Search Results for author:
Found 35 papers, 14 papers with code
The Effect of Pretraining on Extractive Summarization for Scientific Documents
Large pretrained models have seen enormous success in extractive summarization tasks.
Geometry-biased Transformers for Novel View Synthesis
While this representation yields (coarsely) accurate images corresponding to novel viewpoints, the lack of geometric reasoning limits the quality of these outputs.
Hierarchical Semantic Regularization of Latent Spaces in StyleGANs
The quality of the generated images is predicated on two assumptions; (a) The richness of the hierarchical representations learnt by the generator, and, (b) The linearity and smoothness of the style spaces.
Interpretable Acoustic Representation Learning on Breathing and Speech Signals for COVID-19 Detection
In this paper, we describe an approach for representation learning of audio signals for the task of COVID-19 detection.
Svadhyaya system for the Second Diagnosing COVID-19 using Acoustics Challenge 2021
This report describes the system used for detecting COVID-19 positives using three different acoustic modalities, namely speech, breathing, and cough in the second DiCOVA challenge.
Unveiling The Mask of Position-Information Pattern Through the Mist of Image Features
Recent studies show that paddings in convolutional neural networks encode absolute position information which can negatively affect the model performance for certain tasks.
DeLoRes: Decorrelating Latent Spaces for Low-Resource Audio Representation Learning
Inspired by the recent progress in self-supervised learning for computer vision, in this paper we introduce DeLoRes, a new general-purpose audio representation learning approach.
AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generation
This enables us to represent distributions over 3D shapes conditioned on information from an arbitrary set of spatially anchored query locations and thus perform shape completion in such arbitrary settings (e. g., generating a complete chair given only a view of the back leg).
SISL:Self-Supervised Image Signature Learning for Splicing Detection and Localization
Recent algorithms for image manipulation detection almost exclusively use deep network models.
Permutation Invariant Representations with Applications to Graph Deep Learning
In turn, this proves that almost any classifier can be implemented with an arbitrary small loss of performance.
Class Incremental Online Streaming Learning
We propose a novel approach (CIOSL) for the class-incremental learning in an \emph{online streaming setting} to address these challenges.
SpliceOut: A Simple and Efficient Audio Augmentation Method
Time masking has become a de facto augmentation technique for speech and audio tasks, including automatic speech recognition (ASR) and audio classification, most notably as a part of SpecAugment.
Perturb, Predict & Paraphrase: Semi-Supervised Learning using Noisy Student for Image Captioning
The original algorithm relies on computationally expensive data augmentation steps that involve perturbing the raw images and computing features for each perturbed image.
Image Augmentation
Semi Supervised Learning for Image Captioning
Is My Model Using The Right Evidence? Systematic Probes for Examining Evidence-Based Tabular Reasoning
Our experiments demonstrate that a RoBERTa-based model, representative of the current state-of-the-art, fails at reasoning on the following counts: it (a) ignores relevant parts of the evidence, (b) is over-sensitive to annotation artifacts, and (c) relies on the knowledge encoded in the pre-trained language model rather than the evidence presented in its tabular inputs.
Deep Implicit Surface Point Prediction Networks
Unsigned distance function (UDF) based approaches have been proposed recently as a promising alternative to represent both open and closed shapes.
Learning to Stylize Novel Views
Second, we develop point cloud aggregation modules to gather the style information of the 3D scene, and then modulate the features in the point cloud with a linear transformation matrix.
HoVer: A Dataset for Many-Hop Fact Extraction And Claim Verification
We introduce HoVer (HOppy VERification), a dataset for many-hop evidence extraction and fact verification.
DUDE: Deep Unsigned Distance Embeddings for Hi-Fidelity Representation of Complex 3D Surfaces
Several implicit 3D shape representation approaches using deep neural networks have been proposed leading to significant improvements in both quality of representations as well as the impact on downstream applications.
ProAlignNet : Unsupervised Learning for Progressively Aligning Noisy Contours
Contour shape alignment is a fundamental but challenging problem in computer vision, especially when the observations are partial, noisy, and largely misaligned.
End-to-end Training of CNN-CRF via Differentiable Dual-Decomposition
These algorithms can efficiently and exactly solve sub-problems and directly optimize a convex upper bound of the real problem, providing optimality certificates on the way.
Wavelets to the Rescue: Improving Sample Quality of Latent Variable Deep Generative Models
Variational Autoencoders (VAE) are probabilistic deep generative models underpinned by elegant theory, stable training processes, and meaningful manifold representations.
Progressive Domain Adaptation for Object Detection
This intermediate domain is constructed by translating the source images to mimic the ones in the target domain.
High-Frequency guided Curriculum Learning for Class-specific Object Boundary Detection
In this work, we devise a curriculum-learning-based training process for object boundary detection.
Sampling Bias in Deep Active Classification: An Empirical Study
The exploding cost and time needed for data labeling and model training are bottlenecks for training DNN models on large datasets.
Ranked #2 on
Text Classification
on Amazon-5
Accelerating Column Generation via Flexible Dual Optimal Inequalities with Application to Entity Resolution
We tackle optimization of weighted set packing by relaxing integrality in our ILP formulation.
Compositional Video Prediction
We present an approach for pixel-level future prediction given an input image of a scene.
To Beta or Not To Beta: Information Bottleneck for DigitaL Image Forensics
We propose an innovative method to formulate the issue of localizing manipulated regions in an image as a deep representation learning problem using the Information Bottleneck (IB), which has recently gained popularity as a framework for interpreting deep neural networks.
SpliceRadar: A Learned Method For Blind Image Forensics
It comprises a novel approach for learning rich filters and for suppressing image-edges.
DRIT++: Diverse Image-to-Image Translation via Disentangled Representations
In this work, we present an approach based on disentangled representation for generating diverse outputs without paired training images.
Massively Parallel Benders Decomposition for Correlation Clustering
We tackle the problem of graph partitioning for image segmentation using correlation clustering (CC), which we treat as an integer linear program (ILP).
On Lipschitz Bounds of General Convolutional Neural Networks
Many convolutional neural networks (CNNs) have a feed-forward structure.
Disconnected Manifold Learning for Generative Adversarial Networks
Natural images may lie on a union of disjoint manifolds rather than one globally connected manifold, and this can cause several difficulties for the training of common Generative Adversarial Networks (GANs).
Disentangling Factors of Variation with Cycle-Consistent Variational Auto-Encoders
Our non-adversarial approach is in contrast with the recent works that combine adversarial training with auto-encoders to disentangle representations.
Unsupervised Representation Learning by Sorting Sequences
We present an unsupervised representation learning approach using videos without semantic labels.
Ranked #46 on
Self-Supervised Action Recognition
on HMDB51
Lipschitz Properties for Deep Convolutional Networks
In this paper we discuss the stability properties of convolutional neural networks.
