Pravendra Singh

Pranav Singh Chib, Pravendra Singh

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. Autonomous driving transcends conventional traffic patterns by proactively recognizing critical events in advance, ensuring passengers' safety and providing them with comfortable transportation, particularly in highly stochastic and variable traffic settings. This paper presents a comprehensive review of the End-to-End autonomous driving stack. It provides a taxonomy of automated driving tasks wherein neural networks have been employed in an End-to-End manner, encompassing the entire driving process from perception to control, while addressing key challenges encountered in real-world applications. Recent developments in End-to-End autonomous driving are analyzed, and research is categorized based on underlying principles, methodologies, and core functionality. These categories encompass sensorial input, main and auxiliary output, learning approaches ranging from imitation to reinforcement learning, and model evaluation techniques. The survey incorporates a detailed discussion of the explainability and safety aspects. Furthermore, it assesses the state-of-the-art, identifies challenges, and explores future possibilities. We maintained the latest advancements and their corresponding open-source implementations at https://github.com/Pranav-chib/Recent-Advancements-in-End-to-End-Autonomous-Driving-using-Deep-Learning.

Suruchi Kumari, Pravendra Singh

Deep learning has demonstrated remarkable performance across various tasks in medical imaging. However, these approaches primarily focus on supervised learning, assuming that the training and testing data are drawn from the same distribution. Unfortunately, this assumption may not always hold true in practice. To address these issues, unsupervised domain adaptation (UDA) techniques have been developed to transfer knowledge from a labeled domain to a related but unlabeled domain. In recent years, significant advancements have been made in UDA, resulting in a wide range of methodologies, including feature alignment, image translation, self-supervision, and disentangled representation methods, among others. In this paper, we provide a comprehensive literature review of recent deep UDA approaches in medical imaging from a technical perspective. Specifically, we categorize current UDA research in medical imaging into six groups and further divide them into finer subcategories based on the different tasks they perform. We also discuss the respective datasets used in the studies to assess the divergence between the different domains. Finally, we discuss emerging areas and provide insights and discussions on future research directions to conclude this survey.

Suruchi Kumari, Aryan Das, Swalpa Kumar Roy et al.

Traditional supervised 3D medical image segmentation models need voxel-level annotations, which require huge human effort, time, and cost. Semi-supervised learning (SSL) addresses this limitation of supervised learning by facilitating learning with a limited annotated and larger amount of unannotated training samples. However, state-of-the-art SSL models still struggle to fully exploit the potential of learning from unannotated samples. To facilitate effective learning from unannotated data, we introduce LLM-SegNet, which exploits a large language model (LLM) to integrate task-specific knowledge into our co-training framework. This knowledge aids the model in comprehensively understanding the features of the region of interest (ROI), ultimately leading to more efficient segmentation. Additionally, to further reduce erroneous segmentation, we propose a Unified Segmentation loss function. This loss function reduces erroneous segmentation by not only prioritizing regions where the model is confident in predicting between foreground or background pixels but also effectively addressing areas where the model lacks high confidence in predictions. Experiments on publicly available Left Atrium, Pancreas-CT, and Brats-19 datasets demonstrate the superior performance of LLM-SegNet compared to the state-of-the-art. Furthermore, we conducted several ablation studies to demonstrate the effectiveness of various modules and loss functions leveraged by LLM-SegNet.

Md Junaid Mahmood, Pranaw Raj, Divyansh Agarwal et al.

Medical image classification is a challenging task due to the scarcity of labeled samples and class imbalance caused by the high variance in disease prevalence. Semi-supervised learning (SSL) methods can mitigate these challenges by leveraging both labeled and unlabeled data. However, SSL methods for medical image classification need to address two key challenges: (1) estimating reliable pseudo-labels for the images in the unlabeled dataset and (2) reducing biases caused by class imbalance. In this paper, we propose a novel SSL approach, SPLAL, that effectively addresses these challenges. SPLAL leverages class prototypes and a weighted combination of classifiers to predict reliable pseudo-labels over a subset of unlabeled images. Additionally, we introduce alignment loss to mitigate model biases toward majority classes. 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). The experimental results empirically demonstrate that our approach outperforms several state-of-the-art SSL methods over various evaluation metrics. Specifically, our proposed approach achieves a significant improvement over the state-of-the-art approach on the ISIC 2018 dataset in both Accuracy and F1 score, with relative margins of 2.24\% and 11.40\%, respectively. Finally, we conduct extensive ablation experiments to examine the contribution of different components of our approach, validating its effectiveness.

Pranav Singh Chib, Pravendra Singh

The inherently diverse and uncertain nature of trajectories presents a formidable challenge in accurately modeling them. Motion prediction systems must effectively learn spatial and temporal information from the past to forecast the future trajectories of the agent. Many existing methods learn temporal motion via separate components within stacked models to capture temporal features. Furthermore, prediction methods often operate under the assumption that observed trajectory waypoint sequences are complete, disregarding scenarios where missing values may occur, which can influence their performance. Moreover, these models may be biased toward particular waypoint sequences when making predictions. We propose a novel approach called Temporal Waypoint Dropping (TWD) that explicitly incorporates temporal dependencies during the training of a trajectory prediction model. By stochastically dropping waypoints from past observed trajectories, the model is forced to learn the underlying temporal representation from the remaining waypoints, resulting in an improved model. Incorporating stochastic temporal waypoint dropping into the model learning process significantly enhances its performance in scenarios with missing values. Experimental results demonstrate our approach's substantial improvement in trajectory prediction capabilities. Our approach can complement existing trajectory prediction methods to improve their prediction accuracy. We evaluate our proposed approach on three datasets: NBA Sports VU, ETH-UCY, and TrajNet++.

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 concerns, and the restricted class knowledge has to be removed from the models that have been trained on them. The available data may also be limited due to privacy/ethical concerns, and re-training the model will not be possible. We propose a novel approach to address this problem without affecting the model's prediction power for the remaining classes. Our approach identifies the model parameters that are highly relevant to the restricted classes and removes the knowledge regarding the restricted classes from them using the limited available training data. Our approach is significantly faster and performs similar to the model re-trained on the complete data of the remaining classes.

Pranav Singh Chib, Pravendra Singh

Pedestrian trajectory prediction is crucial for several applications such as robotics and self-driving vehicles. Significant progress has been made in the past decade thanks to the availability of pedestrian trajectory datasets, which enable trajectory prediction methods to learn from pedestrians' past movements and predict future trajectories. However, these datasets and methods typically assume that the observed trajectory sequence is complete, ignoring real-world issues such as sensor failure, occlusion, and limited fields of view that can result in missing values in observed trajectories. To address this challenge, we present TrajImpute, a pedestrian trajectory prediction dataset that simulates missing coordinates in the observed trajectory, enhancing real-world applicability. TrajImpute maintains a uniform distribution of missing data within the observed trajectories. In this work, we comprehensively examine several imputation methods to reconstruct the missing coordinates and benchmark them for imputing pedestrian trajectories. Furthermore, we provide a thorough analysis of recent trajectory prediction methods and evaluate the performance of these models on the imputed trajectories. Our experimental evaluation of the imputation and trajectory prediction methods offers several valuable insights. Our dataset provides a foundational resource for future research on imputation-aware pedestrian trajectory prediction, potentially accelerating the deployment of these methods in real-world applications. Publicly accessible links to the datasets and code files are available at https://github.com/Pranav-chib/TrajImpute.

Suruchi Kumari, Pravendra Singh

The rapid evolution of deep learning has significantly advanced the field of medical image analysis. However, despite these achievements, the further enhancement of deep learning models for medical image analysis faces a significant challenge due to the scarcity of large, well-annotated datasets. To address this issue, recent years have witnessed a growing emphasis on the development of data-efficient deep learning methods. This paper conducts a thorough review of data-efficient deep learning methods for medical image analysis. To this end, we categorize these methods based on the level of supervision they rely on, encompassing categories such as no supervision, inexact supervision, incomplete supervision, inaccurate supervision, and only limited supervision. We further divide these categories into finer subcategories. For example, we categorize inexact supervision into multiple instance learning and learning with weak annotations. Similarly, we categorize incomplete supervision into semi-supervised learning, active learning, and domain-adaptive learning and so on. Furthermore, we systematically summarize commonly used datasets for data efficient deep learning in medical image analysis and investigate future research directions to conclude this survey.

Nikhil Kumar, Pravendra Singh

While there has been significant progress in object detection using conventional image processing and machine learning algorithms, exploring small and dim target detection in the IR domain is a relatively new area of study. The majority of small and dim target detection methods are derived from conventional object detection algorithms, albeit with some alterations. The task of detecting small and dim targets in IR imagery is complex. This is because these targets often need distinct features, the background is cluttered with unclear details, and the IR signatures of the scene can change over time due to fluctuations in thermodynamics. The primary objective of this review is to highlight the progress made in this field. 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. The authors have also introduced a taxonomy of such approaches. There are two main types of approaches: methodologies using several frames for detection, and single-frame-based detection techniques. Single frame-based detection techniques encompass a diverse range of methods, spanning from traditional image processing-based approaches to more advanced deep learning methodologies. Our findings indicate that deep learning approaches perform better than traditional image processing-based approaches. In addition, a comprehensive compilation of various available datasets has also been provided. Furthermore, this review identifies the gaps and limitations in existing techniques, paving the way for future research and development in this area.

Pranav Singh Chib, Pravendra Singh

Trajectory prediction is an important task that involves modeling the indeterminate nature of traffic actors to forecast future trajectories given the observed trajectory sequences. However, current methods confine themselves to presumed data manifolds, assuming that trajectories strictly adhere to these manifolds, resulting in overly simplified predictions. To this end, we propose a novel approach called SSWNP (Self-Supervised Waypoint Noise Prediction). In our approach, we first create clean and noise-augmented views of past observed trajectories across the spatial domain of waypoints. We then compel the trajectory prediction model to maintain spatial consistency between predictions from these two views, in addition to the trajectory prediction task. Introducing the noise-augmented view mitigates the model's reliance on a narrow interpretation of the data manifold, enabling it to learn more plausible and diverse representations. We also predict the noise present in the two views of past observed trajectories as an auxiliary self-supervised task, enhancing the model's understanding of the underlying representation and future predictions. Empirical evidence demonstrates that the incorporation of SSWNP into the model learning process significantly improves performance, even in noisy environments, when compared to baseline methods. Our approach can complement existing trajectory prediction methods. To showcase the effectiveness of our approach, we conducted extensive experiments on three datasets: NBA Sports VU, ETH-UCY, and TrajNet++, with experimental results highlighting the substantial improvement achieved in trajectory prediction tasks.

Nikhil Kumar, Avinash Upadhyay, Shreya Sharma et al.

This paper presents a novel mid-wave infrared (MWIR) small target detection dataset (MWIRSTD) comprising 14 video sequences containing approximately 1053 images with annotated targets of three distinct classes of small objects. Captured using cooled MWIR imagers, the dataset offers a unique opportunity for researchers to develop and evaluate state-of-the-art methods for small object detection in realistic MWIR scenes. Unlike existing datasets, which primarily consist of uncooled thermal images or synthetic data with targets superimposed onto the background or vice versa, MWIRSTD provides authentic MWIR data with diverse targets and environments. Extensive experiments on various traditional methods and deep learning-based techniques for small target detection are performed on the proposed dataset, providing valuable insights into their efficacy. The dataset and code are available at https://github.com/avinres/MWIRSTD.

Pranav Singh Chib, Pravendra Singh

Accurate pedestrian trajectory prediction is crucial for various applications, and it requires a deep understanding of pedestrian motion patterns in dynamic environments. However, existing pedestrian trajectory prediction methods still need more exploration to fully leverage these motion patterns. This paper investigates the possibilities of using Large Language Models (LLMs) to improve pedestrian trajectory prediction tasks by inducing motion cues. We introduce LG-Traj, a novel approach incorporating LLMs to generate motion cues present in pedestrian past/observed trajectories. Our approach also incorporates motion cues present in pedestrian future trajectories by clustering future trajectories of training data using a mixture of Gaussians. These motion cues, along with pedestrian coordinates, facilitate a better understanding of the underlying representation. Furthermore, we utilize singular value decomposition to augment the observed trajectories, incorporating them into the model learning process to further enhance representation learning. Our method employs a transformer-based architecture comprising a motion encoder to model motion patterns and a social decoder to capture social interactions among pedestrians. We demonstrate the effectiveness of our approach on popular pedestrian trajectory prediction benchmarks, namely ETH-UCY and SDD, and present various ablation experiments to validate our approach.

Suruchi Kumari, Pravendra Singh

Semi-supervised medical image segmentation has gained growing interest due to its ability to utilize unannotated data. The current state-of-the-art methods mostly rely on pseudo-labeling within a co-training framework. These methods depend on a single pseudo-label for training, but these labels are not as accurate as the ground truth of labeled data. Relying solely on one pseudo-label often results in suboptimal results. To this end, we propose a novel approach where multiple pseudo-labels for the same unannotated image are used to learn from the unlabeled data: the conventional fixed pseudo-label and the newly introduced dynamic pseudo-label. By incorporating multiple pseudo-labels for the same unannotated image into the co-training framework, our approach provides a more robust training approach that improves model performance and generalization capabilities. We validate our novel approach on three semi-supervised medical benchmark segmentation datasets, the Left Atrium dataset, the Pancreas-CT dataset, and the Brats-2019 dataset. Our approach significantly outperforms state-of-the-art methods over multiple medical benchmark segmentation datasets with different labeled data ratios. We also present several ablation experiments to demonstrate the effectiveness of various components used in our approach.

Anshul Pundhir, Balasubramanian Raman, Pravendra Singh

Deep learning models, particularly Convolutional Neural Networks (CNNs), have demonstrated exceptional performance in diagnosing skin diseases, often outperforming dermatologists. However, they have also unveiled biases linked to specific demographic traits, notably concerning diverse skin tones or gender, prompting concerns regarding fairness and limiting their widespread deployment. Researchers are actively working to ensure fairness in AI-based solutions, but existing methods incur an accuracy loss when striving for fairness. To solve this issue, we propose a `two-biased teachers' (i.e., biased on different sensitive attributes) based approach to transfer fair knowledge into the student network. Our approach mitigates biases present in the student network without harming its predictive accuracy. In fact, in most cases, our approach improves the accuracy of the baseline model. To achieve this goal, we developed a weighted loss function comprising biasing and debiasing loss terms. We surpassed available state-of-the-art approaches to attain fairness and also improved the accuracy at the same time. The proposed approach has been evaluated and validated on two dermatology datasets using standard accuracy and fairness evaluation measures. We will make source code publicly available to foster reproducibility and future research.

Pranav Singh, Pravendra Singh

IRSTD (InfraRed Small Target Detection) detects small targets in infrared blurry backgrounds and is essential for various applications. The detection task is challenging due to the small size of the targets and their sparse distribution in infrared small target datasets. Although existing IRSTD methods and datasets have led to significant advancements, they are limited by their reliance solely on the image modality. Recent advances in deep learning and large vision-language models have shown remarkable performance in various visual recognition tasks. In this work, we propose a novel multimodal IRSTD framework that incorporates language priors to guide small target detection. We leverage language-guided attention weights derived from the language prior to enhance the model's ability for IRSTD, presenting a novel approach that combines textual information with image data to improve IRSTD capabilities. Utilizing the state-of-the-art GPT-4 vision model, we generate text descriptions that provide the locations of small targets in infrared images, employing careful prompt engineering to ensure improved accuracy. Due to the absence of multimodal IR datasets, existing IRSTD methods rely solely on image data. To address this shortcoming, we have curated a multimodal infrared dataset that includes both image and text modalities for small target detection, expanding upon the popular IRSTD-1k and NUDT-SIRST datasets. We validate the effectiveness of our approach through extensive experiments and comprehensive ablation studies. The results demonstrate significant improvements over the state-of-the-art method, with relative percentage differences of 9.74%, 13.02%, 1.25%, and 67.87% in IoU, nIoU, Pd, and Fa on the NUAA-SIRST subset, and 4.41%, 2.04%, 2.01%, and 113.43% on the IRSTD-1k subset of the LangIR dataset, respectively.

Aryan Das, Tanishq Rachamalla, Pravendra Singh et al.

We introduce HyperCap, the first large-scale hyperspectral captioning dataset designed to enhance model performance and effectiveness in remote sensing applications. Unlike traditional hyperspectral imaging (HSI) datasets that focus solely on classification tasks, HyperCap integrates spectral data with pixel-wise textual annotations, enabling deeper semantic understanding of hyperspectral imagery. This dataset enhances model performance in tasks like classification and feature extraction, providing a valuable resource for advanced remote sensing applications. HyperCap is constructed from four benchmark datasets and annotated through a hybrid approach combining automated and manual methods to ensure accuracy and consistency. Empirical evaluations using state-of-the-art encoders and diverse fusion techniques demonstrate significant improvements in classification performance. These results underscore the potential of vision-language learning in HSI and position HyperCap as a foundational dataset for future research in the field.

Shourya Goel, Himanshi Tibrewal, Anant Jain et al.

Federated learning (FL) has gained increasing attention due to privacy-preserving collaborative training on decentralized clients, mitigating the need to upload sensitive data to a central server directly. Nonetheless, recent research has underscored the risk of exposing private data to adversaries, even within FL frameworks. In general, existing methods sacrifice performance while ensuring resistance to privacy leakage in FL. We overcome these issues and generate diverse models at a global server through the proposed stochastic bidirectional parameter update mechanism. Using diverse models, we improved the generalization and feature representation in the FL setup, which also helped to improve the robustness of the model against privacy leakage without hurting the model's utility. We use global models from past FL rounds to follow systematic perturbation in parameter space at the server to ensure model generalization and resistance against privacy attacks. We generate diverse models (in close neighborhoods) for each client by using systematic perturbations in model parameters at a fine-grained level (i.e., altering each convolutional filter across the layers of the model) to improve the generalization and security perspective. We evaluated our proposed approach on four benchmark datasets to validate its superiority. We surpassed the state-of-the-art methods in terms of model utility and robustness towards privacy leakage. We have proven the effectiveness of our method by evaluating performance using several quantitative and qualitative results.

Pranav Singh Chib, Pravendra Singh

Accurately predicting future pedestrian trajectories is crucial across various domains. Due to the uncertainty in future pedestrian trajectories, it is important to learn complex spatio-temporal representations in multi-agent scenarios. To address this, we propose a novel Cross-Correction Framework (CCF) to learn spatio-temporal representations of pedestrian trajectories better. Our framework consists of two trajectory prediction models, known as subnets, which share the same architecture and are trained with both cross-correction loss and trajectory prediction loss. Cross-correction leverages the learning from both subnets and enables them to refine their underlying representations of trajectories through a mutual correction mechanism. Specifically, we use the cross-correction loss to learn how to correct each other through an inter-subnet interaction. To induce diverse learning among the subnets, we use the transformed observed trajectories produced by a neural network as input to one subnet and the original observed trajectories as input to the other subnet. We utilize transformer-based encoder-decoder architecture for each subnet to capture motion and social interaction among pedestrians. The encoder of the transformer captures motion patterns in trajectories, while the decoder focuses on pedestrian interactions with neighbors. Each subnet performs the primary task of predicting future trajectories (a regression task) along with the secondary task of classifying the predicted trajectories (a classification task). Extensive experiments on real-world benchmark datasets such as ETH-UCY and SDD demonstrate the efficacy of our proposed framework, CCF, in precisely predicting pedestrian future trajectories. We also conducted several ablation experiments to demonstrate the effectiveness of various modules and loss functions used in our approach.

Soham Mitra, Atri Sukul, Swalpa Kumar Roy et al.

Deep learning models have achieved remarkable success across diverse domains. However, the intricate nature of these models often impedes a clear understanding of their decision-making processes. This is where Explainable AI (XAI) becomes indispensable, offering intuitive explanations for model decisions. In this work, we propose a simple yet highly effective approach, ScoreCAM++, which introduces modifications to enhance the promising ScoreCAM method for visual explainability. Our proposed approach involves altering the normalization function within the activation layer utilized in ScoreCAM, resulting in significantly improved results compared to previous efforts. Additionally, we apply an activation function to the upsampled activation layers to enhance interpretability. This improvement is achieved by selectively gating lower-priority values within the activation layer. Through extensive experiments and qualitative comparisons, we demonstrate that ScoreCAM++ consistently achieves notably superior performance and fairness in interpreting the decision-making process compared to both ScoreCAM and previous methods.

Mohammed Asad Karim, Indu Joshi, Pratik Mazumder et al.

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 learning setting. In this work, we show that the effect of catastrophic forgetting on the model prediction varies with the change in orientation of the same image, which is a novel finding. Based on this, we propose a novel data-ensemble approach that combines the predictions for the different orientations of the image to help the model retain further information regarding the previously seen classes and thereby reduce the effect of forgetting on the model predictions. However, we cannot directly use the data-ensemble approach if the model is trained using traditional techniques. Therefore, we also propose a novel dual-incremental learning framework that involves jointly training the network with two incremental learning objectives, i.e., the class-incremental learning objective and our proposed data-incremental learning objective. In the dual-incremental learning framework, each image belongs to two classes, i.e., the image class (for class-incremental learning) and the orientation class (for data-incremental learning). In class-incremental learning, each new phase introduces a new set of classes, and the model cannot access the complete training data from the older phases. In our proposed data-incremental learning, the orientation classes remain the same across all the phases, and the data introduced by the new phase in class-incremental learning acts as new training data for these orientation classes. We empirically demonstrate that the dual-incremental learning framework is vital to the data-ensemble approach. 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.

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 mitigation techniques assume that a sufficiently large number of training examples are present. However, we observe that if the training data is limited, then the effectiveness of bias mitigation methods is severely degraded. In this paper, we propose a novel approach to address this problem. Specifically, we adapt self-supervision and self-distillation to reduce the impact of biases on the model in this setting. Self-supervision and self-distillation are not used for bias mitigation. However, through this work, we demonstrate for the first time that these techniques are very effective in bias mitigation. We empirically show that our approach can significantly reduce the biases learned by the model. Further, we experimentally demonstrate that our approach is complementary to other bias mitigation strategies. Our approach significantly improves their performance and further reduces the model biases in the limited data regime. Specifically, on the L-CIFAR-10S skewed dataset, our approach significantly reduces the bias score of the baseline model by 78.22% and outperforms it in terms of accuracy by a significant absolute margin of 8.89%. It also significantly reduces the bias score for the state-of-the-art domain independent bias mitigation method by 59.26% and improves its performance by a significant absolute margin of 7.08%.

Mohammed Asad Karim, Vinay Kumar Verma, Pravendra Singh et al.

We propose a novel approach for class incremental online learning in a limited data setting. This problem setting is challenging because of the following constraints: (1) Classes are given incrementally, which necessitates a class incremental learning approach; (2) Data for each class is given in an online fashion, i.e., each training example is seen only once during training; (3) Each class has very few training examples; and (4) We do not use or assume access to any replay/memory to store data from previous classes. Therefore, in this setting, we have to handle twofold problems of catastrophic forgetting and overfitting. 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. Our proposed method leverages the meta-learning framework with knowledge consolidation. The meta-learning framework helps the model for rapid learning when samples appear in an online fashion. Simultaneously, knowledge consolidation helps to learn a robust representation against forgetting under online updates to facilitate future learning. Our approach significantly outperforms other methods on several benchmarks.

Pravendra Singh, Pratik Mazumder, Piyush Rai et al.

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 learning problem, which involves training a model on new tasks that arrive in an incremental manner. The task incremental learning problem becomes even more challenging when the test set contains classes that are not part of the train set, i.e., a task incremental generalized zero-shot learning problem. Our approach can be used in both the zero-shot and non zero-shot task incremental learning settings. Our proposed method uses weight rectifications and affine transformations in order to adapt the model to different tasks that arrive sequentially. Specifically, we adapt the network weights to work for new tasks by "rectifying" the weights learned from the previous task. We learn these weight rectifications using very few parameters. We additionally learn affine transformations on the outputs generated by the network in order to better adapt them for the new task. We perform experiments on several datasets in both zero-shot and non zero-shot task incremental learning settings and empirically show that our approach achieves state-of-the-art results. Specifically, our approach outperforms the state-of-the-art non zero-shot task incremental learning method by over 5% on the CIFAR-100 dataset. Our approach also significantly outperforms the state-of-the-art task incremental generalized zero-shot learning method by absolute margins of 6.91% and 6.33% for the AWA1 and CUB datasets, respectively. We validate our approach using various ablation studies.

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 may be given incrementally. Deep learning models need to deal with this two-fold problem in order to perform well in real-life situations. In this paper, we propose a novel Few-Shot Lifelong Learning (FSLL) method that enables deep learning models to perform lifelong/continual learning on few-shot data. Our method selects very few parameters from the model for training every new set of classes instead of training the full model. This helps in preventing overfitting. We choose the few parameters from the model in such a way that only the currently unimportant parameters get selected. By keeping the important parameters in the model intact, our approach minimizes catastrophic forgetting. Furthermore, we minimize the cosine similarity between the new and the old class prototypes in order to maximize their separation, thereby improving the classification performance. We also show that integrating our method with self-supervision improves the model performance significantly. We experimentally show that our method significantly outperforms existing methods on the miniImageNet, CIFAR-100, and CUB-200 datasets. Specifically, we outperform the state-of-the-art method by an absolute margin of 19.27% for the CUB dataset.

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 that the few examples provided are always correctly labeled. This is a strong assumption, especially if one considers the current techniques for labeling using crowd-based labeling services. We address this issue by proposing a novel robust few-shot learning approach. Our method relies on generating robust prototypes from a set of few examples. Specifically, our method refines the class prototypes by producing hybrid features from the support examples of each class. The refined prototypes help to classify the query images better. Our method can replace the evaluation phase of any few-shot learning method that uses a nearest neighbor prototype-based evaluation procedure to make them robust. We evaluate our method on standard mini-ImageNet and tiered-ImageNet datasets. We perform experiments with various label corruption rates in the support examples of the few-shot classes. We obtain significant improvement over widely used few-shot learning methods that suffer significant performance degeneration in the presence of label noise. We finally provide extensive ablation experiments to validate our method.

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 neural networks that perform well for classes with a large number of training samples and classes with less number of training samples. They employ techniques to enable the network to produce highly discriminative features that are also very generic. Generally, the better the quality and generic-nature of the features produced by the network, the better is the performance of the network on few-shot learning. Our approach aims to train networks to produce such features by using a self-supervised auxiliary task. Our proposed composite rotation based auxiliary task performs rotation at two levels, i.e., rotation of patches inside the image (inner rotation) and rotation of the whole image (outer rotation) and assigns one out of 16 rotation classes to the modified image. 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. We experimentally show that our approach performs better than existing few-shot learning methods on multiple benchmark datasets.

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. This technique aims to reduce overfitting and improve the generalization performance of the network. 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. Passive Batch Injection Training Technique (PBITT) introduces a few passive mini-batches into the training process that contain data from a distribution that is different from the input data distribution. This technique does not increase the number of parameters in the final model and also does not increase the inference (test) time but still improves the performance of deep CNNs. To the best of our knowledge, this is the first work that makes use of different data distribution to aid the training of convolutional neural networks (CNNs). We thoroughly evaluate the proposed approach on standard architectures: VGG, ResNet, and WideResNet, and on several popular datasets: CIFAR-10, CIFAR-100, SVHN, and ImageNet. We observe consistent accuracy improvement by using the proposed technique. We also show experimentally that the model trained by our technique generalizes well to other tasks such as object detection on the MS-COCO dataset using Faster R-CNN. We present extensive ablations to validate the proposed approach. Our approach improves the accuracy of VGG-16 by a significant margin of 2.1% over the CIFAR-100 dataset.

Pratik Mazumder, Pravendra Singh, Kranti Kumar Parida et al.

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 during training. 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. Our approach uses a cross-modal decoder and a composite triplet loss. The cross-modal decoder enforces a constraint that the class label text features can be reconstructed from the audio and video embeddings of data points. This helps the audio and video embeddings to move closer to the class label text embedding. The composite triplet loss makes use of the audio, video, and text embeddings. It helps bring the embeddings from the same class closer and push away the embeddings from different classes in a multi-modal setting. This helps the network to perform better on the multi-modal zero-shot learning task. Importantly, our multi-modal zero-shot learning approach works even if a modality is missing at test time. We test our approach on the generalized zero-shot classification and retrieval tasks and show that our approach outperforms other models in the presence of a single modality as well as in the presence of multiple modalities. We validate our approach by comparing it with previous approaches and using various ablations.

Rajat, Munender Varshney, Pravendra Singh et al.

Multiple categories of objects are present in most images. Treating this as a multi-class classification is not justified. We treat this as a multi-label classification problem. In this paper, we further aim to minimize the supervision required for providing supervision in multi-label classification. Specifically, we investigate an effective class of approaches that associate a weak localization with each category either in terms of the bounding box or segmentation mask. Doing so improves the accuracy of 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 crucial concern is the choice of the set of samples. In doing so, we provide a novel insight, and no specific measure succeeds in obtaining a consistently improved selection criterion. We, therefore, provide a selection criterion that consistently improves the overall baseline criterion by choosing the top k set of samples for a varied set of criteria. Using this criterion, we are able to show that we can retain more than 98% of the fully supervised performance with just 20% of samples (and more than 96% using 10%) of the dataset on PASCAL VOC 2007 and 2012. Also, our proposed approach consistently outperforms all other baseline metrics for all benchmark datasets and model combinations.

Vinay Kumar Verma, Pravendra Singh, Vinay P. Namboodiri et al.

We present a filter pruning approach for deep model compression, using a multitask network. Our approach is based on learning a a pruner network to prune a pre-trained target network. 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. The pruner network has the same architecture as the original network except that it has a multitask/multi-output last layer containing binary-valued outputs (one per filter), which indicate which filters have to be pruned. The pruner's goal is to minimize the number of filters from the original network by assigning zero weights to the corresponding output feature-maps. In contrast to most of the existing methods, instead of relying on iterative pruning, our approach can prune the network (original network) in one go and, moreover, does not require specifying the degree of pruning for each layer (and can learn it instead). The compressed model produced by our approach is generic and does not need any special hardware/software support. Moreover, augmenting with other methods such as knowledge distillation, quantization, and connection pruning can increase the degree of compression for the proposed approach. We show the efficacy of our proposed approach for classification and object detection tasks.

Pravendra Singh, Munender Varshney, Vinay P. Namboodiri

Researchers have proposed various activation functions. These activation functions help the deep network to learn non-linear behavior with a significant effect on training dynamics and task performance. The performance of these activations also depends on the initial state of the weight parameters, i.e., different initial state leads to a difference in the performance of a network. In this paper, we have proposed a cooperative initialization for training the deep network using ReLU activation function to improve the network performance. Our approach uses multiple activation functions in the initial few epochs for the update of all sets of weight parameters while training the network. These activation functions cooperate to overcome their drawbacks in the update of weight parameters, which in effect learn better "feature representation" and boost the network performance later. Cooperative initialization based training also helps in reducing the overfitting problem and does not increase the number of parameters, inference (test) time in the final model while improving the performance. Experiments show that our approach outperforms various baselines and, at the same time, performs well over various tasks such as classification and detection. The Top-1 classification accuracy of the model trained using our approach improves by 2.8% for VGG-16 and 2.1% for ResNet-56 on CIFAR-100 dataset.

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 reduction. However, the PWC ignores the spatial information around the points it is processing. This design is by choice, in order to reduce the overall parameters and computations. However, we hypothesize that this shortcoming of PWC has a significant impact on the network performance. We propose an alternative design for pointwise convolution, which uses spatial information from the input efficiently. Our design significantly improves the performance of the networks without substantially increasing the number of parameters and computations. We experimentally show that our design results in significant improvement in the performance of the network for classification as well as detection.

Pravendra Singh, Vinay Kumar Verma, Piyush Rai et al.

While convolutional neural networks (CNN) have achieved impressive performance on various classification/recognition tasks, they typically consist of a massive number of parameters. This results in significant memory requirement as well as computational overheads. Consequently, there is a growing need for filter-level pruning approaches for compressing CNN based models that not only reduce the total number of parameters but reduce the overall computation as well. We present a new min-max framework for filter-level pruning of CNNs. 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. Our framework consists of two modules: (1) An adaptive filter pruning (AFP) module, which minimizes the number of filters in the model; and (2) A pruning rate controller (PRC) module, which maximizes the accuracy during pruning. Moreover, unlike most previous approaches, our approach allows directly specifying the desired error tolerance instead of pruning level. Our compressed models can be deployed at run-time, without requiring any special libraries or hardware. Our approach reduces the number of parameters of VGG-16 by an impressive factor of 17.5X, and number of FLOPS by 6.43X, with no loss of accuracy, significantly outperforming other state-of-the-art filter pruning methods.

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 success, by extracting useful features from the inputs. 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). These approaches have achieved better performance by Exciting up the important channels or feature maps while diminishing the rest. However, in the process, architectural complexity has increased. We propose an architectural block that introduces much lower complexity than the existing methods of CNN performance boosting while performing significantly better than them. We carry out experiments on the CIFAR, ImageNet and MS-COCO datasets, and show that the proposed block can challenge the state-of-the-art results. Our method boosts the ResNet-50 architecture to perform comparably to the ResNet-152 architecture, which is a three times deeper network, on classification. We also show experimentally that our method is not limited to classification but also generalizes well to other tasks such as object detection.

Pravendra Singh, Vinay Kumar Verma, Piyush Rai et al.

We present a novel deep learning architecture in which the convolution operation leverages heterogeneous kernels. The proposed HetConv (Heterogeneous Kernel-Based Convolution) reduces the computation (FLOPs) and the number of parameters as compared to standard convolution operation while still maintaining representational efficiency. To show the effectiveness of our proposed convolution, we present extensive experimental results on the standard convolutional neural network (CNN) architectures such as VGG \cite{vgg2014very} and ResNet \cite{resnet}. We find that after replacing the standard convolutional filters in these architectures with our proposed HetConv filters, we achieve 3X to 8X FLOPs based improvement in speed while still maintaining (and sometimes improving) the accuracy. We also compare our proposed convolutions with group/depth wise convolutions and show that it achieves more FLOPs reduction with significantly higher accuracy.

Pravendra Singh, Vinay Kumar Verma, Piyush Rai et al.

We present a filter correlation based model compression approach for deep convolutional neural networks. Our approach iteratively identifies pairs of filters with the largest pairwise correlations and drops one of the filters from each such pair. However, instead of discarding one of the filters from each such pair naïvely, the model is re-optimized to make the filters in these pairs maximally correlated, so that discarding one of the filters from the pair results in minimal information loss. Moreover, after discarding the filters in each round, we further finetune the model to recover from the potential small loss incurred by the compression. We evaluate our proposed approach using a comprehensive set of experiments and ablation studies. Our compression method yields state-of-the-art FLOPs compression rates on various benchmarks, such as LeNet-5, VGG-16, and ResNet-50,56, while still achieving excellent predictive performance for tasks such as object detection on benchmark datasets.

Pravendra Singh, Manikandan R, Neeraj Matiyali et al.

We propose a framework for compressing state-of-the-art Single Shot MultiBox Detector (SSD). The framework addresses compression in the following stages: Sparsity Induction, Filter Selection, and Filter Pruning. In the Sparsity Induction stage, the object detector model is sparsified via an improved global threshold. In Filter Selection & Pruning stage, we select and remove filters using sparsity statistics of filter weights in two consecutive convolutional layers. This results in the model with the size smaller than most existing compact architectures. We evaluate the performance of our framework with multiple datasets and compare over multiple methods. Experimental results show that our method achieves state-of-the-art compression of 6.7X and 4.9X on PASCAL VOC dataset on models SSD300 and SSD512 respectively. We further show that the method produces maximum compression of 26X with SSD512 on German Traffic Sign Detection Benchmark (GTSDB). 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. In addition to this, our method does not require any special libraries or hardware support for the resulting compressed models.

Pravendra Singh, Vinay Sameer Raja Kadi, Nikhil Verma et al.

Convolutional neural networks (CNN) have achieved impressive performance on the wide variety of tasks (classification, detection, etc.) across multiple domains at the cost of high computational and memory requirements. Thus, leveraging CNNs for real-time applications necessitates model compression approaches that not only reduce the total number of parameters but reduce the overall computation as well. In this work, we present a stability-based approach for filter-level pruning of CNNs. We evaluate our proposed approach on different architectures (LeNet, VGG-16, ResNet, and Faster RCNN) and datasets and demonstrate its generalizability through extensive experiments. Moreover, our compressed models can be used at run-time without requiring any special libraries or hardware. Our model compression method reduces the number of FLOPS by an impressive factor of 6.03X and GPU memory footprint by more than 17X, significantly outperforming other state-of-the-art filter pruning methods.

Pravendra Singh

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. The game runs in computer system's terminals. Mainly, it was developed for UNIX-type systems but it works pretty well in nearly all the operating systems because of cross-platform compatibility of the programming language used. The game uses language's concurrency primitives to simplify most of the hefty parts of the game. A real-time notification delivery architecture is developed using language's built-in concurrency support, which performs similar to event based context aware invocations like we see on the web platform.