Pranav Jeevan

Pranav Jeevan, Kavitha Viswanathan, Anandu A S et al.

We propose a novel neural architecture for computer vision -- WaveMix -- that is resource-efficient and yet generalizable and scalable. While using fewer trainable parameters, GPU RAM, and computations, WaveMix networks achieve comparable or better accuracy than the state-of-the-art convolutional neural networks, vision transformers, and token mixers for several tasks. This efficiency can translate to savings in time, cost, and energy. To achieve these gains we used multi-level two-dimensional discrete wavelet transform (2D-DWT) in WaveMix blocks, which has the following advantages: (1) It reorganizes spatial information based on three strong image priors -- scale-invariance, shift-invariance, and sparseness of edges -- (2) in a lossless manner without adding parameters, (3) while also reducing the spatial sizes of feature maps, which reduces the memory and time required for forward and backward passes, and (4) expanding the receptive field faster than convolutions do. The whole architecture is a stack of self-similar and resolution-preserving WaveMix blocks, which allows architectural flexibility for various tasks and levels of resource availability. WaveMix establishes new benchmarks for segmentation on Cityscapes; and for classification on Galaxy 10 DECals, Places-365, five EMNIST datasets, and iNAT-mini and performs competitively on other benchmarks. Our code and trained models are publicly available.

Pranav Jeevan, Neeraj Nixon, Amit Sethi

Recent advancements in single image super-resolution have been predominantly driven by token mixers and transformer architectures. WaveMixSR utilized the WaveMix architecture, employing a two-dimensional discrete wavelet transform for spatial token mixing, achieving superior performance in super-resolution tasks with remarkable resource efficiency. In this work, we present an enhanced version of the WaveMixSR architecture by (1) replacing the traditional transpose convolution layer with a pixel shuffle operation and (2) implementing a multistage design for higher resolution tasks ($4\times$). Our experiments demonstrate that our enhanced model -- WaveMixSR-V2 -- outperforms other architectures in multiple super-resolution tasks, achieving state-of-the-art for the BSD100 dataset, while also consuming fewer resources, exhibits higher parameter efficiency, lower latency and higher throughput. Our code is available at https://github.com/pranavphoenix/WaveMixSR.

Pranav Jeevan, Amit Sethi

Although certain vision transformer (ViT) and CNN architectures generalize well on vision tasks, it is often impractical to use them on green, edge, or desktop computing due to their computational requirements for training and even testing. We present WaveMix as an alternative neural architecture that uses a multi-scale 2D discrete wavelet transform (DWT) for spatial token mixing. Unlike ViTs, WaveMix neither unrolls the image nor requires self-attention of quadratic complexity. Additionally, DWT introduces another inductive bias -- besides convolutional filtering -- to utilize the 2D structure of an image to improve generalization. The multi-scale nature of the DWT also reduces the requirement for a deeper architecture compared to the CNNs, as the latter relies on pooling for partial spatial mixing. WaveMix models show generalization that is competitive with ViTs, CNNs, and token mixers on several datasets while requiring lower GPU RAM (training and testing), number of computations, and storage. WaveMix have achieved State-of-the-art (SOTA) results in EMNIST Byclass and EMNIST Balanced datasets.

Pranav Jeevan, Akella Srinidhi, Pasunuri Prathiba et al.

Image super-resolution research recently been dominated by transformer models which need higher computational resources than CNNs due to the quadratic complexity of self-attention. We propose a new neural network -- WaveMixSR -- for image super-resolution based on WaveMix architecture which uses a 2D-discrete wavelet transform for spatial token-mixing. Unlike transformer-based models, WaveMixSR does not unroll the image as a sequence of pixels/patches. It uses the inductive bias of convolutions along with the lossless token-mixing property of wavelet transform to achieve higher performance while requiring fewer resources and training data. We compare the performance of our network with other state-of-the-art methods for image super-resolution. Our experiments show that WaveMixSR achieves competitive performance in all datasets and reaches state-of-the-art performance in the BSD100 dataset on multiple super-resolution tasks. Our model is able to achieve this performance using less training data and computational resources while maintaining high parameter efficiency compared to current state-of-the-art models.

Sunny Gupta, Mohit Jindal, Pankhi Kashyap et al.

Federated learning faces a critical challenge in balancing communication efficiency with rapid convergence, especially for second-order methods. While Newton-type algorithms achieve linear convergence in communication rounds, transmitting full Hessian matrices is often impractical due to quadratic complexity. We introduce Federated Learning with Enhanced Nesterov-Newton Sketch (FLeNS), a novel method that harnesses both the acceleration capabilities of Nesterov's method and the dimensionality reduction benefits of Hessian sketching. FLeNS approximates the centralized Newton's method without relying on the exact Hessian, significantly reducing communication overhead. By combining Nesterov's acceleration with adaptive Hessian sketching, FLeNS preserves crucial second-order information while preserving the rapid convergence characteristics. Our theoretical analysis, grounded in statistical learning, demonstrates that FLeNS achieves super-linear convergence rates in communication rounds - a notable advancement in federated optimization. We provide rigorous convergence guarantees and characterize tradeoffs between acceleration, sketch size, and convergence speed. Extensive empirical evaluation validates our theoretical findings, showcasing FLeNS's state-of-the-art performance with reduced communication requirements, particularly in privacy-sensitive and edge-computing scenarios. The code is available at https://github.com/sunnyinAI/FLeNS

Akhila Krishna K, Ravi Kant Gupta, Nikhil Cherian Kurian et al.

The heterogeneity of breast cancer presents considerable challenges for its early detection, prognosis, and treatment selection. Convolutional neural networks often neglect the spatial relationships within histopathological images, which can limit their accuracy. Graph neural networks (GNNs) offer a promising solution by coding the spatial relationships within images. Prior studies have investigated the modeling of histopathological images as cell and tissue graphs, but they have not fully tapped into the potential of extracting interrelationships between these biological entities. In this paper, we present a novel approach using a heterogeneous GNN that captures the spatial and hierarchical relations between cell and tissue graphs to enhance the extraction of useful information from histopathological images. We also compare the performance of a cross-attention-based network and a transformer architecture for modeling the intricate relationships within tissue and cell graphs. Our model demonstrates superior efficiency in terms of parameter count and achieves higher accuracy compared to the transformer-based state-of-the-art approach on three publicly available breast cancer datasets -- BRIGHT, BreakHis, and BACH.

Pranav Jeevan, Nikhil Cherian Kurian, Amit Sethi

Convolution Neural Networks (CNNs) are widely used in medical image analysis, but their performance degrade when the magnification of testing images differ from the training images. The inability of CNNs to generalize across magnification scales can result in sub-optimal performance on external datasets. This study aims to evaluate the robustness of various deep learning architectures in the analysis of breast cancer histopathological images with varying magnification scales at training and testing stages. Here we explore and compare the performance of multiple deep learning architectures, including CNN-based ResNet and MobileNet, self-attention-based Vision Transformers and Swin Transformers, and token-mixing models, such as FNet, ConvMixer, MLP-Mixer, and WaveMix. The experiments are conducted using the BreakHis dataset, which contains breast cancer histopathological images at varying magnification levels. We show that performance of WaveMix is invariant to the magnification of training and testing data and can provide stable and good classification accuracy. These evaluations are critical in identifying deep learning architectures that can robustly handle changes in magnification scale, ensuring that scale changes across anatomical structures do not disturb the inference results.

Chirag P, Mukta Wagle, Ravi Kant Gupta et al.

We propose a new technique called CHATTY: Coupled Holistic Adversarial Transport Terms with Yield for Unsupervised Domain Adaptation. Adversarial training is commonly used for learning domain-invariant representations by reversing the gradients from a domain discriminator head to train the feature extractor layers of a neural network. We propose significant modifications to the adversarial head, its training objective, and the classifier head. With the aim of reducing class confusion, we introduce a sub-network which displaces the classifier outputs of the source and target domain samples in a learnable manner. We control this movement using a novel transport loss that spreads class clusters away from each other and makes it easier for the classifier to find the decision boundaries for both the source and target domains. The results of adding this new loss to a careful selection of previously proposed losses leads to improvement in UDA results compared to the previous state-of-the-art methods on benchmark datasets. We show the importance of the proposed loss term using ablation studies and visualization of the movement of target domain sample in representation space.

Ashish Prasad, Pranav Jeevan, Amit Sethi

Current video summarization methods largely rely on transformer-based architectures, which, due to their quadratic complexity, require substantial computational resources. In this work, we address these inefficiencies by enhancing the Direct-to-Summarize Network (DSNet) with more resource-efficient token mixing mechanisms. We show that replacing traditional attention with alternatives like Fourier, Wavelet transforms, and Nyströmformer improves efficiency and performance. Furthermore, we explore various pooling strategies within the Regional Proposal Network, including ROI pooling, Fast Fourier Transform pooling, and flat pooling. Our experimental results on TVSum and SumMe datasets demonstrate that these modifications significantly reduce computational costs while maintaining competitive summarization performance. Thus, our work offers a more scalable solution for video summarization tasks.

Pranav Jeevan, Dharshan Sampath Kumar, Amit Sethi

Image inpainting, which refers to the synthesis of missing regions in an image, can help restore occluded or degraded areas and also serve as a precursor task for self-supervision. The current state-of-the-art models for image inpainting are computationally heavy as they are based on transformer or CNN backbones that are trained in adversarial or diffusion settings. This paper diverges from vision transformers by using a computationally-efficient WaveMix-based fully convolutional architecture -- WavePaint. It uses a 2D-discrete wavelet transform (DWT) for spatial and multi-resolution token-mixing along with convolutional layers. The proposed model outperforms the current state-of-the-art models for image inpainting on reconstruction quality while also using less than half the parameter count and considerably lower training and evaluation times. Our model even outperforms current GAN-based architectures in CelebA-HQ dataset without using an adversarially trainable discriminator. Our work suggests that neural architectures that are modeled after natural image priors require fewer parameters and computations to achieve generalization comparable to transformers.

Ardhendu Sekhar, Vasu Soni, Keshav Aske et al.

Accurate survival prediction from histopathology whole-slide images (WSIs) remains challenging due to their gigapixel resolution, strong spatial heterogeneity, and complex survival distributions. We introduce a comprehensive computational pathology framework that addresses these limitations through four complementary innovations: (1) Quantile-Gated Patch Selection for dynamically identifying prognostically relevant regions, (2) Graph-Guided Clustering to group patches by spatial and morphological similarity, (3) Hierarchical Context Attention to model both local tissue interactions and global slide-level context, and (4) an Expert-Driven Mixture of Log-Logistics module that flexibly models complex survival distributions. Across large TCGA cohorts, our method achieves state-of-the-art performance, yielding time-dependent concordance indices of 0.644 on LUAD, 0.751 on KIRC, and 0.752 on BRCA, consistently outperforming both histology-only and multimodal baselines. The framework further provides improved calibration and interpretability, advancing the use of WSIs for personalized cancer prognosis.

Pranav Jeevan, Amit Sethi

In contemporary computer vision applications, particularly image classification, architectural backbones pre-trained on large datasets like ImageNet are commonly employed as feature extractors. Despite the widespread use of these pre-trained convolutional neural networks (CNNs), there remains a gap in understanding the performance of various resource-efficient backbones across diverse domains and dataset sizes. Our study systematically evaluates multiple lightweight, pre-trained CNN backbones under consistent training settings across a variety of datasets, including natural images, medical images, galaxy images, and remote sensing images. This comprehensive analysis aims to aid machine learning practitioners in selecting the most suitable backbone for their specific problem, especially in scenarios involving small datasets where fine-tuning a pre-trained network is crucial. Even though attention-based architectures are gaining popularity, we observed that they tend to perform poorly under low data finetuning tasks compared to CNNs. We also observed that some CNN architectures such as ConvNeXt, RegNet and EfficientNet performs well compared to others on a diverse set of domains consistently. Our findings provide actionable insights into the performance trade-offs and effectiveness of different backbones, facilitating informed decision-making in model selection for a broad spectrum of computer vision domains. Our code is available here: https://github.com/pranavphoenix/Backbones

Pranav Jeevan, Neeraj Nixon, Amit Sethi

We introduce a new metric to assess the quality of generated images that is more reliable, data-efficient, compute-efficient, and adaptable to new domains than the previous metrics, such as Fréchet Inception Distance (FID). The proposed metric is based on normalizing flows, which allows for the computation of density (exact log-likelihood) of images from any domain. Thus, unlike FID, the proposed Flow-based Likelihood Distance Plus (FLD+) metric exhibits strongly monotonic behavior with respect to different types of image degradations, including noise, occlusion, diffusion steps, and generative model size. Additionally, because normalizing flow can be trained stably and efficiently, FLD+ achieves stable results with two orders of magnitude fewer images than FID (which requires more images to reliably compute Fréchet distance between features of large samples of real and generated images). We made FLD+ computationally even more efficient by applying normalizing flows to features extracted in a lower-dimensional latent space instead of using a pre-trained network. We also show that FLD+ can easily be retrained on new domains, such as medical images, unlike the networks behind previous metrics -- such as InceptionNetV3 pre-trained on ImageNet.

Akhila Krishna, Ravi Kant Gupta, Pranav Jeevan et al.

Gene selection plays a pivotal role in oncology research for improving outcome prediction accuracy and facilitating cost-effective genomic profiling for cancer patients. This paper introduces two gene selection strategies for deep learning-based survival prediction models. The first strategy uses a sparsity-inducing method while the second one uses importance based gene selection for identifying relevant genes. Our overall approach leverages the power of deep learning to model complex biological data structures, while sparsity-inducing methods ensure the selection process focuses on the most informative genes, minimizing noise and redundancy. Through comprehensive experimentation on diverse genomic and survival datasets, we demonstrate that our strategy not only identifies gene signatures with high predictive power for survival outcomes but can also streamlines the process for low-cost genomic profiling. The implications of this research are profound as it offers a scalable and effective tool for advancing personalized medicine and targeted cancer therapies. By pushing the boundaries of gene selection methodologies, our work contributes significantly to the ongoing efforts in cancer genomics, promising improved diagnostic and prognostic capabilities in clinical settings.

Ardhendu Sekhar, Vasu Soni, Keshav Aske et al.

We propose a modular framework for predicting cancer specific survival directly from whole slide pathology images (WSIs). The framework consists of four key stages designed to capture prognostic and morphological heterogeneity. First, a Quantile Based Patch Filtering module selects prognostically informative tissue regions through quantile thresholding. Second, Graph Regularized Patch Clustering models phenotype level variations using a k nearest neighbor graph that enforces spatial and morphological coherence. Third, Hierarchical Feature Aggregation learns both intra and inter cluster dependencies to represent multiscale tumor organization. Finally, an Expert Guided Mixture Density Model estimates complex survival distributions via Gaussian mixtures, enabling fine grained risk prediction. Evaluated on TCGA LUAD, TCGA KIRC, and TCGA BRCA cohorts, our model achieves concordance indices of 0.653 ,0.719 ,and 0.733 respectively, surpassing existing state of the art approaches in survival prediction from WSIs.

Pranav Jeevan, Neeraj Nixon, Abhijeet Patil et al.

Our study introduces ResNet-L2 (RL2), a novel metric for evaluating generative models and image quality in histopathology, addressing limitations of traditional metrics, such as Frechet inception distance (FID), when the data is scarce. RL2 leverages ResNet features with a normalizing flow to calculate RMSE distance in the latent space, providing reliable assessments across diverse histopathology datasets. We evaluated the performance of RL2 on degradation types, such as blur, Gaussian noise, salt-and-pepper noise, and rectangular patches, as well as diffusion processes. RL2's monotonic response to increasing degradation makes it well-suited for models that assess image quality, proving a valuable advancement for evaluating image generation techniques in histopathology. It can also be used to discard low-quality patches while sampling from a whole slide image. It is also significantly lighter and faster compared to traditional metrics and requires fewer images to give stable metric value.

Pranav Jeevan, Amit sethi

Vision transformers (ViTs) have found only limited practical use in processing images, in spite of their state-of-the-art accuracy on certain benchmarks. The reason for their limited use include their need for larger training datasets and more computational resources compared to convolutional neural networks (CNNs), owing to the quadratic complexity of their self-attention mechanism. We propose a linear attention-convolution hybrid architecture -- Convolutional X-formers for Vision (CXV) -- to overcome these limitations. We replace the quadratic attention with linear attention mechanisms, such as Performer, Nyströmformer, and Linear Transformer, to reduce its GPU usage. Inductive prior for image data is provided by convolutional sub-layers, thereby eliminating the need for class token and positional embeddings used by the ViTs. We also propose a new training method where we use two different optimizers during different phases of training and show that it improves the top-1 image classification accuracy across different architectures. CXV outperforms other architectures, token mixers (e.g. ConvMixer, FNet and MLP Mixer), transformer models (e.g. ViT, CCT, CvT and hybrid Xformers), and ResNets for image classification in scenarios with limited data and GPU resources (cores, RAM, power).

Anirudh Mittal, Pranav Jeevan, Prerak Gandhi et al.

Computational Humour (CH) has attracted the interest of Natural Language Processing and Computational Linguistics communities. Creating datasets for automatic measurement of humour quotient is difficult due to multiple possible interpretations of the content. In this work, we create a multi-modal humour-annotated dataset ($\sim$40 hours) using stand-up comedy clips. We devise a novel scoring mechanism to annotate the training data with a humour quotient score using the audience's laughter. The normalized duration (laughter duration divided by the clip duration) of laughter in each clip is used to compute this humour coefficient score on a five-point scale (0-4). This method of scoring is validated by comparing with manually annotated scores, wherein a quadratic weighted kappa of 0.6 is obtained. We use this dataset to train a model that provides a "funniness" score, on a five-point scale, given the audio and its corresponding text. We compare various neural language models for the task of humour-rating and achieve an accuracy of $0.813$ in terms of Quadratic Weighted Kappa (QWK). Our "Open Mic" dataset is released for further research along with the code.

Pranav Jeevan, Amit Sethi

Although transformers have become the neural architectures of choice for natural language processing, they require orders of magnitude more training data, GPU memory, and computations in order to compete with convolutional neural networks for computer vision. The attention mechanism of transformers scales quadratically with the length of the input sequence, and unrolled images have long sequence lengths. Plus, transformers lack an inductive bias that is appropriate for images. We tested three modifications to vision transformer (ViT) architectures that address these shortcomings. Firstly, we alleviate the quadratic bottleneck by using linear attention mechanisms, called X-formers (such that, X in {Performer, Linformer, Nyströmformer}), thereby creating Vision X-formers (ViXs). This resulted in up to a seven times reduction in the GPU memory requirement. We also compared their performance with FNet and multi-layer perceptron mixers, which further reduced the GPU memory requirement. Secondly, we introduced an inductive bias for images by replacing the initial linear embedding layer by convolutional layers in ViX, which significantly increased classification accuracy without increasing the model size. Thirdly, we replaced the learnable 1D position embeddings in ViT with Rotary Position Embedding (RoPE), which increases the classification accuracy for the same model size. We believe that incorporating such changes can democratize transformers by making them accessible to those with limited data and computing resources.