Transfer Learning for Human & AI

Recent state-of-the-art active learning methods have mostly leveragedGenerative Adversarial Networks (GAN) for sample acquisition . However, GAN isusually known to suffer from instability and sensitivity to hyper-parameters . In contrast to these methods, we propose in this paper a novel active learningframework that we call Maximum Classifier Discrepancy for Active Learning(MCDAL) which takes the prediction discrepancies between multiple classifiers .…

Deep learning models have gained great popularity in statistical modeling . Theadvantage of deep learning models is that their solutions are difficult tointerpret and explain . We propose a new network architecture that sharessimilar features as generalized linear models, but provides superior predictivepower benefiting from the art of representation learning .…

Dawar and Wilsenach (ICALP 2020) show an exponential separation between the sizes of symmetric arithmeticcircuits for computing the determinant and the permanent . The symmetryrestriction is that the circuits which take a matrix input are unchanged by a permutation applied simultaneously to the rows and columns of the matrix .…

Dawar and Wilsenach (ICALP 2020) show an exponential separation between the sizes of symmetric arithmeticcircuits for computing the determinant and the permanent . The symmetryrestriction is that the circuits which take a matrix input are unchanged by a permutation applied simultaneously to the rows and columns of the matrix .…

This paper explores the convenience of using additional signals apart fromelectroencephalograms . The best overall model, an ensemble of Depth-wiseSeparational Convolutional Neural Networks, has achieved an accuracy of 86.06\% with a Cohen’s Kappa of 0.80 and a $F_{1}$ of $F_1 of $1.77 .…

Viewing neural network models in terms of their loss landscapes has a longhistory in the statistical mechanics approach to learning . Local metrics (such as the smoothness of the loss landscape) have been shown tocorrelate with global properties of the model .…

Graph neural networks (GNNs) have achieved remarkable success as a framework for deep learning on graph-structured data . However, GNNs are fundamentallylimited by their tree-structuring inductive bias . We propose to augment the GNN message-passing operations with information on ego graphs (i.e.,…

Legged robots have been shown to be effective in navigating unstructured environments . There has been much success in learning locomotionpolicies for quadruped robots, but there is little research on how to incorporatehuman knowledge to facilitate this learning process . In this paper, wedemonstrate that human knowledge in the form of LTL formulas can be applied to quadruped locomotion learning within a Reward Machine framework .…

Privacy is important for all individuals in everyday life . With emergingtechnologies, smartphones with AR, various social networking applications and modes of surveillance, they tend to intrudeprivacy . This study aimed to explore and discover various concerns related toperception of privacy in this era of ubiquitous technologies .…

The Earth’s primary source of energy is the radiant energy generated by the sun . A minor change in the solar irradiancecan have a significant impact on the Earth’s climate and atmosphere . The method agrees well with the state-of-the-art physics-based reconstruction models .…

Density estimation plays a crucial role in many data analysis tasks . It is used in tasks as diverse as analyzing population data, spatiallocations in 2D sensor readings, or reconstructing scenes from 3D scans . In this paper, we introduce a learned, data-driven deep density estimation (DDE)to infer PDFs in an accurate and efficient manner, while being independent of domain dimensionality or sample size .…

This document describes the generalized moving peaks benchmark (GMPB) and how it can be used to generate problem instances for continuous large-scale dynamic optimization problems . It presents a set of 15 benchmark problems, the relevantsource code, and a performance indicator .…

Understanding emotions that people express during large-scale crises helps inform policy makers and first responders about theemotional states of the population . We present CovidEmo, ~1K tweets labeled withemotions. We examine how well large pre-trained language models generalizeacross domains and crises in the task of perceived emotion prediction .…

StudSat1, which was successfully launched on 12th July 2010, is the first Pico satellite developed in India by undergraduate students from seven different engineering colleges across South India . StudSat2 is India’s first twin satellite mission having twonanosatellites whose overall mass is less than 10kg .…

Wavelets have proven to be highly successful in several signal and image processing applications . We aim atdesigning data-independent wavelets by training filterbank autoencoders, which .precludes the need for customized datasets . We show that anear-zero training loss implies that the learnt filters satisfy the perfect .reconstruction…

The CV-based system allows the user to control the swarm behavior without additional devices through human gestures and motions in real-time . The proposed system can be potentially applied in complex environment exploration, spraypainting using drones, and interactive drone shows .…

Constellation is anetwork that learns relational abstractions of static visual scenes, and generalises these abstractions over sensory particularities . We further show that thisbasis, along with language association, provides a means to imagine sensorycontent in new ways . This work is a first step in the explicit representation of visual relationships and using them for complex cognitive procedures .…

Mobile malware are malicious programs that target mobile devices . They are anincreasing problem, as seen in the rise of detected mobile malware samples peryear . The number of active smartphone users is expected to grow, stressing theimportance of research on the detection of mobile malware .…

We describe a project to formalize Galois theory using the Lean theoremprover . We discuss some of the challenges we faced and the decisions we made in the course of this project . The maintheorems we formalized are the primitive element theorem, the fundamentaltheorem of Galois Theory, and the equivalence of several characterizations offinite degree Galois extensions .…

We present four different robust transfer learning strategies for robust mobile scene recognition . Fine-Tuning in combination withextensive data augmentation improves accuracy and robustness in mobile robot place recognition . We achieved state-of-the-art results using variousbaseline convolutional neural networks and showed the robustness againstlighting and viewpoint changes in challenging mobile robot places recognition .…

Future urban transportation concepts include a mixture of ground and air vehicles with varying degrees of autonomy in a congested environment . Safe and efficient transportation requires reasoning about the 3Dflow of traffic and properly modeling uncertainty . This paper explores a Bayesian approach that captures our uncertainty in the map given training data .…

In this paper we introduce a simple modal logic framework to reason about theexpertise of an information source . In the framework, a source is an expert on a proposition $p$ if they are able to correctly determine the truth value of$p$ in any possible world .…

Value iteration is a well-known method of solving Markov Decision Processes . However, the computational cost of value iteration quickly becomesfeasible as the size of the state space increases . In this paper, we propose an intuitive algorithm for solving MDPsthat reduces the cost of updates by dynamically grouping together states with similar cost-to-go values .…

We introduce a runtime-efficient tree hashing algorithm for the identification of isomorphic subtrees . We propose a simple diversity-preservationmechanism with promising results on a collection of symbolic regressionbenchmark problems . The algorithm has two important applications: fast calculation ofpopulation diversity and algebraic simplification of symbolic expression trees .…

Developing a framework for the locomotion of a hexapod is a complex task that has extensive hardware and computational requirements . Our locomotion model draws inspiration from the structure of acockroach, with its fairly simple central nervous system, and results in our model being computationally inexpensive with simpler control mechanisms .…

CARP (Collision Avoidance byReciprocal Projections) is effective even when the estimates of otheragents’ positions and velocities are noisy . The method’s main computational step involves the solution of a small convex optimization problem, which can be easily solved in practice, even on embedded platforms .…

Deep Q Network (DQN) has several limitations when applied in planning a path in an environment with a number of dilemmas according to our experiment . In this context, this paper proposes animproved Double DQN to solve the problem by reference to A* andRapidly-Exploring Random Tree (RRT) In order to achieve the rich experimentsin experience replay, the initialization of robot in each training round is defined based on RRT strategy .…

Organ matching decision is the most critical decision to assign limited viable organs to the most suitable patients . Currently, organ matching decisions were only made by matching scores calculated viascoring models . AWTR improves performance of the current scoring models by using limited actual matching performance in historical data set as well as thecollected covariates from organ donors and patients .…

Aligned Disentangling Generative AdversarialNetwork (AD-GAN) introduces representationdisentanglement to separate content representation from style representation . With this framework, spatial structure can be preserved explicitly, enabling asignificant reduction of macro-level lossy transformation . AD-GAN leads to significant improvement over the current best unsupervised methods by an average 17.8% relatively (w.r.t.…

A paper develops a new shape model that allows synthesizing noveldistance views by optimizing a continuous signed directional distance function . Unlike an SDF, an SDDF measures distance in a given direction . This allows us to form a shape model without 3D shape supervision, using only distancemeasurements, readily available from depth camera or Lidar sensors .…

DistributionAlignment and Random Sampling (DARS) method to produce unbiased pseudo labelsthat match the true class distribution estimated from the labeled data . Code will be available athttps://://github.com/CVMI-Lab/DARS . Experiments on both Cityscapes and PASCAL VOC 2012 datasets demonstrate effectiveness of our approach .…

Heatmap-based methods dominate in the field of human pose estimation by modelling the output distribution through likelihood heatmaps . Residual Log-likelihood Estimation(RLE) is effective, efficient and flexible . Compared to the conventional regression paradigm, regression with RLE bring 12.4 mAPimprovement on MSCOCO without any test-time overhead .…

Unrealistic feature suppression (UFS) module keeps high-quality features and suppresses unrealistic features . UFS module keeps the training stability of networks and improves the quality ofgenerated images . We demonstrate effectiveness of the module on various models such as WGAN-GP, SNGAN, and BigGAN .…

A paper uses distanceregularized level set (DRL SE) to explore the segmentation effect of epicardiumand endocardium . Five CT images are used to verify the proposedmethod, and image quality evaluation indexes such as dice score and Hausdorffdistance are used . The results showed that the researchers could separate the inner and outer membrane very well (endocardiumdice = 0.9253, Hausorfff = 7.8740) and epicocardium Hausdice= 0.9687 .…

Most image-to-image translation methods focus on learning mappings across domains with the assumption that images share content but have their own domain-specific information known as style . In this work, we consider the scenariowhere the target image has a very low resolution .…

Compact convolutional neural networks (CNNs) have witnessed exceptionalimprovements in performance in recent years . However, they still fail toprovide the same predictive power as CNNs with a large number of parameters . Diverse features present in activation maps indicate presence of unique descriptors necessary to distinguish between objects of differentclasses .…

A novel shape-perception network (HSPN) is proposed to reconstruct the 3D point clouds (PCs) of specific brains from one single incomplete image with low latency . 3D shape reconstruction is essential in the navigation of minimally-invasive and auto robot-guided surgeries whose operating environments are indirect and narrow .…

Language instruction plays an essential role in the natural language groundednavigation tasks . We propose a DynamicReinforced Instruction Attacker (DR-Attacker) which learns to mislead thenavigator to move to the wrong target by destroying the most instructive information in instructions at different timesteps .…

This short contribution presents a method for generating $N$-point sphericalconfigurations with low mesh ratios . The method extends Caspar-Klug icosahedral point-grids to non-icosahedral nets . The proposed procedure may be applied iteratively and is parameterised by a sequence of integer pairs .…

The combined use of multiple modalities enables accurate pedestrian detection under poor lighting conditions by using the high visibility areas from thesemodalities together . The vital assumption for the combination use is that thereis no or only a weak misalignment between the two modalities .…

Visual DomainAdaptation (VisDA) 2021 competition tests models’ ability to adapt to novel test distributions and handle distributional shift . Ourchallenge draws on large-scale publicly available datasets but constructs the evaluation across domains . Performance will be measured using a rigorous protocol,comparing to state-of-the-art domain adaptation methods with the help ofestablished metrics .…

We consider a family of constrained optimization problems arising in machine learning that involve optimizing a non-decomposable evaluation metric with a certain thresholded form . We show how the resulting optimization problem can be solved using standard gradient based methods .…

We present a four-pronged approach to build firefighter’s situationalawareness for the first time in the literature . We construct a series of deeplearning frameworks built on top of one another to enhance the safety, efficiency, and successful completion of rescue missions conducted by firefighters in emergency first response settings .…

The full range of activity in a temporal network is captured in its edgeactivity data — time series encoding the tie strengths or on-off dynamics of each edge in the network . In many practical applications, edge-leveldata are unavailable, and the network analyses must rely instead on nodeactivity data .…

Existing Unsupervised Domain Adaptation (UDA) literature adopts the covariateshift and conditional shift assumptions, which essentially encourage models to learn common features across domains . However, due to the lack of supervision in the target domain, they suffer from the semantic loss .…

Meta-learning provides a promising way for learning to efficiently learn andachieve great success in many applications . Most meta-learning literature focuses on dealing with tasks from a same domain, making it brittle to generalize to tasks from the other unseen domains .…

Skyline plays a pivotal role in mountainous visual geo-localization and localization/navigation of planetary rovers/UAVs and virtual/augmented realityapplications . We present a novel mountainous skyline detection approach wherewe adapt a shallow learning approach to learn a set of filters to discriminate between edges belonging to sky-mountain boundary and others coming from different regions .…

Semantic segmentation on 3D point clouds is an important task for 3D sceneunderstanding . We train a semantic point cloud segmentation network with only asmall portion of points being labeled . We argue that we can better utilize thelimited supervision information as we densely propagate the supervision signalfrom the labeled points to other points within and across the input samples .…

Recent state-of-the-art active learning methods have mostly leveragedGenerative Adversarial Networks (GAN) for sample acquisition . However, GAN isusually known to suffer from instability and sensitivity to hyper-parameters . In contrast to these methods, we propose in this paper a novel active learningframework that we call Maximum Classifier Discrepancy for Active Learning(MCDAL) which takes the prediction discrepancies between multiple classifiers .…

Most of existing studies on adaptive submodular optimization focus on theaverage-case, i.e., their objective is to find a policy that maximizes theexpected utility over a known distribution of realizations . We introduce a new class ofstochastic functions, called \emph{worst-case submodular function .…