Search Results for author:
Found 16 papers, 9 papers with code
NGAME: Negative Mining-aware Mini-batching for Extreme Classification
This paper identifies that memory overheads of popular negative mining techniques often force mini-batch sizes to remain small and slow training down.
Multi-Modal Extreme Classification
On the other hand, XC methods utilize classifier architectures to offer superior accuracies than embedding-only methods but mostly focus on text-based categorization tasks.
DeepXML: A Deep Extreme Multi-Label Learning Framework Applied to Short Text Documents
Scalability and accuracy are well recognized challenges in deep extreme multi-label learning where the objective is to train architectures for automatically annotating a data point with the most relevant subset of labels from an extremely large label set.
DECAF: Deep Extreme Classification with Label Features
This paper develops the DECAF algorithm that addresses these challenges by learning models enriched by label metadata that jointly learn model parameters and feature representations using deep networks and offer accurate classification at the scale of millions of labels.
ECLARE: Extreme Classification with Label Graph Correlations
This paper presents ECLARE, a scalable deep learning architecture that incorporates not only label text, but also label correlations, to offer accurate real-time predictions within a few milliseconds.
RNNPool: Efficient Non-linear Pooling for RAM Constrained Inference
Standard Convolutional Neural Networks (CNNs) designed for computer vision tasks tend to have large intermediate activation maps.
Ranked #16 on
Face Detection
on WIDER Face (Medium)
Extreme Regression for Dynamic Search Advertising
This paper also introduces a (3) new labelwise prediction algorithm in XReg useful for DSA and other recommendation tasks.
GesturePod: Enabling On-device Gesture-based Interaction for White Cane Users
Our in-lab study shows that GesturePod achieves 92% gesture recognition accuracy and can help perform common smartphone tasks faster.
Ranked #1 on
Gesture Recognition
on GesturePod
DeepXML: Scalable & Accurate Deep Extreme Classification for Matching User Queries to Advertiser Bid Phrases
The objective in deep extreme multi-label learning is to jointly learn feature representations and classifiers to automatically tag data points with the most relevant subset of labels from an extremely large label set.
One Size Does Not Fit All: Multi-Scale, Cascaded RNNs for Radar Classification
Edge sensing with micro-power pulse-Doppler radars is an emergent domain in monitoring and surveillance with several smart city applications.
FastGRNN: A Fast, Accurate, Stable and Tiny Kilobyte Sized Gated Recurrent Neural Network
FastRNN addresses these limitations by adding a residual connection that does not constrain the range of the singular values explicitly and has only two extra scalar parameters.
Resource-efficient Machine Learning in 2 KB RAM for the Internet of Things
This paper develops a novel tree-based algorithm, called Bonsai, for efficient prediction on IoT devices – such as those based on the Arduino Uno board having an 8 bit ATmega328P microcontroller operating at 16 MHz with no native floating point support, 2 KB RAM and 32 KB read-only flash.
ProtoNN: Compressed and Accurate kNN for Resource-scarce Devices
Such applications demand prediction models with small storage and computational complexity that do not compromise significantly on accuracy.
Sparse Local Embeddings for Extreme Multi-label Classification
The objective in extreme multi-label learning is to train a classifier that can automatically tag a novel data point with the most relevant subset of labels from an extremely large label set.
Locally Non-linear Embeddings for Extreme Multi-label Learning
Embedding based approaches make training and prediction tractable by assuming that the training label matrix is low-rank and hence the effective number of labels can be reduced by projecting the high dimensional label vectors onto a low dimensional linear subspace.
Extreme Multi-Label Classification
General Classification
+2
Multiple Kernel Learning and the SMO Algorithm
Our objective is to train $p$-norm Multiple Kernel Learning (MKL) and, more generally, linear MKL regularised by the Bregman divergence, using the Sequential Minimal Optimization (SMO) algorithm.
