Search Results for author:
Found 29 papers, 9 papers with code
Weighted Ensemble Self-Supervised Learning
Ensembling has proven to be a powerful technique for boosting model performance, uncertainty estimation, and robustness in supervised learning.
LilNetX: Lightweight Networks with EXtreme Model Compression and Structured Sparsification
We introduce LilNetX, an end-to-end trainable technique for neural networks that enables learning models with specified accuracy-rate-computation trade-off.
3D Scene Compression through Entropy Penalized Neural Representation Functions
We unify these steps by directly compressing an implicit representation of the scene, a function that maps spatial coordinates to a radiance vector field, which can then be queried to render arbitrary viewpoints.
A Review on Cyber Crimes on the Internet of Things
The success of IoT cannot be ignored in the scenario today, along with its attacks and threats on IoT devices and facilities are also increasing day by day.
An Approximate Carry Estimating Simultaneous Adder with Rectification
In this work, we propose a new approximate adder that employs a carry prediction method.
Hardware Architecture
End-to-end Learning of Compressible Features
We propose a learned method that jointly optimizes for compressibility along with the task objective for learning the features.
Channel-wise Autoregressive Entropy Models for Learned Image Compression
In learning-based approaches to image compression, codecs are developed by optimizing a computational model to minimize a rate-distortion objective.
Deep Implicit Volume Compression
We describe a novel approach for compressing truncated signed distance fields (TSDF) stored in 3D voxel grids, and their corresponding textures.
DAYENU: A Simple Filter of Smooth Foregrounds for Intensity Mapping Power Spectra
We introduce DAYENU, a linear, spectral filter for HI intensity mapping that achieves the desirable foreground mitigation and error minimization properties of inverse co-variance weighting with minimal modeling of the underlying data.
Cosmology and Nongalactic Astrophysics Instrumentation and Methods for Astrophysics
PatchVAE: Learning Local Latent Codes for Recognition
Unsupervised representation learning holds the promise of exploiting large amounts of unlabeled data to learn general representations.
Filter Response Normalization Layer: Eliminating Batch Dependence in the Training of Deep Neural Networks
Our method outperforms BN and other alternatives in a variety of settings for all batch sizes.
Ranked #656 on
Image Classification
on ImageNet
Scalable Model Compression by Entropy Penalized Reparameterization
We describe a simple and general neural network weight compression approach, in which the network parameters (weights and biases) are represented in a "latent" space, amounting to a reparameterization.
EvalNorm: Estimating Batch Normalization Statistics for Evaluation
Batch normalization (BN) has been very effective for deep learning and is widely used.
Image-Dependent Local Entropy Models for Learned Image Compression
The leading approach for image compression with artificial neural networks (ANNs) is to learn a nonlinear transform and a fixed entropy model that are optimized for rate-distortion performance.
Spatially adaptive image compression using a tiled deep network
Deep neural networks represent a powerful class of function approximators that can learn to compress and reconstruct images.
Variational image compression with a scale hyperprior
We describe an end-to-end trainable model for image compression based on variational autoencoders.
All that is English may be Hindi: Enhancing language identification through automatic ranking of the likeliness of word borrowing in social media
Based on this likeliness estimate we asked annotators to re-annotate the language tags of foreign words in predominantly native contexts.
All that is English may be Hindi: Enhancing language identification through automatic ranking of likeliness of word borrowing in social media
Based on this likeliness estimate we asked annotators to re-annotate the language tags of foreign words in predominantly native contexts.
Revisiting Unreasonable Effectiveness of Data in Deep Learning Era
What will happen if we increase the dataset size by 10x or 100x?
Ranked #2 on
Semantic Segmentation
on PASCAL VOC 2007
Target-Quality Image Compression with Recurrent, Convolutional Neural Networks
Our methods introduce a multi-pass training method to combine the training goals of high-quality reconstructions in areas around stop-code masking as well as in highly-detailed areas.
Aligned Image-Word Representations Improve Inductive Transfer Across Vision-Language Tasks
In this paper, we investigate a vision-language embedding as a core representation and show that it leads to better cross-task transfer than standard multi-task learning.
Improved Lossy Image Compression with Priming and Spatially Adaptive Bit Rates for Recurrent Networks
We propose a method for lossy image compression based on recurrent, convolutional neural networks that outperforms BPG (4:2:0 ), WebP, JPEG2000, and JPEG as measured by MS-SSIM.
No Fuss Distance Metric Learning using Proxies
Traditionally, for this problem supervision is expressed in the form of sets of points that follow an ordinal relationship -- an anchor point $x$ is similar to a set of positive points $Y$, and dissimilar to a set of negative points $Z$, and a loss defined over these distances is minimized.
Is this word borrowed? An automatic approach to quantify the likeliness of borrowing in social media
We first propose context based clustering method to sample a set of candidate words from the social media data. Next, we propose three novel and similar metrics based on the usage of these words by the users in different tweets; these metrics were used to score and rank the candidate words indicating their borrowed likeliness.
Learning to Localize Little Landmarks
We describe a method to find such landmarks by finding a sequence of latent landmarks, each with a prediction model.
Swapout: Learning an ensemble of deep architectures
When viewed as a regularization method swapout not only inhibits co-adaptation of units in a layer, similar to dropout, but also across network layers.
Where To Look: Focus Regions for Visual Question Answering
We present a method that learns to answer visual questions by selecting image regions relevant to the text-based query.
Part Localization using Multi-Proposal Consensus for Fine-Grained Categorization
We present a simple deep learning framework to simultaneously predict keypoint locations and their respective visibilities and use those to achieve state-of-the-art performance for fine-grained classification.
Learning a Sequential Search for Landmarks
We propose a general method to find landmarks in images of objects using both appearance and spatial context.
