13 papers
Logit-Origin Centering for Singleton Test-Time Adaptation
Mayank Sharma, Rohit Kumar Mourya, Pratik Mazumder
Tabular data is used extensively in many real-world use cases. Deep learning models have been developed to deal with tabular data, but generally perform poorly when the test data d…
Hybrid Sample Synthesis-based Debiasing of Classifier in Limited Data Setting
Piyush Arora, Pratik Mazumder
Deep learning models are known to suffer from the problem of bias, and researchers have been exploring methods to address this issue. However, most of these methods require prior k…
Attaining Class-level Forgetting in Pretrained Model using Few Samples
Pravendra Singh, Pratik Mazumder, Mohammed Asad Karim
In order to address real-world problems, deep learning models are jointly trained on many classes. However, in the future, some classes may become restricted due to privacy/ethical…
DILF-EN framework for Class-Incremental Learning
Mohammed Asad Karim, Indu Joshi, Pratik Mazumder +1
Deep learning models suffer from catastrophic forgetting of the classes in the older phases as they get trained on the classes introduced in the new phase in the class-incremental…
Fair Visual Recognition in Limited Data Regime using Self-Supervision and Self-Distillation
Pratik Mazumder, Pravendra Singh, Vinay P. Namboodiri
Deep learning models generally learn the biases present in the training data. Researchers have proposed several approaches to mitigate such biases and make the model fair. Bias mit…
Rectification-based Knowledge Retention for Continual Learning
Pravendra Singh, Pratik Mazumder, Piyush Rai +1
Deep learning models suffer from catastrophic forgetting when trained in an incremental learning setting. In this work, we propose a novel approach to address the task incremental…
Few-Shot Lifelong Learning
Pratik Mazumder, Pravendra Singh, Piyush Rai
Many real-world classification problems often have classes with very few labeled training samples. Moreover, all possible classes may not be initially available for training, and m…
RNNP: A Robust Few-Shot Learning Approach
Pratik Mazumder, Pravendra Singh, Vinay P. Namboodiri
Learning from a few examples is an important practical aspect of training classifiers. Various works have examined this aspect quite well. However, all existing approaches assume t…
Passive Batch Injection Training Technique: Boosting Network Performance by Injecting Mini-Batches from a different Data Distribution
Pravendra Singh, Pratik Mazumder, Vinay P. Namboodiri
This work presents a novel training technique for deep neural networks that makes use of additional data from a distribution that is different from that of the original input data.…
Improving Few-Shot Learning using Composite Rotation based Auxiliary Task
Pratik Mazumder, Pravendra Singh, Vinay P. Namboodiri
In this paper, we propose an approach to improve few-shot classification performance using a composite rotation based auxiliary task. Few-shot classification methods aim to produce…
AVGZSLNet: Audio-Visual Generalized Zero-Shot Learning by Reconstructing Label Features from Multi-Modal Embeddings
Pratik Mazumder, Pravendra Singh, Kranti Kumar Parida +1
In this paper, we propose a novel approach for generalized zero-shot learning in a multi-modal setting, where we have novel classes of audio/video during testing that are not seen…
CPWC: Contextual Point Wise Convolution for Object Recognition
Pratik Mazumder, Pravendra Singh, Vinay Namboodiri
Convolutional layers are a major driving force behind the successes of deep learning. Pointwise convolution (PWC) is a 1x1 convolutional filter that is primarily used for parameter…
Accuracy Booster: Performance Boosting using Feature Map Re-calibration
Pravendra Singh, Pratik Mazumder, Vinay P. Namboodiri
Convolution Neural Networks (CNN) have been extremely successful in solving intensive computer vision tasks. The convolutional filters used in CNNs have played a major role in this…