Search Results for author:
Found 30 papers, 4 papers with code
LG-Traj: LLM Guided Pedestrian Trajectory Prediction
We introduce LG-Traj, a novel approach incorporating LLMs to generate motion cues present in pedestrian past/observed trajectories.
Small and Dim Target Detection in IR Imagery: A Review
This is the first review in the field of small and dim target detection in infrared imagery, encompassing various methodologies ranging from conventional image processing to cutting-edge deep learning-based approaches.
Data efficient deep learning for medical image analysis: A survey
This paper conducts a thorough review of data-efficient deep learning methods for medical image analysis.
Improving Trajectory Prediction in Dynamic Multi-Agent Environment by Dropping Waypoints
Motion prediction systems must effectively learn spatial and temporal information from the past to forecast the future trajectories of the agent.
Deep learning for unsupervised domain adaptation in medical imaging: Recent advancements and future perspectives
In this paper, we provide a comprehensive literature review of recent deep UDA approaches in medical imaging from a technical perspective.
SPLAL: Similarity-based pseudo-labeling with alignment loss for semi-supervised medical image classification
To evaluate the performance of our proposed approach, we conduct experiments on two publicly available medical image classification benchmark datasets: the skin lesion classification (ISIC 2018) and the blood cell classification dataset (BCCD).
Recent Advancements in End-to-End Autonomous Driving using Deep Learning: A Survey
End-to-End driving is a promising paradigm as it circumvents the drawbacks associated with modular systems, such as their overwhelming complexity and propensity for error propagation.
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.
Knowledge Consolidation based Class Incremental Online Learning with Limited Data
In our approach, we learn robust representations that are generalizable across tasks without suffering from the problems of catastrophic forgetting and overfitting to accommodate future classes with limited samples.
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)
Minimizing Supervision in Multi-label Categorization
The approach we adopt is one of active learning, i. e., incrementally selecting a set of samples that need supervision based on the current model, obtaining supervision for these samples, retraining the model with the additional set of supervised samples and proceeding again to select the next set of samples.
A "Network Pruning Network" Approach to Deep Model Compression
The pruner is essentially a multitask deep neural network with binary outputs that help identify the filters from each layer of the original network that do not have any significant contribution to the model and can therefore be pruned.
Cooperative Initialization based Deep Neural Network Training
In this paper, we have proposed a cooperative initialization for training the deep network using ReLU activation function to improve the network performance.
CPWC: Contextual Point Wise Convolution for Object Recognition
We propose an alternative design for pointwise convolution, which uses spatial information from the input efficiently.
Play and Prune: Adaptive Filter Pruning for Deep Model Compression
Our framework, called Play and Prune (PP), jointly prunes and fine-tunes CNN model parameters, with an adaptive pruning rate, while maintaining the model's predictive performance.
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).
HetConv: Heterogeneous Kernel-Based Convolutions for Deep CNNs
We present a novel deep learning architecture in which the convolution operation leverages heterogeneous kernels.
Leveraging Filter Correlations for Deep Model Compression
We present a filter correlation based model compression approach for deep convolutional neural networks.
Stability Based Filter Pruning for Accelerating Deep CNNs
Convolutional neural networks (CNN) have achieved impressive performance on the wide variety of tasks (classification, detection, etc.)
Multi-layer Pruning Framework for Compressing Single Shot MultiBox Detector
Additionally, we also empirically show our method's adaptability for classification based architecture VGG16 on datasets CIFAR and German Traffic Sign Recognition Benchmark (GTSRB) achieving a compression rate of 125X and 200X with the reduction in flops by 90. 50% and 96. 6% respectively with no loss of accuracy.
Implementing an intelligent version of the classical sliding-puzzle game for unix terminals using Golang's concurrency primitives
An intelligent version of the sliding-puzzle game is developed using the new Go programming language, which uses a concurrent version of the A* Informed Search Algorithm to power solver-bot that runs in the background.
