arXiv subjects

Jinkyu Kim

Publications and source records attributed to Jinkyu Kim.

70 records · Page 4Linked to original sources

arXiv2021

Sound-Guided Semantic Image Manipulation

The recent success of the generative model shows that leveraging the multi-modal embedding space can manipulate an image using text information. However, manipulating an image with other sources rather than text, such as sound, is not easy due to the dynamic characteristics of the sources. Especially, sound can convey vivid emotions and dynamic expressions of the real world. Here, we propose a framework that directly encodes sound into the multi-modal (image-text) embedding space and manipulates an image from the space. Our audio encoder is trained to produce a latent representation from an audio input, which is forced to be aligned with image and text representations in the multi-modal embedding space. We use a direct latent optimization method based on aligned embeddings for sound-guided image manipulation. We also show that our method can mix text and audio modalities, which enrich the variety of the image modification. We verify the effectiveness of our sound-guided image manipulation quantitatively and qualitatively. We also show that our method can mix different modalities, i.e., text and audio, which enrich the variety of the image modification. The experiments on zero-shot audio classification and semantic-level image classification show that our proposed model outperforms other text and sound-guided state-of-the-art methods.

cs.GR↗

arXiv2021

A Scenario-Based Platform for Testing Autonomous Vehicle Behavior Prediction Models in Simulation

Behavior prediction remains one of the most challenging tasks in the autonomous vehicle (AV) software stack. Forecasting the future trajectories of nearby agents plays a critical role in ensuring road safety, as it equips AVs with the necessary information to plan safe routes of travel. However, these prediction models are data-driven and trained on data collected in real life that may not represent the full range of scenarios an AV can encounter. Hence, it is important that these prediction models are extensively tested in various test scenarios involving interactive behaviors prior to deployment. To support this need, we present a simulation-based testing platform which supports (1) intuitive scenario modeling with a probabilistic programming language called Scenic, (2) specifying a multi-objective evaluation metric with a partial priority ordering, (3) falsification of the provided metric, and (4) parallelization of simulations for scalable testing. As a part of the platform, we provide a library of 25 Scenic programs that model challenging test scenarios involving interactive traffic participant behaviors. We demonstrate the effectiveness and the scalability of our platform by testing a trained behavior prediction model and searching for failure scenarios.

cs.AI↗

arXiv2021

SelfReg: Self-supervised Contrastive Regularization for Domain Generalization

In general, an experimental environment for deep learning assumes that the training and the test dataset are sampled from the same distribution. However, in real-world situations, a difference in the distribution between two datasets, domain shift, may occur, which becomes a major factor impeding the generalization performance of the model. The research field to solve this problem is called domain generalization, and it alleviates the domain shift problem by extracting domain-invariant features explicitly or implicitly. In recent studies, contrastive learning-based domain generalization approaches have been proposed and achieved high performance. These approaches require sampling of the negative data pair. However, the performance of contrastive learning fundamentally depends on quality and quantity of negative data pairs. To address this issue, we propose a new regularization method for domain generalization based on contrastive learning, self-supervised contrastive regularization (SelfReg). The proposed approach use only positive data pairs, thus it resolves various problems caused by negative pair sampling. Moreover, we propose a class-specific domain perturbation layer (CDPL), which makes it possible to effectively apply mixup augmentation even when only positive data pairs are used. The experimental results show that the techniques incorporated by SelfReg contributed to the performance in a compatible manner. In the recent benchmark, DomainBed, the proposed method shows comparable performance to the conventional state-of-the-art alternatives. Codes are available at https://github.com/dnap512/SelfReg.

cs.CV↗

arXiv2020

Attentional Bottleneck: Towards an Interpretable Deep Driving Network

Deep neural networks are a key component of behavior prediction and motion generation for self-driving cars. One of their main drawbacks is a lack of transparency: they should provide easy to interpret rationales for what triggers certain behaviors. We propose an architecture called Attentional Bottleneck with the goal of improving transparency. Our key idea is to combine visual attention, which identifies what aspects of the input the model is using, with an information bottleneck that enables the model to only use aspects of the input which are important. This not only provides sparse and interpretable attention maps (e.g. focusing only on specific vehicles in the scene), but it adds this transparency at no cost to model accuracy. In fact, we find slight improvements in accuracy when applying Attentional Bottleneck to the ChauffeurNet model, whereas we find that the accuracy deteriorates with a traditional visual attention model.

cs.CV↗

arXiv2019

Grounding Human-to-Vehicle Advice for Self-driving Vehicles

Recent success suggests that deep neural control networks are likely to be a key component of self-driving vehicles. These networks are trained on large datasets to imitate human actions, but they lack semantic understanding of image contents. This makes them brittle and potentially unsafe in situations that do not match training data. Here, we propose to address this issue by augmenting training data with natural language advice from a human. Advice includes guidance about what to do and where to attend. We present the first step toward advice giving, where we train an end-to-end vehicle controller that accepts advice. The controller adapts the way it attends to the scene (visual attention) and the control (steering and speed). Attention mechanisms tie controller behavior to salient objects in the advice. We evaluate our model on a novel advisable driving dataset with manually annotated human-to-vehicle advice called Honda Research Institute-Advice Dataset (HAD). We show that taking advice improves the performance of the end-to-end network, while the network cues on a variety of visual features that are provided by advice. The dataset is available at https://usa.honda-ri.com/HAD.

cs.CV↗

arXiv2019

HATS: A Hierarchical Graph Attention Network for Stock Movement Prediction

Many researchers both in academia and industry have long been interested in the stock market. Numerous approaches were developed to accurately predict future trends in stock prices. Recently, there has been a growing interest in utilizing graph-structured data in computer science research communities. Methods that use relational data for stock market prediction have been recently proposed, but they are still in their infancy. First, the quality of collected information from different types of relations can vary considerably. No existing work has focused on the effect of using different types of relations on stock market prediction or finding an effective way to selectively aggregate information on different relation types. Furthermore, existing works have focused on only individual stock prediction which is similar to the node classification task. To address this, we propose a hierarchical attention network for stock prediction (HATS) which uses relational data for stock market prediction. Our HATS method selectively aggregates information on different relation types and adds the information to the representations of each company. Specifically, node representations are initialized with features extracted from a feature extraction module. HATS is used as a relational modeling module with initialized node representations. Then, node representations with the added information are fed into a task-specific layer. Our method is used for predicting not only individual stock prices but also market index movements, which is similar to the graph classification task. The experimental results show that performance can change depending on the relational data used. HATS which can automatically select information outperformed all the existing methods.

q-fin.ST↗

arXiv2019

Periphery-Fovea Multi-Resolution Driving Model guided by Human Attention

Inspired by human vision, we propose a new periphery-fovea multi-resolution driving model that predicts vehicle speed from dash camera videos. The peripheral vision module of the model processes the full video frames in low resolution. Its foveal vision module selects sub-regions and uses high-resolution input from those regions to improve its driving performance. We train the fovea selection module with supervision from driver gaze. We show that adding high-resolution input from predicted human driver gaze locations significantly improves the driving accuracy of the model. Our periphery-fovea multi-resolution model outperforms a uni-resolution periphery-only model that has the same amount of floating-point operations. More importantly, we demonstrate that our driving model achieves a significantly higher performance gain in pedestrian-involved critical situations than in other non-critical situations.

cs.CV↗

arXiv2019

Extended framework of Hamilton's principle applied to Duffing oscillation

The paper begins with a novel variational formulation of Duffing equation using the extended framework of Hamilton's principle (EHP). This formulation properly accounts for initial conditions, and it recovers all the governing differential equations as its Euler-Lagrange equation. Thus, it provides elegant structure for the development of versatile temporal finite element methods. Herein, the simplest temporal finite element method is presented by adopting linear temporal shape functions. Numerical examples are included to verify and investigate performance of non-iterative algorithm in the developed method.

math.NA↗

arXiv2018

Predicting Driver Attention in Critical Situations

Robust driver attention prediction for critical situations is a challenging computer vision problem, yet essential for autonomous driving. Because critical driving moments are so rare, collecting enough data for these situations is difficult with the conventional in-car data collection protocol---tracking eye movements during driving. Here, we first propose a new in-lab driver attention collection protocol and introduce a new driver attention dataset, Berkeley DeepDrive Attention (BDD-A) dataset, which is built upon braking event videos selected from a large-scale, crowd-sourced driving video dataset. We further propose Human Weighted Sampling (HWS) method, which uses human gaze behavior to identify crucial frames of a driving dataset and weights them heavily during model training. With our dataset and HWS, we built a driver attention prediction model that outperforms the state-of-the-art and demonstrates sophisticated behaviors, like attending to crossing pedestrians but not giving false alarms to pedestrians safely walking on the sidewalk. Its prediction results are nearly indistinguishable from ground-truth to humans. Although only being trained with our in-lab attention data, the model also predicts in-car driver attention data of routine driving with state-of-the-art accuracy. This result not only demonstrates the performance of our model but also proves the validity and usefulness of our dataset and data collection protocol.

cs.CV↗

arXiv2018

Textual Explanations for Self-Driving Vehicles

Deep neural perception and control networks have become key components of self-driving vehicles. User acceptance is likely to benefit from easy-to-interpret textual explanations which allow end-users to understand what triggered a particular behavior. Explanations may be triggered by the neural controller, namely introspective explanations, or informed by the neural controller's output, namely rationalizations. We propose a new approach to introspective explanations which consists of two parts. First, we use a visual (spatial) attention model to train a convolutional network end-to-end from images to the vehicle control commands, i.e., acceleration and change of course. The controller's attention identifies image regions that potentially influence the network's output. Second, we use an attention-based video-to-text model to produce textual explanations of model actions. The attention maps of controller and explanation model are aligned so that explanations are grounded in the parts of the scene that mattered to the controller. We explore two approaches to attention alignment, strong- and weak-alignment. Finally, we explore a version of our model that generates rationalizations, and compare with introspective explanations on the same video segments. We evaluate these models on a novel driving dataset with ground-truth human explanations, the Berkeley DeepDrive eXplanation (BDD-X) dataset. Code is available at https://github.com/JinkyuKimUCB/explainable-deep-driving.

cs.CV↗

arXiv2017

Interpretable Learning for Self-Driving Cars by Visualizing Causal Attention

Deep neural perception and control networks are likely to be a key component of self-driving vehicles. These models need to be explainable - they should provide easy-to-interpret rationales for their behavior - so that passengers, insurance companies, law enforcement, developers etc., can understand what triggered a particular behavior. Here we explore the use of visual explanations. These explanations take the form of real-time highlighted regions of an image that causally influence the network's output (steering control). Our approach is two-stage. In the first stage, we use a visual attention model to train a convolution network end-to-end from images to steering angle. The attention model highlights image regions that potentially influence the network's output. Some of these are true influences, but some are spurious. We then apply a causal filtering step to determine which input regions actually influence the output. This produces more succinct visual explanations and more accurately exposes the network's behavior. We demonstrate the effectiveness of our model on three datasets totaling 16 hours of driving. We first show that training with attention does not degrade the performance of the end-to-end network. Then we show that the network causally cues on a variety of features that are used by humans while driving.

cs.CV↗

arXiv2013

Higher order temporal finite element methods through mixed formulations

The EHP and the MCAP provide new rigorous weak variational formalism for a broad range of initial boundary value problems in mathematical physics and mechanics. Both approaches utilize the mixed formulation and lead to the development of various space-time finite element methods. In this paper, their potential when adopting temporally higher order approximations is investigated. The classical single-degree-of-freedom dynamical systems are primarily considered to validate and to investigate the performance of the numerical algorithms developed from both formulations. For the undamped system, all the algorithms are found to be symplectic and unconditionally stable with respect to the time step. On the other hand, for the damped system, the approach is shown to be robust and to be accurate with good convergence characteristics.

math.DS↗

arXiv2012

Multiplying decomposition of stress/strain, constitutive/compliance relations, and strain energy

To account for phenomenological theories and a set of invariants, stress and strain are usually decomposed into a pair of pressure and deviatoric stress and a pair of volumetric strain and deviatoric strain. However, the conventional decomposition method only focuses on individual stress and strain, so that cannot be directly applied to either formulation in Finite Element Method (FEM) or Boundary Element Method (BEM). In this paper, a simpler, more general, and widely applicable decomposition is suggested. A new decomposition method adopts multiplying decomposition tensors or matrices to not only stress and strain but also constitutive and compliance relation. With this, we also show its practical usage on FEM and BEM in terms of tensors and matrices.

math-ph↗

arXiv2012

Extended Hamilton's principle

Hamilton's principle is extended to have compatible initial conditions to the strong form. To use a number of computational and theoretical benefits for dynamical systems, the mixed variational formulation is preferred in the systems other than particle systems. With this formulation and the Rayleigh's dissipation function, we could have all the pertinent initial/boundary conditions for both conservative and non-conservative dynamical system. Based upon the extension framework of Hamilton's principle, the numerical method for representative lumped parameter models is also developed through applying Galerkin's method to time domain with the discussion of its numerical properties and simulation results.

math-ph↗

arXiv2011

The mixed convolved action

A series of stationary principles are developed for dynamical systems by formulating the concept of mixed convolved action, which is written in terms of mixed variables, using temporal convolutions and fractional derivatives. Dynamical systems with discrete and continuous spatial representations are considered as initial applications. In each case, a single scalar functional provides the governing differential equations, along with all the pertinent initial and boundary conditions, as the Euler-Lagrange equations emanating from the stationarity of this mixed convolved action. Both conservative and non-conservative processes can be considered within a common framework, thus resolving a long-standing limitation of variational approaches for dynamical systems. Several results in fractional calculus also are developed.

math-ph↗

arXiv2011

HiTRACE: High-throughput robust analysis for capillary electrophoresis

Motivation: Capillary electrophoresis (CE) of nucleic acids is a workhorse technology underlying high-throughput genome analysis and large-scale chemical mapping for nucleic acid structural inference. Despite the wide availability of CE-based instruments, there remain challenges in leveraging their full power for quantitative analysis of RNA and DNA structure, thermodynamics, and kinetics. In particular, the slow rate and poor automation of available analysis tools have bottlenecked a new generation of studies involving hundreds of CE profiles per experiment. Results: We propose a computational method called high-throughput robust analysis for capillary electrophoresis (HiTRACE) to automate the key tasks in large-scale nucleic acid CE analysis, including the profile alignment that has heretofore been a rate-limiting step in the highest throughput experiments. We illustrate the application of HiTRACE on thirteen data sets representing 4 different RNAs, three chemical modification strategies, and up to 480 single mutant variants; the largest data sets each include 87,360 bands. By applying a series of robust dynamic programming algorithms, HiTRACE outperforms prior tools in terms of alignment and fitting quality, as assessed by measures including the correlation between quantified band intensities between replicate data sets. Furthermore, while the smallest of these data sets required 7 to 10 hours of manual intervention using prior approaches, HiTRACE quantitation of even the largest data sets herein was achieved in 3 to 12 minutes. The HiTRACE method therefore resolves a critical barrier to the efficient and accurate analysis of nucleic acid structure in experiments involving tens of thousands of electrophoretic bands.

q-bio.QM↗