6 papers
Retrieval-Guided Generation for Safer Histopathology Image Captioning
Md. Enamul Hoq, Wataru Uegami, Saghir Alfasly +6
Generative vision-language models can produce fluent medical image captions but remain prone to hallucination, over-specific diagnostic claims, and factual inconsistency-serious is…
GIF: Generative Inspiration for Face Recognition at Scale
Saeed Ebrahimi, Sahar Rahimi, Ali Dabouei +3
Aiming to reduce the computational cost of Softmax in massive label space of Face Recognition (FR) benchmarks, recent studies estimate the output using a subset of identities. Alth…
Decomposed Distribution Matching in Dataset Condensation
Sahar Rahimi Malakshan, Mohammad Saeed Ebrahimi Saadabadi, Ali Dabouei +1
Dataset Condensation (DC) aims to reduce deep neural networks training efforts by synthesizing a small dataset such that it will be as effective as the original large dataset. Conv…
Boosting Unconstrained Face Recognition with Targeted Style Adversary
Mohammad Saeed Ebrahimi Saadabadi, Sahar Rahimi Malakshan, Seyed Rasoul Hosseini +1
While deep face recognition models have demonstrated remarkable performance, they often struggle on the inputs from domains beyond their training data. Recent attempts aim to expan…
ARoFace: Alignment Robustness to Improve Low-Quality Face Recognition
Mohammad Saeed Ebrahimi Saadabadi, Sahar Rahimi Malakshan, Ali Dabouei +1
Aiming to enhance Face Recognition (FR) on Low-Quality (LQ) inputs, recent studies suggest incorporating synthetic LQ samples into training. Although promising, the quality factors…
Hyperspherical Classification with Dynamic Label-to-Prototype Assignment
Mohammad Saeed Ebrahimi Saadabadi, Ali Dabouei, Sahar Rahimi Malakshan +1
Aiming to enhance the utilization of metric space by the parametric softmax classifier, recent studies suggest replacing it with a non-parametric alternative. Although a non-parame…