Search Results for author:
Found 48 papers, 22 papers with code
TSMixer: An all-MLP Architecture for Time Series Forecasting
Our results underline the importance of efficiently utilizing cross-variate and auxiliary information for improving the performance of time series forecasting.
Pic2Word: Mapping Pictures to Words for Zero-shot Composed Image Retrieval
Existing methods rely on supervised learning of CIR models using labeled triplets consisting of the query image, text specification, and the target image.
Neural Spline Search for Quantile Probabilistic Modeling
Accurate estimation of output quantiles is crucial in many use cases, where it is desired to model the range of possibility.
Hyperbolic Contrastive Learning for Visual Representations beyond Objects
To exploit such a structure, we propose a contrastive learning framework where a Euclidean loss is used to learn object representations and a hyperbolic loss is used to encourage representations of scenes to lie close to representations of their constituent objects in a hyperbolic space.
SPADE: Semi-supervised Anomaly Detection under Distribution Mismatch
Semi-supervised anomaly detection is a common problem, as often the datasets containing anomalies are partially labeled.
Semi-supervised Anomaly Detection
supervised anomaly detection
Prefix Conditioning Unifies Language and Label Supervision
However, a naive unification of the real caption and the prompt sentences could lead to a complication in learning, as the distribution shift in text may not be handled properly in the language encoder.
Learning Instance-Specific Adaptation for Cross-Domain Segmentation
We propose a test-time adaptation method for cross-domain image segmentation.
FormNet: Structural Encoding beyond Sequential Modeling in Form Document Information Extraction
Sequence modeling has demonstrated state-of-the-art performance on natural language and document understanding tasks.
Decoupling Local and Global Representations of Time Series
Learning representations that capture the factors contributing to this variability enables a better understanding of the data via its underlying generative process and improves performance on downstream machine learning tasks.
Anomaly Clustering: Grouping Images into Coherent Clusters of Anomaly Types
We define a distance function between images, each of which is represented as a bag of embeddings, by the Euclidean distance between weighted averaged embeddings.
Improving Model Compatibility of Generative Adversarial Networks by Boundary Calibration
To improve GAN in terms of model compatibility, we propose Boundary-Calibration GANs (BCGANs), which leverage the boundary information from a set of pre-trained classifiers using the original data.
A Unified View of cGANs with and without Classifiers
Conditional Generative Adversarial Networks (cGANs) are implicit generative models which allow to sample from class-conditional distributions.
Robust Contrastive Learning Using Negative Samples with Diminished Semantics
We also show that model bias favors texture and shape features differently under different test settings.
Unifying Distribution Alignment as a Loss for Imbalanced Semi-supervised Learning
While remarkable progress in imbalanced supervised learning has been made recently, less attention has been given to the setting of imbalanced semi-supervised learning (SSL) where not only is a few labeled data provided, but the underlying data distribution can be severely imbalanced.
Object-aware Contrastive Learning for Debiased Scene Representation
Contrastive self-supervised learning has shown impressive results in learning visual representations from unlabeled images by enforcing invariance against different data augmentations.
ROPE: Reading Order Equivariant Positional Encoding for Graph-based Document Information Extraction
Natural reading orders of words are crucial for information extraction from form-like documents.
Self-supervise, Refine, Repeat: Improving Unsupervised Anomaly Detection
We demonstrate our method on various unsupervised AD tasks with image and tabular data.
DISSECT: Disentangled Simultaneous Explanations via Concept Traversals
Explaining deep learning model inferences is a promising venue for scientific understanding, improving safety, uncovering hidden biases, evaluating fairness, and beyond, as argued by many scholars.
CutPaste: Self-Supervised Learning for Anomaly Detection and Localization
We aim at constructing a high performance model for defect detection that detects unknown anomalous patterns of an image without anomalous data.
Ranked #8 on
Unsupervised Anomaly Detection
on DAGM2007
(using extra training data)
Learning and Evaluating Representations for Deep One-class Classification
We first learn self-supervised representations from one-class data, and then build one-class classifiers on learned representations.
Ranked #7 on
Anomaly Detection
on One-class CIFAR-100
PseudoSeg: Designing Pseudo Labels for Semantic Segmentation
We demonstrate the effectiveness of the proposed pseudo-labeling strategy in both low-data and high-data regimes.
i-Mix: A Domain-Agnostic Strategy for Contrastive Representation Learning
Contrastive representation learning has shown to be effective to learn representations from unlabeled data.
Interpretable Sequence Learning for COVID-19 Forecasting
We propose a novel approach that integrates machine learning into compartmental disease modeling to predict the progression of COVID-19.
Kernel Stein Generative Modeling
NCK is crucial for successful inference with SVGD in high dimension, as it adapts the kernel to the noise level of the score estimate.
A Simple Semi-Supervised Learning Framework for Object Detection
Semi-supervised learning (SSL) has a potential to improve the predictive performance of machine learning models using unlabeled data.
Ranked #10 on
Semi-Supervised Object Detection
on COCO 100% labeled data
(using extra training data)
Unsupervised Program Synthesis for Images By Sampling Without Replacement
However, they struggle with the inherent sparsity of meaningful programs in the search space.
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
Semi-supervised learning (SSL) provides an effective means of leveraging unlabeled data to improve a model's performance.
Getting Topology and Point Cloud Generation to Mesh
In this work, we explore the idea that effective generative models for point clouds under the autoencoding framework must acknowledge the relationship between a continuous surface, a discretized mesh, and a set of points sampled from the surface.
Learned Interpolation for 3D Generation
The typical approach for incorporating this creative process is to interpolate in a learned latent space so as to avoid the problem of generating unrealistic instances by exploiting the model's learned structure.
On Completeness-aware Concept-Based Explanations in Deep Neural Networks
Next, we propose a concept discovery method that aims to infer a complete set of concepts that are additionally encouraged to be interpretable, which addresses the limitations of existing methods on concept explanations.
On Concept-Based Explanations in Deep Neural Networks
Next, we propose a concept discovery method that considers two additional constraints to encourage the interpretability of the discovered concepts.
Developing Creative AI to Generate Sculptural Objects
We explore the intersection of human and machine creativity by generating sculptural objects through machine learning.
LBS Autoencoder: Self-supervised Fitting of Articulated Meshes to Point Clouds
As input, we take a sequence of point clouds to be registered as well as an artist-rigged mesh, i. e. a template mesh equipped with a linear-blend skinning (LBS) deformation space parameterized by a skeleton hierarchy.
Implicit Kernel Learning
While learning the kernel in a data driven way has been investigated, in this paper we explore learning the spectral distribution of kernel via implicit generative models parametrized by deep neural networks.
Kernel Change-point Detection with Auxiliary Deep Generative Models
Detecting the emergence of abrupt property changes in time series is a challenging problem.
Hallucinating Point Cloud into 3D Sculptural Object
Our approach extends DeepDream from images to 3D point clouds.
Point Cloud GAN
In this paper, we first show a straightforward extension of existing GAN algorithm is not applicable to point clouds, because the constraint required for discriminators is undefined for set data.
Beyond Pixel Norm-Balls: Parametric Adversaries using an Analytically Differentiable Renderer
As such, we propose the direct perturbation of physical parameters that underly image formation: lighting and geometry.
Nonparametric Density Estimation under Adversarial Losses
We study minimax convergence rates of nonparametric density estimation under a large class of loss functions called "adversarial losses", which, besides classical $\mathcal{L}^p$ losses, includes maximum mean discrepancy (MMD), Wasserstein distance, and total variation distance.
Pedestrian-Synthesis-GAN: Generating Pedestrian Data in Real Scene and Beyond
The results show that our framework can smoothly synthesize pedestrians on background images of variations and different levels of details.
Ranked #2 on
Scene Text Recognition
on MSDA
Sobolev GAN
We show that the Sobolev IPM compares two distributions in high dimensions based on weighted conditional Cumulative Distribution Functions (CDF) of each coordinate on a leave one out basis.
One Network to Solve Them All -- Solving Linear Inverse Problems Using Deep Projection Models
While deep learning methods have achieved state-of-the-art performance in many challenging inverse problems like image inpainting and super-resolution, they invariably involve problem-specific training of the networks.
MMD GAN: Towards Deeper Understanding of Moment Matching Network
In this paper, we propose to improve both the model expressiveness of GMMN and its computational efficiency by introducing adversarial kernel learning techniques, as the replacement of a fixed Gaussian kernel in the original GMMN.
Data-driven Random Fourier Features using Stein Effect
Large-scale kernel approximation is an important problem in machine learning research.
One Network to Solve Them All --- Solving Linear Inverse Problems using Deep Projection Models
On the other hand, traditional methods using signal priors can be used in all linear inverse problems but often have worse performance on challenging tasks.
CMU DeepLens: Deep Learning For Automatic Image-based Galaxy-Galaxy Strong Lens Finding
We find on our simulated data set that for a rejection rate of non-lenses of 99%, a completeness of 90% can be achieved for lenses with Einstein radii larger than 1. 4" and S/N larger than 20 on individual $g$-band LSST exposures.
Instrumentation and Methods for Astrophysics Cosmology and Nongalactic Astrophysics Astrophysics of Galaxies
Annealing Gaussian into ReLU: a New Sampling Strategy for Leaky-ReLU RBM
Due to numerical stability and quantifiability of the likelihood, RBM is commonly used with Bernoulli units.
Rivalry of Two Families of Algorithms for Memory-Restricted Streaming PCA
In this paper, we analyze the convergence rate of a representative algorithm with decayed learning rate (Oja and Karhunen, 1985) in the first family for the general $k>1$ case.
