Search Results for author:
Found 25 papers, 18 papers with code
Deep Expander Networks: Efficient Deep Networks from Graph Theory
Inspired by these techniques, we propose to model connections between filters of a CNN using graphs which are simultaneously sparse and well connected.
GDumb: A Simple Approach that Questions Our Progress in Continual Learning
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.
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
Towards Deep Learning in Hindi NER: An approach to tackle the Labelled Data Scarcity
In this paper we describe an end to end Neural Model for Named Entity Recognition NER) which is based on Bi-Directional RNN-LSTM.
Towards Sub-Word Level Compositions for Sentiment Analysis of Hindi-English Code Mixed Text
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.
No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance
Web-crawled pretraining datasets underlie the impressive "zero-shot" evaluation performance of multimodal models, such as CLIP for classification/retrieval and Stable-Diffusion for image generation.
Towards Adversarial Evaluations for Inexact Machine Unlearning
Machine Learning models face increased concerns regarding the storage of personal user data and adverse impacts of corrupted data like backdoors or systematic bias.
Computationally Budgeted Continual Learning: What Does Matter?
Our conclusions are consistent in a different number of stream time steps, e. g., 20 to 200, and under several computational budgets.
Real-Time Evaluation in Online Continual Learning: A New Hope
We show that a simple baseline outperforms state-of-the-art CL methods under this evaluation, questioning the applicability of existing methods in realistic settings.
Online Continual Learning Without the Storage Constraint
In this paper, we target such applications, investigating the online continual learning problem under relaxed storage constraints and limited computational budgets.
Hybrid Binary Networks: Optimizing for Accuracy, Efficiency and Memory
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.
Distribution-Aware Binarization of Neural Networks for Sketch Recognition
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.
"You might also like this model": Data Driven Approach for Recommending Deep Learning Models for Unknown Image Datasets
Further, we predict the performance accuracy of the recommended architecture on the given unknown dataset, without the need for training the model.
No Cost Likelihood Manipulation at Test Time for Making Better Mistakes in Deep Networks
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.
Corrective Machine Unlearning
We hope our work spurs research towards developing better methods for corrective unlearning and offers practitioners a new strategy to handle data integrity challenges arising from web-scale training.
Rapid Adaptation in Online Continual Learning: Are We Evaluating It Right?
We revisit the common practice of evaluating adaptation of Online Continual Learning (OCL) algorithms through the metric of online accuracy, which measures the accuracy of the model on the immediate next few samples.
Lifelong Benchmarks: Efficient Model Evaluation in an Era of Rapid Progress
However, with repeated testing, the risk of overfitting grows as algorithms over-exploit benchmark idiosyncrasies.
Simple Unsupervised Multi-Object Tracking
Multi-object tracking has seen a lot of progress recently, albeit with substantial annotation costs for developing better and larger labeled datasets.
Amending Mistakes Post-hoc in Deep Networks by Leveraging Class Hierarchies
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.
Inverse Scaling: When Bigger Isn't Better
Here, we present evidence for the claim that LMs may show inverse scaling, or worse task performance with increased scale, e. g., due to flaws in the training objective and data.
From Categories to Classifier: Name-Only Continual Learning by Exploring the Web
Continual Learning (CL) often relies on the availability of extensive annotated datasets, an assumption that is unrealistically time-consuming and costly in practice.
RanDumb: A Simple Approach that Questions the Efficacy of Continual Representation Learning
Our investigation is both surprising and alarming as it questions our understanding of how to effectively design and train models that require efficient continual representation learning, and necessitates a principled reinvestigation of the widely explored problem formulation itself.
Wu's Method can Boost Symbolic AI to Rival Silver Medalists and AlphaGeometry to Outperform Gold Medalists at IMO Geometry
In this note, we revisit the IMO-AG-30 Challenge introduced with AlphaGeometry, and find that Wu's method is surprisingly strong.
kNN-CLIP: Retrieval Enables Training-Free Segmentation on Continually Expanding Large Vocabularies
Rapid advancements in continual segmentation have yet to bridge the gap of scaling to large continually expanding vocabularies under compute-constrained scenarios.
