Search Results for author: Ameya Prabhu

Found 12 papers, 9 papers with code

GDumb: A Simple Approach that Questions Our Progress in Continual Learning

1 code implementation ECCV 2020 Ameya Prabhu, Philip H. S. Torr, Puneet K. Dokania

We discuss a general formulation for the Continual Learning (CL) problem for classification---a learning task where a stream provides samples to a learner and the goal of the learner, depending on the samples it receives, is to continually upgrade its knowledge about the old classes and learn new ones.

Continual Learning Open Set Learning

No Cost Likelihood Manipulation at Test Time for Making Better Mistakes in Deep Networks

1 code implementation1 Apr 2021 Shyamgopal Karthik, Ameya Prabhu, Puneet K. Dokania, Vineet Gandhi

There has been increasing interest in building deep hierarchy-aware classifiers that aim to quantify and reduce the severity of mistakes, and not just reduce the number of errors.

Amending Mistakes Post-hoc in Deep Networks by Leveraging Class Hierarchies

no code implementations ICLR 2021 Shyamgopal Karthik, Ameya Prabhu, Puneet K. Dokania, Vineet Gandhi

There has been increasing interest in building deep hierarchy-aware classifiers, aiming to quantify and reduce the severity of mistakes and not just count the number of errors.

Simple Unsupervised Multi-Object Tracking

no code implementations4 Jun 2020 Shyamgopal Karthik, Ameya Prabhu, Vineet Gandhi

Multi-object tracking has seen a lot of progress recently, albeit with substantial annotation costs for developing better and larger labeled datasets.

Multi-Object Tracking

"You might also like this model": Data Driven Approach for Recommending Deep Learning Models for Unknown Image Datasets

1 code implementation26 Nov 2019 Ameya Prabhu, Riddhiman Dasgupta, Anush Sankaran, Srikanth Tamilselvam, Senthil Mani

Further, we predict the performance accuracy of the recommended architecture on the given unknown dataset, without the need for training the model.

Sampling Bias in Deep Active Classification: An Empirical Study

2 code implementations IJCNLP 2019 Ameya Prabhu, Charles Dognin, Maneesh Singh

The exploding cost and time needed for data labeling and model training are bottlenecks for training DNN models on large datasets.

Active Learning Classification +2

Hybrid Binary Networks: Optimizing for Accuracy, Efficiency and Memory

1 code implementation11 Apr 2018 Ameya Prabhu, Vishal Batchu, Rohit Gajawada, Sri Aurobindo Munagala, Anoop Namboodiri

We analyze the binarization tradeoff using a metric that jointly models the input binarization-error and computational cost and introduce an efficient algorithm to select layers whose inputs are to be binarized.

Binarization Model Compression +1

Distribution-Aware Binarization of Neural Networks for Sketch Recognition

1 code implementation9 Apr 2018 Ameya Prabhu, Vishal Batchu, Sri Aurobindo Munagala, Rohit Gajawada, Anoop Namboodiri

We present a theoretical analysis of the technique to show the effective representational power of the resulting layers, and explore the forms of data they model best.

Binarization Sketch Recognition

Deep Expander Networks: Efficient Deep Networks from Graph Theory

2 code implementations ECCV 2018 Ameya Prabhu, Girish Varma, Anoop Namboodiri

Inspired by these techniques, we propose to model connections between filters of a CNN using graphs which are simultaneously sparse and well connected.

Towards Sub-Word Level Compositions for Sentiment Analysis of Hindi-English Code Mixed Text

3 code implementations COLING 2016 Ameya Prabhu, Aditya Joshi, Manish Shrivastava, Vasudeva Varma

We introduce a Hindi-English (Hi-En) code-mixed dataset for sentiment analysis and perform empirical analysis comparing the suitability and performance of various state-of-the-art SA methods in social media.

Opinion Mining Sentiment Analysis

Cannot find the paper you are looking for? You can Submit a new open access paper.