37 citations · 54 across the 21 of their papers we have counts for
23 papers
Uncertainty Quantification for Computer-Use Agents: A Benchmark across Vision-Language Models and GUI Grounding Datasets
Divake Kumar, Sina Tayebati, Devashri Naik +5
Computer-use agents turn vision-language model (VLM) predictions into executable GUI clicks, so reliable uncertainty estimates are essential for rejection, calibration, miss-severi…
TRIAGE: Type-Routed Interventions via Aleatoric-Epistemic Gated Estimation in Robotic Manipulation and Adaptive Perception -- Don't Treat All Uncertainty the Same
Divake Kumar, Sina Tayebati, Devashri Naik +4
Most uncertainty-aware robotic systems collapse prediction uncertainty into a single scalar score and use it to trigger uniform corrective responses. This aggregation obscures whet…
Parts-Mamba: Augmenting Joint Context with Part-Level Scanning for Occluded Human Skeleton
Tianyi Shen, Huijuan Xu, Nilesh Ahuja +3
Skeleton action recognition involves recognizing human action from human skeletons. The use of graph convolutional networks (GCNs) has driven major advances in this recognition tas…
Calibrated Decomposition of Aleatoric and Epistemic Uncertainty in Deep Features for Inference-Time Adaptation
Divake Kumar, Patrick Poggi, Sina Tayebati +3
Most estimators collapse all uncertainty modes into a single confidence score, preventing reliable reasoning about when to allocate more compute or adjust inference. We introduce U…
MoRA: Missing Modality Low-Rank Adaptation for Visual Recognition
Shu Zhao, Nilesh Ahuja, Tan Yu +2
Pre-trained vision language models have shown remarkable performance on visual recognition tasks, but they typically assume the availability of complete multimodal inputs during bo…
Windsock is Dancing: Adaptive Multimodal Retrieval-Augmented Generation
Shu Zhao, Tianyi Shen, Nilesh Ahuja +2
Multimodal Retrieval-Augmented Generation (MRAG) has emerged as a promising method to generate factual and up-to-date responses of Multimodal Large Language Models (MLLMs) by incor…
TS-OOD: Evaluating Time-Series Out-of-Distribution Detection and Prospective Directions for Progress
Onat Gungor, Amanda Sofie Rios, Nilesh Ahuja +1
Detecting out-of-distribution (OOD) data is a fundamental challenge in the deployment of machine learning models. From a security standpoint, this is particularly important because…
Uncertainty Quantification in Continual Open-World Learning
Amanda S. Rios, Ibrahima J. Ndiour, Parual Datta +3
AI deployed in the real-world should be capable of autonomously adapting to novelties encountered after deployment. Yet, in the field of continual learning, the reliance on novelty…
CONCLAD: COntinuous Novel CLAss Detector
Amanda Rios, Ibrahima Ndiour, Parual Datta +2
In the field of continual learning, relying on so-called oracles for novelty detection is commonplace albeit unrealistic. This paper introduces CONCLAD ("COntinuous Novel CLAss Det…
CUAL: Continual Uncertainty-aware Active Learner
Amanda Rios, Ibrahima Ndiour, Parual Datta +3
AI deployed in many real-world use cases should be capable of adapting to novelties encountered after deployment. Here, we consider a challenging, under-explored and realistic cont…
Rate-Distortion Theory in Coding for Machines and its Application
Alon Harell, Yalda Foroutan, Nilesh Ahuja +6
Recent years have seen a tremendous growth in both the capability and popularity of automatic machine analysis of images and video. As a result, a growing need for efficient compre…
FRE: A Fast Method For Anomaly Detection And Segmentation
Ibrahima Ndiour, Nilesh Ahuja, Utku Genc +1
This paper presents a fast and principled approach for solving the visual anomaly detection and segmentation problem. In this setup, we have access to only anomaly-free training da…
A Low-Complexity Approach to Rate-Distortion Optimized Variable Bit-Rate Compression for Split DNN Computing
Parual Datta, Nilesh Ahuja, V. Srinivasa Somayazulu +1
Split computing has emerged as a recent paradigm for implementation of DNN-based AI workloads, wherein a DNN model is split into two parts, one of which is executed on a mobile/cli…
Subspace Modeling for Fast Out-Of-Distribution and Anomaly Detection
Ibrahima J. Ndiour, Nilesh A. Ahuja, Omesh Tickoo
This paper presents a fast, principled approach for detecting anomalous and out-of-distribution (OOD) samples in deep neural networks (DNN). We propose the application of linear st…
Anomalib: A Deep Learning Library for Anomaly Detection
Samet Akcay, Dick Ameln, Ashwin Vaidya +3
This paper introduces anomalib, a novel library for unsupervised anomaly detection and localization. With reproducibility and modularity in mind, this open-source library provides…
Mitigating Sampling Bias and Improving Robustness in Active Learning
Ranganath Krishnan, Alok Sinha, Nilesh Ahuja +3
This paper presents simple and efficient methods to mitigate sampling bias in active learning while achieving state-of-the-art accuracy and model robustness. We introduce supervise…
Robust Contrastive Active Learning with Feature-guided Query Strategies
Ranganath Krishnan, Nilesh Ahuja, Alok Sinha +3
We introduce supervised contrastive active learning (SCAL) and propose efficient query strategies in active learning based on the feature similarity (featuresim) and principal comp…
Energy-Based Anomaly Detection and Localization
Ergin Utku Genc, Nilesh Ahuja, Ibrahima J Ndiour +1
This brief sketches initial progress towards a unified energy-based solution for the semi-supervised visual anomaly detection and localization problem. In this setup, we have acces…
Out-Of-Distribution Detection With Subspace Techniques And Probabilistic Modeling Of Features
Ibrahima Ndiour, Nilesh Ahuja, Omesh Tickoo
This paper presents a principled approach for detecting out-of-distribution (OOD) samples in deep neural networks (DNN). Modeling probability distributions on deep features has rec…
Deep Probabilistic Models to Detect Data Poisoning Attacks
Mahesh Subedar, Nilesh Ahuja, Ranganath Krishnan +2
Data poisoning attacks compromise the integrity of machine-learning models by introducing malicious training samples to influence the results during test time. In this work, we inv…
Tree pyramidal adaptive importance sampling
Javier Felip, Nilesh Ahuja, Omesh Tickoo
This paper introduces Tree-Pyramidal Adaptive Importance Sampling (TP-AIS), a novel iterated sampling method that outperforms state-of-the-art approaches like deterministic mixture…
Probabilistic Modeling of Deep Features for Out-of-Distribution and Adversarial Detection
Nilesh A. Ahuja, Ibrahima Ndiour, Trushant Kalyanpur +1
We present a principled approach for detecting out-of-distribution (OOD) and adversarial samples in deep neural networks. Our approach consists in modeling the outputs of the vario…
Real-time Approximate Bayesian Computation for Scene Understanding
Javier Felip, Nilesh Ahuja, David Gómez-Gutiérrez +2
Consider scene understanding problems such as predicting where a person is probably reaching, or inferring the pose of 3D objects from depth images, or inferring the probable stree…