Search Results for author:
Found 66 papers, 17 papers with code
GenMix: Effective Data Augmentation with Generative Diffusion Model Image Editing
Data augmentation is widely used to enhance generalization in visual classification tasks.
Safety Without Semantic Disruptions: Editing-free Safe Image Generation via Context-preserving Dual Latent Reconstruction
We identify trade-offs between safety and censorship, which presents a necessary perspective in the development of ethical AI models.
GLMHA A Guided Low-rank Multi-Head Self-Attention for Efficient Image Restoration and Spectral Reconstruction
Unique to the proposed GLMHA is its ability to provide computational gain for both short and long input sequences.
Regulating Model Reliance on Non-Robust Features by Smoothing Input Marginal Density
Trustworthy machine learning necessitates meticulous regulation of model reliance on non-robust features.
Suitability of KANs for Computer Vision: A preliminary investigation
Kolmogorov-Arnold Networks (KANs) introduce a paradigm of neural modeling that implements learnable functions on the edges of the networks, diverging from the traditional node-centric activations in neural networks.
From CNNs to Transformers in Multimodal Human Action Recognition: A Survey
We analyze the classic and emerging techniques in this regard, while also highlighting the popular trends in the adaption of CNN and Transformer building blocks for the overall problem.
Backdoor-based Explainable AI Benchmark for High Fidelity Evaluation of Attribution Methods
This setup is ultimately employed for a comprehensive comparison of existing methods using our BackX benchmark.
Manipulating and Mitigating Generative Model Biases without Retraining
As a by-product, this control serves as a form of precise prompt engineering to generate images which are generally implausible using regular text prompts.
ASCNet: Asymmetric Sampling Correction Network for Infrared Image Destriping
In a real-world infrared imaging system, effectively learning a consistent stripe noise removal model is essential.
SCTransNet: Spatial-channel Cross Transformer Network for Infrared Small Target Detection
In the proposed SCTBs, the outputs of all encoders are interacted with cross transformer to generate mixed features, which are redistributed to all decoders to effectively reinforce semantic differences between the target and clutter at full scales.
M3BUNet: Mobile Mean Max UNet for Pancreas Segmentation on CT-Scans
Segmenting organs in CT scan images is a necessary process for multiple downstream medical image analysis tasks.
Quantifying Bias in Text-to-Image Generative Models
Bias in text-to-image (T2I) models can propagate unfair social representations and may be used to aggressively market ideas or push controversial agendas.
On quantifying and improving realism of images generated with diffusion
Recent advances in diffusion models have led to a quantum leap in the quality of generative visual content.
Text-image guided Diffusion Model for generating Deepfake celebrity interactions
To curb their exploitation for Deepfakes, it is imperative to first explore the extent to which diffusion models can be used to generate realistic content that is controllable with convenient prompts.
PRAT: PRofiling Adversarial aTtacks
Inspired by this, we introduce a novel problem of PRofiling Adversarial aTtacks (PRAT).
MAiVAR-T: Multimodal Audio-image and Video Action Recognizer using Transformers
This model employs an intuitive approach for the combination of audio-image and video modalities, with a primary aim to escalate the effectiveness of multimodal human action recognition (MHAR).
BAGM: A Backdoor Attack for Manipulating Text-to-Image Generative Models
Based on the penetration level, BAGM takes the form of a suite of attacks that are referred to as surface, shallow and deep attacks in this article.
A Comprehensive Overview of Large Language Models
Large Language Models (LLMs) have recently demonstrated remarkable capabilities in natural language processing tasks and beyond.
UnLoc: A Universal Localization Method for Autonomous Vehicles using LiDAR, Radar and/or Camera Input
The results ascertain the efficacy of our technique.
Towards credible visual model interpretation with path attribution
We also devise a scheme to preclude the conditions in which visual model interpretation can invalidate the axiomatic properties of path attribution.
Rethinking interpretation: Input-agnostic saliency mapping of deep visual classifiers
Addressing the gap, we introduce a new perspective of input-agnostic saliency mapping that computationally estimates the high-level features attributed by the model to its outputs.
A Survey of Explainable AI in Deep Visual Modeling: Methods and Metrics
Deep visual models have widespread applications in high-stake domains.
Pre-text Representation Transfer for Deep Learning with Limited Imbalanced Data : Application to CT-based COVID-19 Detection
We fuse the output of this layer with the predictions of a model induced with the traditional transfer learning performed over our pre-text transferred model.
Slice Transformer and Self-supervised Learning for 6DoF Localization in 3D Point Cloud Maps
We present a self-supervised learning method that employs Transformers for the first time for the task of outdoor localization using LiDAR data.
AShapeFormer: Semantics-Guided Object-Level Active Shape Encoding for 3D Object Detection via Transformers
In this work, we propose AShapeFormer, a semantics-guided object-level shape encoding module for 3D object detection.
Query Efficient Cross-Dataset Transferable Black-Box Attack on Action Recognition
By using a nearly disjoint dataset to train the substitute model, our method removes the requirement that the substitute model be trained using the same dataset as the target model, and leverages queries to the target model to retain the fooling rate benefits provided by query-based methods.
Simultaneous Multiple Object Detection and Pose Estimation using 3D Model Infusion with Monocular Vision
Using the labeling method, we provide the KITTI-6DoF dataset with $\sim7. 5$K annotated frames.
Efficient Diffusion Models for Vision: A Survey
In this review, we present the most recent advances in diffusion models for vision, specifically focusing on the important design aspects that affect the computational efficiency of DMs.
Vision Transformers for Action Recognition: A Survey
Finally, it provides a discussion on the challenges, outlook, and future avenues for this research direction.
MAiVAR: Multimodal Audio-Image and Video Action Recognizer
Currently, action recognition is predominately performed on video data as processed by CNNs.
Contrastive Self-Supervised Learning Leads to Higher Adversarial Susceptibility
We establish that this is a result of the presence of false negative pairs in the training process, which increases model sensitivity to input perturbations.
Deformation and Correspondence Aware Unsupervised Synthetic-to-Real Scene Flow Estimation for Point Clouds
With that, we develop a large-scale synthetic scene flow dataset GTA-SF.
A Survey of Neural Trojan Attacks and Defenses in Deep Learning
It provides a comprehensible gateway to the broader community to understand the recent developments in Neural Trojans.
Mesh Convolution with Continuous Filters for 3D Surface Parsing
In this paper, we propose a series of modular operations for effective geometric feature learning from 3D triangle meshes.
Resetting the baseline: CT-based COVID-19 diagnosis with Deep Transfer Learning is not as accurate as widely thought
We hope that our reproducible investigation will help in curbing hype-driven claims for the critical problem of COVID-19 diagnosis, and pave the way for a more transparent performance evaluation of techniques for CT-based COVID-19 detection.
Advances in adversarial attacks and defenses in computer vision: A survey
In [2], we reviewed the contributions made by the computer vision community in adversarial attacks on deep learning (and their defenses) until the advent of year 2018.
Controlled Caption Generation for Images Through Adversarial Attacks
In contrast, we propose a GAN-based algorithm for crafting adversarial examples for neural image captioning that mimics the internal representation of the CNN such that the resulting deep features of the input image enable a controlled incorrect caption generation through the recurrent network.
Attack to Fool and Explain Deep Networks
Exploring this phenomenon further, we alter the `adversarial' objective of our attack to use it as a tool to `explain' deep visual representation.
CAMERAS: Enhanced Resolution And Sanity preserving Class Activation Mapping for image saliency
Backpropagation image saliency aims at explaining model predictions by estimating model-centric importance of individual pixels in the input.
Picasso: A CUDA-based Library for Deep Learning over 3D Meshes
We present Picasso, a CUDA-based library comprising novel modules for deep learning over complex real-world 3D meshes.
Boosting Deep Transfer Learning for COVID-19 Classification
COVID-19 classification using chest Computed Tomography (CT) has been found pragmatically useful by several studies.
Simultaneous Detection and Tracking with Motion Modelling for Multiple Object Tracking
Deep learning-based Multiple Object Tracking (MOT) currently relies on off-the-shelf detectors for tracking-by-detection. This results in deep models that are detector biased and evaluations that are detector influenced.
Orthogonal Deep Models As Defense Against Black-Box Attacks
On the other, deep learning has also been found vulnerable to adversarial attacks, which calls for new techniques to defend deep models against these attacks.
Adversarial Perturbations Prevail in the Y-Channel of the YCbCr Color Space
Our results show that our approach achieves the best balance between defence against adversarial attacks such as FGSM, PGD and DDN and maintaining the original accuracies of VGG-16, ResNet50 and DenseNet121 on clean images.
Empirical Autopsy of Deep Video Captioning Frameworks
We perform extensive experiments by varying the constituent components of the video captioning framework, and quantify the performance gains that are possible by mere component selection.
Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds
We propose a spherical kernel for efficient graph convolution of 3D point clouds.
Ranked #5 on
3D Object Classification
on ModelNet40
Adversarial Attack on Skeleton-based Human Action Recognition
We also explore the possibility of semantically imperceptible localized attacks with CIASA, and succeed in fooling the state-of-the-art skeleton action recognition models with high confidence.
Temporally Coherent Full 3D Mesh Human Pose Recovery from Monocular Video
A major challenge in this regard is the lack of appropriately annotated video data for learning the desired deep models.
Label Universal Targeted Attack
We introduce Label Universal Targeted Attack (LUTA) that makes a deep model predict a label of attacker's choice for `any' sample of a given source class with high probability.
Octree guided CNN with Spherical Kernels for 3D Point Clouds
We propose an octree guided neural network architecture and spherical convolutional kernel for machine learning from arbitrary 3D point clouds.
Ranked #11 on
3D Part Segmentation
on ShapeNet-Part
Spatio-Temporal Dynamics and Semantic Attribute Enriched Visual Encoding for Video Captioning
The final representation is projected to a compact space and fed to a language model.
Going Deep in Medical Image Analysis: Concepts, Methods, Challenges and Future Directions
Unique to this study is the Computer Vision/Machine Learning perspective taken on the advances of Deep Learning in Medical Imaging.
Deep Affinity Network for Multiple Object Tracking
In this paper, we harness the power of deep learning for data association in tracking by jointly modelling object appearances and their affinities between different frames in an end-to-end fashion.
Spherical Convolutional Neural Network for 3D Point Clouds
We propose a neural network for 3D point cloud processing that exploits `spherical' convolution kernels and octree partitioning of space.
Benchmark data and method for real-time people counting in cluttered scenes using depth sensors
A thorough evaluation on PCDS demonstrates that our technique is able to count people in cluttered scenes with high accuracy at 45 fps on a 1. 7 GHz processor, and hence it can be deployed for effective real-time people counting for intelligent transportation systems.
Hyperspectral recovery from RGB images using Gaussian Processes
We propose to recover spectral details from RGB images of known spectral quantization by modeling natural spectra under Gaussian Processes and combining them with the RGB images.
Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey
This article presents the first comprehensive survey on adversarial attacks on deep learning in Computer Vision.
Defense against Universal Adversarial Perturbations
A rigorous evaluation shows that our framework can defend the network classifiers against unseen adversarial perturbations in the real-world scenarios with up to 97. 5% success rate.
Skepxels: Spatio-temporal Image Representation of Human Skeleton Joints for Action Recognition
The proposed action recognition exploits the representation in a hierarchical manner by first capturing the micro-temporal relations between the skeleton joints with the Skepxels and then exploiting their macro-temporal relations by computing the Fourier Temporal Pyramids over the CNN features of the skeletal images.
Viewpoint Invariant Action Recognition using RGB-D Videos
The proposed technique capitalizes on the spatio-temporal information available in the two data streams to the extract action features that are largely insensitive to the viewpoint variations.
Learning Human Pose Models from Synthesized Data for Robust RGB-D Action Recognition
We propose Human Pose Models that represent RGB and depth images of human poses independent of clothing textures, backgrounds, lighting conditions, body shapes and camera viewpoints.
Ranked #100 on
Skeleton Based Action Recognition
on NTU RGB+D
Joint Discriminative Bayesian Dictionary and Classifier Learning
To further encourage discrimination in the dictionary, our model uses separate (sets of) Bernoulli distributions to represent data from different classes.
Sparseness helps: Sparsity Augmented Collaborative Representation for Classification
Many classification approaches first represent a test sample using the training samples of all the classes.
Bayesian Sparse Representation for Hyperspectral Image Super Resolution
We propose a hyperspectral image super resolution approach that fuses a high resolution image with the low resolution hyperspectral image using non-parametric Bayesian sparse representation.
Discriminative Bayesian Dictionary Learning for Classification
We propose a Bayesian approach to learn discriminative dictionaries for sparse representation of data.
