Modern one-stage video instance segmentation networks suffer from two limitations. First, convolutional features are neither aligned with anchor boxes nor with ground-truth bounding boxes, reducing the mask sensitivity to spatial location. Second, a video is directly divided into individual frames for frame-level instance segmentation, ignoring the temporal correlation between adjacent frames. To address these issues, we propose a simple yet effective one-stage video instance segmentation framework by spatial calibration and temporal fusion, namely STMask. To ensure spatial feature calibration with ground-truth bounding boxes, we first predict regressed bounding boxes around ground-truth bounding boxes, and extract features from them for frame-level instance segmentation. To further explore temporal correlation among video frames, we aggregate a temporal fusion module to infer instance masks from each frame to its adjacent frames, which helps our framework to handle challenging videos such as motion blur, partial occlusion and unusual object-to-camera poses. Experiments on the YouTube-VIS valid set show that the proposed STMask with ResNet-50/-101 backbone obtains 33.5 % / 36.8 % mask AP, while achieving 28.6 / 23.4 FPS on video instance segmentation. The code is released online https://github.com/MinghanLi/STMask.
In this note an assessment of the condition \(K_w/K=S_w/S\) is made to interpret its meaning to the Passineti's theory of distribution\cite{pasinetti1962rate}. This condition leads the theory to enforce the result \(s_w\rightarrow0\) as \(P_w\rightarrow 0\), which is the Pasinetti's description about behavior of the workers. We find that the Pasinetti's claim, of long run worker's propensity to save as not influencing the distribution of income between profits and the wage can not be generalized. This claim is found to be valid only when \(W>>P_w\) or \(P_w=0\) with \(W\ne0\). In practice, the Pasinetti's condition imposes a restriction on the actual savings by one of the agents to a lower level compared to its full saving capacity. An implied relationship between the propensities to save by workers and capitalists shows that the Passineti's condition can be practiced only through a contract for a constant value of \(R=s_w/s_c\), to be agreed upon between the workers and the capitalists. It is showed that the Passineti's condition can not be described as a dynamic equilibrium of economic growth. Implementation of this condition (a) may lead to accumulation of unsaved income, (b) reduces growth of capital, (c)is not practicable and (d) is not warranted. We have also presented simple mathematical steps for the derivation of the Pasinetti's final equation compared to those presented in \cite{pasinetti1962rate}
This paper proposes a simple method which solves an open problem of multi-view 3D-Reconstruction for objects with unknown and generic surface materials, imaged by a freely moving camera and a freely moving point light source. The object can have arbitrary (e.g. non-Lambertian), spatially-varying (or everywhere different) surface reflectances (svBRDF). Our solution consists of two smallsized neural networks (dubbed the 'Shape-Net' and 'BRDFNet'), each having about 1,000 neurons, used to parameterize the unknown shape and unknown svBRDF, respectively. Key to our method is a special network design (namely, a ResNet with a global feedback or 'ring' connection), which has a provable guarantee for finding a valid diffeomorphic shape parameterization. Despite the underlying problem is highly non-convex hence impractical to solve by traditional optimization techniques, our method converges reliably to high quality solutions, even without initialization. Extensive experiments demonstrate the superiority of our method, and it naturally enables a wide range of special-effect applications including novel-view-synthesis, relighting, material retouching, and shape exchange without additional coding effort. We encourage the reader to view our demo video for better visualizations.
Discourse signals are often implicit, leaving it up to the interpreter to draw the required inferences. At the same time, discourse is embedded in a social context, meaning that interpreters apply their own assumptions and beliefs when resolving these inferences, leading to multiple, valid interpretations. However, current discourse data and frameworks ignore the social aspect, expecting only a single ground truth. We present the first discourse dataset with multiple and subjective interpretations of English conversation in the form of perceived conversation acts and intents. We carefully analyze our dataset and create computational models to (1) confirm our hypothesis that taking into account the bias of the interpreters leads to better predictions of the interpretations, (2) and show disagreements are nuanced and require a deeper understanding of the different contextual factors. We share our dataset and code at http://github.com/elisaF/subjective_discourse.
We propose a combination of a variational autoencoder and a transformer based model which fully utilises graph convolutional and graph pooling layers to operate directly on graphs. The transformer model implements a novel node encoding layer, replacing the position encoding typically used in transformers, to create a transformer with no position information that operates on graphs, encoding adjacent node properties into the edge generation process. The proposed model builds on graph generative work operating on graphs with edge features, creating a model that offers improved scalability with the number of nodes in a graph. In addition, our model is capable of learning a disentangled, interpretable latent space that represents graph properties through a mapping between latent variables and graph properties. In experiments we chose a benchmark task of molecular generation, given the importance of both generated node and edge features. Using the QM9 dataset we demonstrate that our model performs strongly across the task of generating valid, unique and novel molecules. Finally, we demonstrate that the model is interpretable by generating molecules controlled by molecular properties, and we then analyse and visualise the learned latent representation.
The angular measure on the unit sphere characterizes the first-order dependence structure of the components of a random vector in extreme regions and is defined in terms of standardized margins. Its statistical recovery is an important step in learning problems involving observations far away from the center. In the common situation that the components of the vector have different distributions, the rank transformation offers a convenient and robust way of standardizing data in order to build an empirical version of the angular measure based on the most extreme observations. However, the study of the sampling distribution of the resulting empirical angular measure is challenging. It is the purpose of the paper to establish finite-sample bounds for the maximal deviations between the empirical and true angular measures, uniformly over classes of Borel sets of controlled combinatorial complexity. The bounds are valid with high probability and, up to logarithmic factors, scale as the square root of the effective sample size. The bounds are applied to provide performance guarantees for two statistical learning procedures tailored to extreme regions of the input space and built upon the empirical angular measure: binary classification in extreme regions through empirical risk minimization and unsupervised anomaly detection through minimum-volume sets of the sphere.
This paper works towards unifying two popular approaches in the safety control community: Hamilton-Jacobi (HJ) reachability and Control Barrier Functions (CBFs). HJ Reachability has methods for direct construction of value functions that provide safety guarantees and safe controllers, however the online implementation can be overly conservative and/or rely on chattering bang-bang control. The CBF community has methods for safe-guarding controllers in the form of point-wise optimization using quadratic programs (CBF-QP), where the CBF-based safety certificate is used as a constraint. However, finding a valid CBF for a general dynamical system is challenging. This paper unifies these two methods by introducing a new reachability formulation inspired by the structure of CBFs to construct a Control Barrier-Value Function (CBVF). We verify that CBVF is a viscosity solution to a novel Hamilton-Jacobi-Isaacs Variational Inequality and preserves the same safety guarantee as the original reachability formulation. Finally, inspired by the CBF-QP, we propose a QP-based online control synthesis for systems affine in control and disturbance, whose solution is always the CBVF's optimal control signal robust to bounded disturbance. We demonstrate the benefit of using the CBVFs for double-integrator and Dubins car systems by comparing it to previous methods.
DoubleML is an open-source Python library implementing the double machine learning framework of Chernozhukov et al. (2018) for a variety of causal models. It contains functionalities for valid statistical inference on causal parameters when the estimation of nuisance parameters is based on machine learning methods. The object-oriented implementation of DoubleML provides a high flexibility in terms of model specifications and makes it easily extendable. The package is distributed under the MIT license and relies on core libraries from the scientific Python ecosystem: scikit-learn, numpy, pandas, scipy, statsmodels and joblib. Source code, documentation and an extensive user guide can be found at https://github.com/DoubleML/doubleml-for-py and https://docs.doubleml.org.
This paper presents a soft-label anonymous gastric X-ray image distillation method based on a gradient descent approach. The sharing of medical data is demanded to construct high-accuracy computer-aided diagnosis (CAD) systems. However, the large size of the medical dataset and privacy protection are remaining problems in medical data sharing, which hindered the research of CAD systems. The idea of our distillation method is to extract the valid information of the medical dataset and generate a tiny distilled dataset that has a different data distribution. Different from model distillation, our method aims to find the optimal distilled images, distilled labels and the optimized learning rate. Experimental results show that the proposed method can not only effectively compress the medical dataset but also anonymize medical images to protect the patient's private information. The proposed approach can improve the efficiency and security of medical data sharing.
Image denoising and artefact removal are complex inverse problems admitting multiple valid solutions. Unsupervised diversity restoration, that is, obtaining a diverse set of possible restorations given a corrupted image, is important for ambiguity removal in many applications such as microscopy where paired data for supervised training are often unobtainable. In real world applications, imaging noise and artefacts are typically hard to model, leading to unsatisfactory performance of existing unsupervised approaches. This work presents an interpretable approach for unsupervised and diverse image restoration. To this end, we introduce a capable architecture called Hierarchical DivNoising (HDN) based on hierarchical Variational Autoencoder. We show that HDN learns an interpretable multi-scale representation of artefacts and we leverage this interpretability to remove imaging artefacts commonly occurring in microscopy data. Our method achieves state-of-the-art results on twelve benchmark image denoising datasets while providing access to a whole distribution of sensibly restored solutions. Additionally, we demonstrate on three real microscopy datasets that HDN removes artefacts without supervision, being the first method capable of doing so while generating multiple plausible restorations all consistent with the given corrupted image.
Humans and animals are able to generalize or transfer information from previous experience so that they can behave appropriately in novel situations. What mechanisms--computations, representations, and neural systems--give rise to this remarkable ability? The members of this Generative Adversarial Collaboration (GAC) come from a range of academic backgrounds but are all interested in uncovering the mechanisms of generalization. We started out this GAC with the aim of arbitrating between two alternative conceptual accounts: (1) generalization stems from integration of multiple experiences into summary representations that reflect generalized knowledge, and (2) generalization is computed on-the-fly using separately stored individual memories. Across the course of this collaboration, we found that--despite using different terminology and techniques, and although some of our specific papers may provide evidence one way or the other--we in fact largely agree that both of these broad accounts (as well as several others) are likely valid. We believe that future research and theoretical synthesis across multiple lines of research is necessary to help determine the degree to which different candidate generalization mechanisms may operate simultaneously, operate on different scales, or be employed under distinct conditions. Here, as the first step, we introduce some of these candidate mechanisms and we discuss the issues currently hindering better synthesis of generalization research. Finally, we introduce some of our own research questions that have arisen over the course of this GAC, that we believe would benefit from future collaborative efforts.
This paper presents Out-of-Context Summarizer, a tool that takes arbitrary public news articles out of context by summarizing them to coherently fit either a liberal- or conservative-leaning agenda. The Out-of-Context Summarizer also suggests hashtag keywords to bolster the polarization of the summary, in case one is inclined to take it to Twitter, Parler or other platforms for trolling. Out-of-Context Summarizer achieved 79% precision and 99% recall when summarizing COVID-19 articles, 93% precision and 93% recall when summarizing politically-centered articles, and 87% precision and 88% recall when taking liberally-biased articles out of context. Summarizing valid sources instead of synthesizing fake text, the Out-of-Context Summarizer could fairly pass the "adversarial disclosure" test, but we didn't take this easy route in our paper. Instead, we used the Out-of-Context Summarizer to push the debate of potential misuse of automated text generation beyond the boilerplate text of responsible disclosure of adversarial language models.
Automated fact-checking systems verify claims against evidence to predict their veracity. In real-world scenarios, the retrieved evidence may not unambiguously support or refute the claim and yield conflicting but valid interpretations. Existing fact-checking datasets assume that the models developed with them predict a single veracity label for each claim, thus discouraging the handling of such ambiguity. To address this issue we present AmbiFC, a fact-checking dataset with 10k claims derived from real-world information needs. It contains fine-grained evidence annotations of 50k passages from 5k Wikipedia pages. We analyze the disagreements arising from ambiguity when comparing claims against evidence in AmbiFC, observing a strong correlation of annotator disagreement with linguistic phenomena such as underspecification and probabilistic reasoning. We develop models for predicting veracity handling this ambiguity via soft labels and find that a pipeline that learns the label distribution for sentence-level evidence selection and veracity prediction yields the best performance. We compare models trained on different subsets of AmbiFC and show that models trained on the ambiguous instances perform better when faced with the identified linguistic phenomena.
Textbook wisdom advocates for smooth function fits and implies that interpolation of noisy data should lead to poor generalization. A related heuristic is that fitting parameters should be fewer than measurements (Occam's Razor). Surprisingly, contemporary machine learning (ML) approaches, cf. deep nets (DNNs), generalize well despite interpolating noisy data. This may be understood via Statistically Consistent Interpolation (SCI), i.e. data interpolation techniques that generalize optimally for big data. In this article we elucidate SCI using the weighted interpolating nearest neighbors (wiNN) algorithm, which adds singular weight functions to kNN (k-nearest neighbors). This shows that data interpolation can be a valid ML strategy for big data. SCI clarifies the relation between two ways of modeling natural phenomena: the rationalist approach (strong priors) of theoretical physics with few parameters and the empiricist (weak priors) approach of modern ML with more parameters than data. SCI shows that the purely empirical approach can successfully predict. However data interpolation does not provide theoretical insights, and the training data requirements may be prohibitive. Complex animal brains are between these extremes, with many parameters, but modest training data, and with prior structure encoded in species-specific mesoscale circuitry. Thus, modern ML provides a distinct epistemological approach different both from physical theories and animal brains.
Estimating scene geometry from data obtained with cost-effective sensors is key for robots and self-driving cars. In this paper, we study the problem of predicting dense depth from a single RGB image (monodepth) with optional sparse measurements from low-cost active depth sensors. We introduce Sparse Auxiliary Networks (SANs), a new module enabling monodepth networks to perform both the tasks of depth prediction and completion, depending on whether only RGB images or also sparse point clouds are available at inference time. First, we decouple the image and depth map encoding stages using sparse convolutions to process only the valid depth map pixels. Second, we inject this information, when available, into the skip connections of the depth prediction network, augmenting its features. Through extensive experimental analysis on one indoor (NYUv2) and two outdoor (KITTI and DDAD) benchmarks, we demonstrate that our proposed SAN architecture is able to simultaneously learn both tasks, while achieving a new state of the art in depth prediction by a significant margin.
By estimating 3D shape and instances from a single view, we can capture information about an environment quickly, without the need for comprehensive scanning and multi-view fusion. Solving this task for composite scenes (such as object stacks) is challenging: occluded areas are not only ambiguous in shape but also in instance segmentation; multiple decompositions could be valid. We observe that physics constrains decomposition as well as shape in occluded regions and hypothesise that a latent space learned from scenes built under physics simulation can serve as a prior to better predict shape and instances in occluded regions. To this end we propose SIMstack, a depth-conditioned Variational Auto-Encoder (VAE), trained on a dataset of objects stacked under physics simulation. We formulate instance segmentation as a centre voting task which allows for class-agnostic detection and doesn't require setting the maximum number of objects in the scene. At test time, our model can generate 3D shape and instance segmentation from a single depth view, probabilistically sampling proposals for the occluded region from the learned latent space. Our method has practical applications in providing robots some of the ability humans have to make rapid intuitive inferences of partially observed scenes. We demonstrate an application for precise (non-disruptive) object grasping of unknown objects from a single depth view.
Pairs trading is a strategy based on exploiting mean reversion in prices of securities. It has been shown to generate significant excess returns, but its profitability has dropped significantly in recent periods. We employ the most common distance and cointegration methods on US equities from 1990 to 2020 including the Covid-19 crisis. The strategy overall fails to outperform the market benchmark even with hyperparameter tuning, but it performs very strongly during bear markets. Furthermore, we demonstrate that market factors have a strong relationship with the optimal parametrization for the strategy, and adjustments are appropriate for modern market conditions.
While there are many different methods for peak detection, no automatic methods for marking peak boundaries to calculate area under the curve (AUC) and signal-to-noise ratio (SNR) estimation exist. An algorithm for the automation of liquid chromatography tandem mass spectrometry (LC-MS/MS) mass chromatogram quantification was developed and validated. Continuous wavelet transformation and other digital signal processing methods were used in a multi-step procedure to calculate concentrations of six different analytes. To evaluate the performance of the algorithm, the results of the manual quantification of 446 hair samples with 6 different steroid hormones by two experts were compared to the algorithm results. The proposed approach of automating mass chromatogram quantification is reliable and valid. The algorithm returns less nondetectables than human raters. Based on signal to noise ratio, human non-detectables could be correctly classified with a diagnostic performance of AUC = 0.95. The algorithm presented here allows fast, automated, reliable, and valid computational peak detection and quantification in LC- MS/MS.
The outbreak of COVID-19 in 2020 has led to a surge in interest in the mathematical modeling of infectious diseases. Such models are usually defined as compartmental models, in which the population under study is divided into compartments based on qualitative characteristics, with different assumptions about the nature and rate of transfer across compartments. Though most commonly formulated as ordinary differential equation (ODE) models, in which the compartments depend only on time, recent works have also focused on partial differential equation (PDE) models, incorporating the variation of an epidemic in space. Such research on PDE models within a Susceptible, Infected, Exposed, Recovered, and Deceased (SEIRD) framework has led to promising results in reproducing COVID-19 contagion dynamics. In this paper, we assess the robustness of this modeling framework by considering different geometries over more extended periods than in other similar studies. We first validate our code by reproducing previously shown results for Lombardy, Italy. We then focus on the U.S. state of Georgia and on the Brazilian state of Rio de Janeiro, one of the most impacted areas in the world. Our results show good agreement with real-world epidemiological data in both time and space for all regions across major areas and across three different continents, suggesting that the modeling approach is both valid and robust.
Three major biomarkers: beta-amyloid (A), pathologic tau (T), and neurodegeneration (N), are recognized as valid proxies for neuropathologic changes of Alzheimer's disease. While there are extensive studies on cerebrospinal fluids biomarkers (amyloid, tau), the spatial propagation pattern across brain is missing and their interactive mechanisms with neurodegeneration are still unclear. To this end, we aim to analyze the spatiotemporal associations between ATN biomarkers using large-scale neuroimaging data. We first investigate the temporal appearances of amyloid plaques, tau tangles, and neuronal loss by modeling the longitudinal transition trajectories. Second, we propose linear mixed-effects models to quantify the pathological interactions and propagation of ATN biomarkers at each brain region. Our analysis of the current data shows that there exists a temporal latency in the build-up of amyloid to the onset of tau pathology and neurodegeneration. The propagation pattern of amyloid can be characterized by its diffusion along the topological brain network. Our models provide sufficient evidence that the progression of pathological tau and neurodegeneration share a strong regional association, which is different from amyloid.