Search Results for author:
Found 14 papers, 0 papers with code
Hybrid Sample Synthesis-based Debiasing of Classifier in Limited Data Setting
In this paper, we focus on a more practical setting with no prior information about the bias.
Attaining Class-level Forgetting in Pretrained Model using Few Samples
However, in the future, some classes may become restricted due to privacy/ethical concerns, and the restricted class knowledge has to be removed from the models that have been trained on them.
DILF-EN framework for Class-Incremental Learning
We apply our proposed approach to state-of-the-art class-incremental learning methods and empirically show that our framework significantly improves the performance of these methods.
Restricted Category Removal from Model Representations using Limited Data
A naive solution is to simply train the model from scratch on the complete training data while leaving out the training samples from the restricted classes (FDR - full data retraining).
Fair Visual Recognition in Limited Data Regime using Self-Supervision and Self-Distillation
Our approach significantly improves their performance and further reduces the model biases in the limited data regime.
Rectification-based Knowledge Retention for Continual Learning
Our proposed method uses weight rectifications and affine transformations in order to adapt the model to different tasks that arrive sequentially.
Few-Shot Lifelong Learning
Our method selects very few parameters from the model for training every new set of classes instead of training the full model.
Calibrating CNNs for Lifelong Learning
Further, our approach does not require storing data samples from the old tasks, which is done by many replay based methods.
RNNP: A Robust Few-Shot Learning Approach
Our method relies on generating robust prototypes from a set of few examples.
Improving Few-Shot Learning using Composite Rotation based Auxiliary Task
We then simultaneously train for the composite rotation prediction task along with the original classification task, which forces the network to learn high-quality generic features that help improve the few-shot classification performance.
Passive Batch Injection Training Technique: Boosting Network Performance by Injecting Mini-Batches from a different Data Distribution
Our proposed technique, namely Passive Batch Injection Training Technique (PBITT), even reduces the level of overfitting in networks that already use the standard techniques for reducing overfitting such as $L_2$ regularization and batch normalization, resulting in significant accuracy improvements.
AVGZSLNet: Audio-Visual Generalized Zero-Shot Learning by Reconstructing Label Features from Multi-Modal Embeddings
We use the semantic relatedness of text embeddings as a means for zero-shot learning by aligning audio and video embeddings with the corresponding class label text feature space.
Ranked #6 on
GZSL Video Classification
on ActivityNet-GZSL(main)
CPWC: Contextual Point Wise Convolution for Object Recognition
We propose an alternative design for pointwise convolution, which uses spatial information from the input efficiently.
Accuracy Booster: Performance Boosting using Feature Map Re-calibration
Recently researchers have tried to boost the performance of CNNs by re-calibrating the feature maps produced by these filters, e. g., Squeeze-and-Excitation Networks (SENets).
