16 papers
Toward Calibrated Mixture-of-Experts Under Distribution Shift
Gina Wong, Drew Prinster, Suchi Saria +2
Calibration aligns a model's predictive uncertainty with the frequencies of its empirical outcomes and is important for understanding and trusting reported probabilities. Recent wo…
AttriBE: Quantifying Attribute Expressivity in Body Embeddings for Recognition and Identification
Basudha Pal, Siyuan Huang, Anirudh Nanduri +2
Person re-identification (ReID) systems that match individuals across images or video frames are essential in many real-world applications. However, existing methods are often infl…
DiffInf: Influence-Guided Diffusion for Supervision Alignment in Facial Attribute Learning
Basudha Pal, Zhaoyang Wang, Rama Chellappa
Facial attribute classification relies on large-scale annotated datasets in which many traits, such as age and expression, are inherently ambiguous and continuous but are discretiz…
Polysemantic Dropout: Conformal OOD Detection for Specialized LLMs
Ayush Gupta, Ramneet Kaur, Anirban Roy +3
We propose a novel inference-time out-of-domain (OOD) detection algorithm for specialized large language models (LLMs). Despite achieving state-of-the-art performance on in-domain…
TOGA: Temporally Grounded Open-Ended Video QA with Weak Supervision
Ayush Gupta, Anirban Roy, Rama Chellappa +3
We address the problem of video question answering (video QA) with temporal grounding in a weakly supervised setup, without any temporal annotations. Given a video and a question,…
Cross-Spectral Body Recognition with Side Information Embedding: Benchmarks on LLCM and Analyzing Range-Induced Occlusions on IJB-MDF
Anirudh Nanduri, Siyuan Huang, Rama Chellappa
Vision Transformers (ViTs) have demonstrated impressive performance across a wide range of biometric tasks, including face and body recognition. In this work, we adapt a ViT model…
Medical World Model: Generative Simulation of Tumor Evolution for Treatment Planning
Yijun Yang, Zhao-Yang Wang, Qiuping Liu +8
Providing effective treatment and making informed clinical decisions are essential goals of modern medicine and clinical care. We are interested in simulating disease dynamics for…
Encoding of Demographic and Anatomical Information in Chest X-Ray-based Severe Left Ventricular Hypertrophy Classifiers
Basudha Pal, Rama Chellappa, Muhammad Umair
While echocardiography and MRI are clinical standards for evaluating cardiac structure, their use is limited by cost and accessibility.We introduce a direct classification framewor…
Multi-Domain Biometric Recognition using Body Embeddings
Anirudh Nanduri, Siyuan Huang, Rama Chellappa
Biometric recognition becomes increasingly challenging as we move away from the visible spectrum to infrared imagery, where domain discrepancies significantly impact identification…
A Quantitative Evaluation of the Expressivity of BMI, Pose and Gender in Body Embeddings for Recognition and Identification
Basudha Pal, Siyuan Huang, Rama Chellappa
Person Re-identification (ReID) systems that match individuals across images or video frames are essential in many real-world applications. However, existing methods are often infl…
MimicGait: A Model Agnostic approach for Occluded Gait Recognition using Correlational Knowledge Distillation
Ayush Gupta, Rama Chellappa
Gait recognition is an important biometric technique over large distances. State-of-the-art gait recognition systems perform very well in controlled environments at close range. Re…
PETALface: Parameter Efficient Transfer Learning for Low-resolution Face Recognition
Kartik Narayan, Nithin Gopalakrishnan Nair, Jennifer Xu +2
Pre-training on large-scale datasets and utilizing margin-based loss functions have been highly successful in training models for high-resolution face recognition. However, these m…
Template-based Multi-Domain Face Recognition
Anirudh Nanduri, Rama Chellappa
Despite the remarkable performance of deep neural networks for face detection and recognition tasks in the visible spectrum, their performance on more challenging non-visible domai…
Generating Potent Poisons and Backdoors from Scratch with Guided Diffusion
Hossein Souri, Arpit Bansal, Hamid Kazemi +7
Modern neural networks are often trained on massive datasets that are web scraped with minimal human inspection. As a result of this insecure curation pipeline, an adversary can po…
CLR-Face: Conditional Latent Refinement for Blind Face Restoration Using Score-Based Diffusion Models
Maitreya Suin, Rama Chellappa
Recent generative-prior-based methods have shown promising blind face restoration performance. They usually project the degraded images to the latent space and then decode high-qua…
You Can Run but not Hide: Improving Gait Recognition with Intrinsic Occlusion Type Awareness
Ayush Gupta, Rama Chellappa
While gait recognition has seen many advances in recent years, the occlusion problem has largely been ignored. This problem is especially important for gait recognition from uncont…