Search

The challenge of Out-Of-Distribution (OOD) robustness remains a critical hurdle towards deploying deep vision models. Vision-Language Models (VLMs) have recently achieved groundbreaking results. VLM-based open-vocabulary object detection extends the capabilities of traditional object detection frameworks, enabling the recognition and classification of objects beyond predefined categories. Investigating OOD robustness in recent open-vocabulary object detection is essential to increase the trustworthiness of these models. This study presents a comprehensive robustness evaluation of the zero-shot capabilities of three recent open-vocabulary (OV) foundation object detection models: OWL-ViT, YOLO World, and Grounding DINO. Experiments carried out on the robustness benchmarks COCO-O, COCO-DC, and COCO-C encompassing distribution shifts due to information loss, corruption, adversarial attacks, and geometrical deformation, highlighting the challenges of the model's robustness to foster the research for achieving robustness. Source code shall be made available to the research community on GitHub., Comment: 14 + 3 single column pages

Perspective distortion (PD) causes unprecedented changes in shape, size, orientation, angles, and other spatial relationships of visual concepts in images. Precisely estimating camera intrinsic and extrinsic parameters is a challenging task that prevents synthesizing perspective distortion. Non-availability of dedicated training data poses a critical barrier to developing robust computer vision methods. Additionally, distortion correction methods make other computer vision tasks a multi-step approach and lack performance. In this work, we propose mitigating perspective distortion (MPD) by employing a fine-grained parameter control on a specific family of M\"obius transform to model real-world distortion without estimating camera intrinsic and extrinsic parameters and without the need for actual distorted data. Also, we present a dedicated perspectively distorted benchmark dataset, ImageNet-PD, to benchmark the robustness of deep learning models against this new dataset. The proposed method outperforms existing benchmarks, ImageNet-E and ImageNet-X. Additionally, it significantly improves performance on ImageNet-PD while consistently performing on standard data distribution. Notably, our method shows improved performance on three PD-affected real-world applications crowd counting, fisheye image recognition, and person re-identification and one PD-affected challenging CV task: object detection. The source code, dataset, and models are available on the project webpage at https://prakashchhipa.github.io/projects/mpd., Comment: Accepted to European Conference on Computer Vision(ECCV2024). project page- https://prakashchhipa.github.io/projects/mpd

Medical question answer (QA) assistants respond to lay users' health-related queries by synthesizing information from multiple sources using natural language processing and related techniques. They can serve as vital tools to alleviate issues of misinformation, information overload, and complexity of medical language, thus addressing lay users' information needs while reducing the burden on healthcare professionals. QA systems, the engines of such assistants, have typically used either language models (LMs) or knowledge graphs (KG), though the approaches could be complementary. LM-based QA systems excel at understanding complex questions and providing well-formed answers, but are prone to factual mistakes. KG-based QA systems, which represent facts well, are mostly limited to answering short-answer questions with pre-created templates. While a few studies have jointly used LM and KG approaches for text-based QA, this was done to answer multiple-choice questions. Extant QA systems also have limitations in terms of automation and performance. We address these challenges by designing a novel, automated disease QA system which effectively utilizes both LM and KG techniques through a joint-reasoning approach to answer disease-related questions appropriate for lay users. Our evaluation of the system using a range of quality metrics demonstrates its efficacy over benchmark systems, including the popular ChatGPT., Comment: 36 pages, 6 figures, submitted to TMIS on 14 July 2023 (status: under review)

Fitting's Heyting-valued logic and Heyting-valued modal logic have already been studied from an algebraic viewpoint. In addition to algebraic axiomatizations with the completeness of Fitting's Heyting-valued logic and Heyting-valued modal logic, both topological and coalgebraic dualities have also been developed for algebras of Fitting's Heyting-valued modal logic. Bitopological methods have recently been employed to investigate duality for Fitting's Heyting-valued logic. However, the concepts of bitopology and biVietoris coalgebras are conspicuously absent from the development of dualities for Fitting's many-valued modal logic. With this study, we try to bridge that gap. We develop a bitopological duality for algebras of Fitting's Heyting-valued modal logic. We construct a bi-Vietoris functor on the category $PBS_{\mathcal{L}}$ of $\mathcal{L}$-valued ($\mathcal{L}$ is a Heyting algebra) pairwise Boolean spaces. Finally, we obtain a dual equivalence between categories of biVietoris coalgebras and algebras of Fitting's Heyting-valued modal logic. As a result, we conclude that Fitting's many-valued modal logic is sound and complete with respect to the coalgebras of a biVietoris functor. We discuss the application of this coalgebraic approach to bitopological duality.

Electrical current rectification is an interesting electronic feature, popularly known as a diode. Achieving a high rectification ratio in a molecular junction has been a long-standing goal in molecular electronics. The present work describes mimicking electrical current rectification with pi-stacked rhenium(I) compound sandwiched between two electrical contacts. Among the two mononuclear rhenium compounds studied here, [Re(CO)4(PPh3){(N)-saccharinate}] (1) and [Re(CO)3(phen){(N)-saccharinate}] (2), the latter show strong pi-pi interactions-induced high rectification ratio of ~ 4000 at 2.0 V at room temperature. Alternating current (AC)-based electrical measurements ensuring AC to DC electrical signal conversion at a frequency f of 1 KHz showing 2 can act as an excellent half-wave rectifier. Asymmetric charge injection barrier height at the electrode/Re(I) interfaces of the devices with a stacking configuration of p++-Si/Re compound31nm(2)/ITO originates the flow of electrical current unidirectionally. The charge transport mechanism governed by thermally activated hopping phenomena, and charge carrier propagation is explained through an energy profile considering the Fermi levels of two electrodes, and the energy of frontier molecular orbitals, HOMO, and LUMO, confirming rectification is of a molecular origin. The present work paves the way to combine different organometallic compounds as circuit elements in nanoelectronic devices to achieve numerous exciting electronic features., Comment: 16 pages, 5 figures

This article contributes to the new summation of Sz\'asz operators with the help of Appell polynomials of class $A^{2}$. We verified Bohman-Korovkin's theorem and prove the convergence results like Lipschitz-type space, Voronvaskaja-type asymptotic formula, and modulus of continuity using the given operators. Furthermore, we have shown the weighted modulus of continuity and the derivative of bounded variation.

Self-supervised learning in computer vision aims to leverage the inherent structure and relationships within data to learn meaningful representations without explicit human annotation, enabling a holistic understanding of visual scenes. Robustness in vision machine learning ensures reliable and consistent performance, enhancing generalization, adaptability, and resistance to noise, variations, and adversarial attacks. Self-supervised paradigms, namely contrastive learning, knowledge distillation, mutual information maximization, and clustering, have been considered to have shown advances in invariant learning representations. This work investigates the robustness of learned representations of self-supervised learning approaches focusing on distribution shifts and image corruptions in computer vision. Detailed experiments have been conducted to study the robustness of self-supervised learning methods on distribution shifts and image corruptions. The empirical analysis demonstrates a clear relationship between the performance of learned representations within self-supervised paradigms and the severity of distribution shifts and corruptions. Notably, higher levels of shifts and corruptions are found to significantly diminish the robustness of the learned representations. These findings highlight the critical impact of distribution shifts and image corruptions on the performance and resilience of self-supervised learning methods, emphasizing the need for effective strategies to mitigate their adverse effects. The study strongly advocates for future research in the field of self-supervised representation learning to prioritize the key aspects of safety and robustness in order to ensure practical applicability. The source code and results are available on GitHub., Comment: Accepted at 2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW). Corresponding author - prakash.chandra.chhipa@ltu.se

Bio-spinterfaces present numerous opportunities to study spintronics across the biomolecules attached to (ferro)magnetic electrodes. While it offers various exciting phenomena to investigate, it's simultaneously challenging to make stable bio-spinterfaces, as biomolecules are sensitive to many factors that it encounters during thin-film growth to device fabrication. The chirality-induced spin-selectivity (CISS) effect is an exciting discovery demonstrating an understanding that a specific electron's spin (either UP or DOWN) passes through a chiral molecule. The present work utilizes Ustilago maydis Rvb2 protein, an ATP-dependent DNA helicase (also known as Reptin) for the fabrication of bio-spintronic devices to investigate spin-selective electron transport through protein. Ferromagnetic materials are well-known for showing spin-polarization, which many chiral and biomolecules can mimic. We report spin-selective electron transmission through Rvb2 that exhibits 30% spin polarization at a low bias (+ 0.5 V) in a device configuration, Ni/Rvb2 protein/ITO measured under two different magnetic configurations. Our findings demonstrate that biomolecules can be put in circuit components without any expensive vacuum deposition for the top contact. Thus, it holds a remarkable potential to advance spin-selective electron transport in other biomolecules such as proteins, and peptides for biomedical applications., Comment: 14 pages, 5 figures

This work presents a novel label-efficient selfsupervised representation learning-based approach for classifying diabetic retinopathy (DR) images in cross-domain settings. Most of the existing DR image classification methods are based on supervised learning which requires a lot of time-consuming and expensive medical domain experts-annotated data for training. The proposed approach uses the prior learning from the source DR image dataset to classify images drawn from the target datasets. The image representations learned from the unlabeled source domain dataset through contrastive learning are used to classify DR images from the target domain dataset. Moreover, the proposed approach requires a few labeled images to perform successfully on DR image classification tasks in cross-domain settings. The proposed work experiments with four publicly available datasets: EyePACS, APTOS 2019, MESSIDOR-I, and Fundus Images for self-supervised representation learning-based DR image classification in cross-domain settings. The proposed method achieves state-of-the-art results on binary and multiclassification of DR images, even in cross-domain settings. The proposed method outperforms the existing DR image binary and multi-class classification methods proposed in the literature. The proposed method is also validated qualitatively using class activation maps, revealing that the method can learn explainable image representations. The source code and trained models are published on GitHub., Comment: Accepted to International Joint Conference on Neural Networks (IJCNN) 2023

This work presents a novel domain adaption paradigm for studying contrastive self-supervised representation learning and knowledge transfer using remote sensing satellite data. Major state-of-the-art remote sensing visual domain efforts primarily focus on fully supervised learning approaches that rely entirely on human annotations. On the other hand, human annotations in remote sensing satellite imagery are always subject to limited quantity due to high costs and domain expertise, making transfer learning a viable alternative. The proposed approach investigates the knowledge transfer of selfsupervised representations across the distinct source and target data distributions in depth in the remote sensing data domain. In this arrangement, self-supervised contrastive learning-based pretraining is performed on the source dataset, and downstream tasks are performed on the target datasets in a round-robin fashion. Experiments are conducted on three publicly available datasets, UC Merced Landuse (UCMD), SIRI-WHU, and MLRSNet, for different downstream classification tasks versus label efficiency. In self-supervised knowledge transfer, the proposed approach achieves state-of-the-art performance with label efficiency labels and outperforms a fully supervised setting. A more in-depth qualitative examination reveals consistent evidence for explainable representation learning. The source code and trained models are published on GitHub., Comment: Accepted in International Joint Conference on Neural Networks (IJCNN) 2023. First three authors shares equal contribution!