Tapan Kumar Gandhi

Ankita Raj, Kaashika Prajaapat, Tapan Kumar Gandhi et al.

The human visual system is remarkably adept at adapting to changes in the input distribution; a capability modern convolutional neural networks (CNNs) still struggle to match. Drawing inspiration from the developmental trajectory of human vision, we propose a progressive blurring curriculum to improve the generalization and robustness of CNNs. Human infants are born with poor visual acuity, gradually refining their ability to perceive fine details. Mimicking this process, we begin training CNNs on highly blurred images during the initial epochs and progressively reduce the blur as training advances. This approach encourages the network to prioritize global structures over high-frequency artifacts, improving robustness against distribution shifts and noisy inputs. Challenging prior claims that blurring in the initial training epochs imposes a stimulus deficit and irreversibly harms model performance, we reveal that early-stage blurring enhances generalization with minimal impact on in-domain accuracy. Our experiments demonstrate that the proposed curriculum reduces mean corruption error (mCE) by up to 8.30% on CIFAR-10-C and 4.43% on ImageNet-100-C datasets, compared to standard training without blurring. Unlike static blur-based augmentation, which applies blurred images randomly throughout training, our method follows a structured progression, yielding consistent gains across various datasets. Furthermore, our approach complements other augmentation techniques, such as CutMix and MixUp, and enhances both natural and adversarial robustness against common attack methods. Code is available at https://github.com/rajankita/Visual_Acuity_Curriculum.

Rohit Misra, Sapna S Mishra, Tapan K. Gandhi

Damage to the inferior frontal gyrus (Broca's area) can cause agrammatic aphasia wherein patients, although able to comprehend, lack the ability to form complete sentences. This inability leads to communication gaps which cause difficulties in their daily lives. The usage of assistive devices can help in mitigating these issues and enable the patients to communicate effectively. However, due to lack of large scale studies of linguistic deficits in aphasia, research on such assistive technology is relatively limited. In this work, we present two contributions that aim to re-initiate research and development in this field. Firstly, we propose a model that uses linguistic features from small scale studies on aphasia patients and generates large scale datasets of synthetic aphasic utterances from grammatically correct datasets. We show that the mean length of utterance, the noun/verb ratio, and the simple/complex sentence ratio of our synthetic datasets correspond to the reported features of aphasic speech. Further, we demonstrate how the synthetic datasets may be utilized to develop assistive devices for aphasia patients. The pre-trained T5 transformer is fine-tuned using the generated dataset to suggest 5 corrected sentences given an aphasic utterance as input. We evaluate the efficacy of the T5 model using the BLEU and cosine semantic similarity scores. Affirming results with BLEU score of 0.827/1.00 and semantic similarity of 0.904/1.00 were obtained. These results provide a strong foundation for the concept that a synthetic dataset based on small scale studies on aphasia can be used to develop effective assistive technology.

Pooja Singh, Siddhant Ujjain, Tapan Kumar Gandhi et al.

Recent advances in multimodal large language models have enabled unified processing of visual and textual inputs, offering promising applications in general-purpose medical AI. However, their ability to generalize compositionally across unseen combinations of imaging modality, anatomy, and task type remains underexplored. We introduce CrossMed, a benchmark designed to evaluate compositional generalization (CG) in medical multimodal LLMs using a structured Modality-Anatomy-Task (MAT) schema. CrossMed reformulates four public datasets, CheXpert (X-ray classification), SIIM-ACR (X-ray segmentation), BraTS 2020 (MRI classification and segmentation), and MosMedData (CT classification) into a unified visual question answering (VQA) format, resulting in 20,200 multiple-choice QA instances. We evaluate two open-source multimodal LLMs, LLaVA-Vicuna-7B and Qwen2-VL-7B, on both Related and Unrelated MAT splits, as well as a zero-overlap setting where test triplets share no Modality, Anatomy, or Task with the training data. Models trained on Related splits achieve 83.2 percent classification accuracy and 0.75 segmentation cIoU, while performance drops significantly under Unrelated and zero-overlap conditions, demonstrating the benchmark difficulty. We also show cross-task transfer, where segmentation performance improves by 7 percent cIoU even when trained using classification-only data. Traditional models (ResNet-50 and U-Net) show modest gains, confirming the broad utility of the MAT framework, while multimodal LLMs uniquely excel at compositional generalization. CrossMed provides a rigorous testbed for evaluating zero-shot, cross-task, and modality-agnostic generalization in medical vision-language models.

Akshat Kishore Shrivastava, Tapan Kumar Gandhi · meta-ai

In this paper, we propose an novel methodology aimed at simulating the learning phenomenon of nystagmus through the application of differential blurring on datasets. Nystagmus is a biological phenomenon that influences human vision throughout life, notably by diminishing head shake from infancy to adulthood. Leveraging this concept, we address the issue of waste classification, a pressing global concern. The proposed framework comprises two modules, with the second module closely resembling the original Vision Transformer, a state-of-the-art model model in classification tasks. The primary motivation behind our approach is to enhance the model's precision and adaptability, mirroring the real-world conditions that the human visual system undergoes. This novel methodology surpasses the standard Vision Transformer model in waste classification tasks, exhibiting an improvement with a margin of 2%. This improvement underscores the potential of our methodology in improving model precision by drawing inspiration from human vision perception. Further research in the proposed methodology could yield greater performance results, and can be extrapolated to other global issues.

Chetan Ralekar, Shubham Choudhary, Tapan Kumar Gandhi et al.

Human observers engage in selective information uptake when classifying visual patterns. The same is true of deep neural networks, which currently constitute the best performing artificial vision systems. Our goal is to examine the congruence, or lack thereof, in the information-gathering strategies of the two systems. We have operationalized our investigation as a character recognition task. We have used eye-tracking to assay the spatial distribution of information hotspots for humans via fixation maps and an activation mapping technique for obtaining analogous distributions for deep networks through visualization maps. Qualitative comparison between visualization maps and fixation maps reveals an interesting correlate of congruence. The deep learning model considered similar regions in character, which humans have fixated in the case of correctly classified characters. On the other hand, when the focused regions are different for humans and deep nets, the characters are typically misclassified by the latter. Hence, we propose to use the visual fixation maps obtained from the eye-tracking experiment as a supervisory input to align the model's focus on relevant character regions. We find that such supervision improves the model's performance significantly and does not require any additional parameters. This approach has the potential to find applications in diverse domains such as medical analysis and surveillance in which explainability helps to determine system fidelity.

Rohan Wadhawan, Tapan K. Gandhi

Facial Expression Recognition from static images is a challenging problem in computer vision applications. Convolutional Neural Network (CNN), the state-of-the-art method for various computer vision tasks, has had limited success in predicting expressions from faces having extreme poses, illumination, and occlusion conditions. To mitigate this issue, CNNs are often accompanied by techniques like transfer, multi-task, or ensemble learning that often provide high accuracy at the cost of increased computational complexity. In this work, we propose a Part-based Ensemble Transfer Learning network that models how humans recognize facial expressions by correlating the spatial orientation pattern of the facial features with a specific expression. It consists of 5 sub-networks, and each sub-network performs transfer learning from one of the five subsets of facial landmarks: eyebrows, eyes, nose, mouth, or jaw to expression classification. We show that our proposed ensemble network uses visual patterns emanating from facial muscles' motor movements to predict expressions and demonstrate the usefulness of transfer learning from Facial Landmark Localization to Facial Expression Recognition. We test the proposed network on the CK+, JAFFE, and SFEW datasets, and it outperforms the benchmark for CK+ and JAFFE datasets by 0.51% and 5.34%, respectively. Additionally, the proposed ensemble network consists of only 1.65M model parameters, ensuring computational efficiency during training and real-time deployment. Grad-CAM visualizations of our proposed ensemble highlight the complementary nature of its sub-networks, a key design parameter of an effective ensemble network. Lastly, cross-dataset evaluation results reveal that our proposed ensemble has a high generalization capacity, making it suitable for real-world usage.

Sai Sukruth Bezugam, Swatilekha Majumdar, Chetan Ralekar et al.

This paper proposes an efficient video summarization framework that will give a gist of the entire video in a few key-frames or video skims. Existing video summarization frameworks are based on algorithms that utilize computer vision low-level feature extraction or high-level domain level extraction. However, being the ultimate user of the summarized video, humans remain the most neglected aspect. Therefore, the proposed paper considers human's role in summarization and introduces human visual attention-based summarization techniques. To understand human attention behavior, we have designed and performed experiments with human participants using electroencephalogram (EEG) and eye-tracking technology. The EEG and eye-tracking data obtained from the experimentation are processed simultaneously and used to segment frames containing useful information from a considerable video volume. Thus, the frame segmentation primarily relies on the cognitive judgments of human beings. Using our approach, a video is summarized by 96.5% while maintaining higher precision and high recall factors. The comparison with the state-of-the-art techniques demonstrates that the proposed approach yields ceiling-level performance with reduced computational cost in summarising the videos.

Shiva Azimi, Tapan K. Gandhi

Plant Phenomics can be used to monitor the health and the growth of plants. Computer vision applications like stereo reconstruction, image retrieval, object tracking, and object recognition play an important role in imaging based plant phenotyping. This paper offers a comparative evaluation of some popular 3D correspondence grouping algorithms, motivated by the important role that they can play in tasks such as model creation, plant recognition and identifying plant parts. Another contribution of this paper is the extension of 2D maximum likelihood matching to 3D Maximum Likelihood Estimation Sample Consensus (MLEASAC). MLESAC is efficient and is computationally less intense than 3D random sample consensus (RANSAC). We test these algorithms on 3D point clouds of plants along with two standard benchmarks addressing shape retrieval and point cloud registration scenarios. The performance is evaluated in terms of precision and recall.

Shiva Azimi, Brejesh lall, Tapan K. Gandhi

Plant Phenomics based on imaging based techniques can be used to monitor the health and the diseases of plants and crops. The use of 3D data for plant phenomics is a recent phenomenon. However, since 3D point cloud contains more information than plant images, in this paper, we compare the performance of different keypoint detectors and local feature descriptors combinations for the plant growth stage and it's growth condition classification based on 3D point clouds of the plants. We have also implemented a modified form of 3D SIFT descriptor, that is invariant to rotation and is computationally less intense than most of the 3D SIFT descriptors reported in the existing literature. The performance is evaluated in terms of the classification accuracy and the results are presented in terms of accuracy tables. We find the ISS-SHOT and the SIFT-SIFT combinations consistently perform better and Fisher Vector (FV) is a better encoder than Vector of Linearly Aggregated (VLAD) for such applications. It can serve as a better modality.

Tanvi Gupta, Pranay Manocha, Tapan K. Gandhi et al.

The diagnosis and segmentation of tumors using any medical diagnostic tool can be challenging due to the varying nature of this pathology. Magnetic Reso- nance Imaging (MRI) is an established diagnostic tool for various diseases and disorders and plays a major role in clinical neuro-diagnosis. Supplementing this technique with automated classification and segmentation tools is gaining importance, to reduce errors and time needed to make a conclusive diagnosis. In this paper a simple three-step algorithm is proposed; (1) identification of patients that present with tumors, (2) automatic selection of abnormal slices of the patients, and (3) segmentation and detection of the tumor. Features were extracted by using discrete wavelet transform on the normalized images and classified by support vector machine (for step (1)) and random forest (for step (2)). The 400 subjects were divided in a 3:1 ratio between training and test with no overlap. This study is novel in terms of use of data, as it employed the entire T2 weighted slices as a single image for classification and a unique combination of contralateral approach with patch thresholding for segmentation, which does not require a training set or a template as is used by most segmentation studies. Using the proposed method, the tumors were segmented accurately with a classification accuracy of 95% with 100% specificity and 90% sensitivity.

Pranay Manocha, Snehal Bhasme, Tanvi Gupta et al.

Magnetic Resonance Imaging (MRI) is an important diagnostic tool for precise detection of various pathologies. Magnetic Resonance (MR) is more preferred than Computed Tomography (CT) due to the high resolution in MR images which help in better detection of neurological conditions. Graphical user interface (GUI) aided disease detection has become increasingly useful due to the increasing workload of doctors. In this proposed work, a novel two steps GUI technique for brain tumor segmentation as well as Brodmann area detec-tion of the segmented tumor is proposed. A data set of T2 weighted images of 15 patients is used for validating the proposed method. The patient data incor-porates variations in ethnicities, gender (male and female) and age (25-50), thus enhancing the authenticity of the proposed method. The tumors were segmented using Fuzzy C Means Clustering and Brodmann area detection was done using a known template, mapping each area to the segmented tumor image. The proposed method was found to be fairly accurate and robust in detecting tumor.