these problems, we propose a novel Dimension Fusion Edge-guided network (DFENet) that can meet both of these requirements by fusing the features of 2D and 3D CNNs. Unlike other methods, our proposed network uses a parallel partial decoder (PPD) module for aggregating and upsampling selected features, rich in important contextual information. Additionally, we use an edge-guidance and enhanced mixing loss for constantly supervising and improvising the learning process of the network. The proposed method is evaluated on publicly available Anatomical Tracings of Lesions After Stroke (ATLAS) dataset, resulting in mean DSC, IoU, Precision and Recall values of 0.5457, 0.4015, 0.6371, and 0.4969 respectively. The results, when compared to other state-of-the-art methods, outperforms them by a significant margin. Therefore, the proposed model is robust, accurate, superior to the existing methods, and can be relied upon for biomedical applications.
Abstract (translated)
URL
https://arxiv.org/abs/2105.07962
PDF
