← Search

Amin Banitalebi-dehkordi

6 accepted papers

2024

Skin Tone Disentanglement in 2D Makeup Transfer With Graph Neural Networks

ICASSP 2024accepted

Makeup transfer involves transferring makeup from a reference image to a target image while maintaining the target’s identity. Existing methods, which use Generative Adversarial Networks, often transfer not just makeup but also the reference image’s skin tone. This limits their use to similar skin t…

Cited by 0SourceScholar
2023

Asynchronous, Option-Based Multi-Agent Policy Gradient: A Conditional Reasoning Approach

IROS 2023poster

Cooperative multi-agent problems often require coordination between agents, which can be achieved through a centralized policy that considers the global state. Multi-agent policy gradient (MAPG) methods are commonly used to learn such policies, but they are often limited to problems with low-level a…

Cited by 3SourceScholar
2022

Augmenting Operations Research with Auto-Formulation of Optimization Models From Problem Descriptions

EMNLP 2022industry

We describe an augmented intelligence system for simplifying and enhancing the modeling experience for operations research. Using this system, the user receives a suggested formulation of an optimization problem based on its description. To facilitate this process, we build an intuitive user interfa…

2022

E-LANG: Energy-Based Joint Inferencing of Super and Swift Language Models

ACL 2022long

Building huge and highly capable language models has been a trend in the past years. Despite their great performance, they incur high computational cost. A common solution is to apply model compression or choose light-weight architectures, which often need a separate fixed-size model for each desira…

Cited by 11SourcePDFScholar
2022

SemAug: Semantically Meaningful Image Augmentations for Object Detection through Language Grounding

ECCV 2022poster

"Data augmentation is an essential technique in improving the generalization of deep neural networks. The majority of existing image-domain augmentations either rely on geometric and structural transformations, or apply different kinds of photometric distortions. In this paper, we propose an effecti…

Cited by 6SourcePDFScholar
2021

SimROD: A Simple Adaptation Method for Robust Object Detection

ICCV 2021poster

This paper presents a Simple and effective unsupervised adaptation method for Robust Object Detection (SimROD). To overcome the challenging issues of domain shift and pseudo-label noise, our method integrates a novel domain-centric data augmentation, a gradual self-labeling adaptation procedure, and…

Cited by 61PDFcodeScholar