Search Results for author: Amin Banitalebi-Dehkordi

Found 23 papers, 9 papers with code

Beauty Beyond Words: Explainable Beauty Product Recommendations Using Ingredient-Based Product Attributes

no code implementations20 Sep 2024 Siliang Liu, Rahul Suresh, Amin Banitalebi-Dehkordi

Finally, we showcase how ingredient-based attribute extraction contributes to enhancing the explainability of beauty recommendations.

Attribute Attribute Extraction

Automated Material Properties Extraction For Enhanced Beauty Product Discovery and Makeup Virtual Try-on

no code implementations1 Dec 2023 Fatemeh Taheri Dezaki, Himanshu Arora, Rahul Suresh, Amin Banitalebi-Dehkordi

An intelligent approach for product discovery is required to enhance the makeup shopping experience to make it more convenient and satisfying.

Virtual Try-on

ArchBERT: Bi-Modal Understanding of Neural Architectures and Natural Languages

no code implementations26 Oct 2023 Mohammad Akbari, Saeed Ranjbar Alvar, Behnam Kamranian, Amin Banitalebi-Dehkordi, Yong Zhang

Despite the success of these multi-modal language models with different modalities, there is no existing solution for neural network architectures and natural languages.

AutoML Question Answering

Improving the Accuracy of Beauty Product Recommendations by Assessing Face Illumination Quality

no code implementations7 Sep 2023 Parnian Afshar, Jenny Yeon, Andriy Levitskyy, Rahul Suresh, Amin Banitalebi-Dehkordi

To make accurate recommendations, it is crucial to infer both the product attributes and the product specific facial features such as skin conditions or tone.

Product Recommendation

NL4Opt Competition: Formulating Optimization Problems Based on Their Natural Language Descriptions

1 code implementation14 Mar 2023 Rindranirina Ramamonjison, Timothy T. Yu, Raymond Li, Haley Li, Giuseppe Carenini, Bissan Ghaddar, Shiqi He, Mahdi Mostajabdaveh, Amin Banitalebi-Dehkordi, Zirui Zhou, Yong Zhang

The Natural Language for Optimization (NL4Opt) Competition was created to investigate methods of extracting the meaning and formulation of an optimization problem based on its text description.

Language Modelling Large Language Model

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

no code implementations15 Aug 2022 Morgan Heisler, Amin Banitalebi-Dehkordi, Yong Zhang

Our method of semantically meaningful image augmentation for object detection via language grounding, SemAug, starts by calculating semantically appropriate new objects that can be placed into relevant locations in the image (the what and where problems).

Diversity Image Augmentation +3

Deep Reinforcement Learning for Exact Combinatorial Optimization: Learning to Branch

no code implementations14 Jun 2022 Tianyu Zhang, Amin Banitalebi-Dehkordi, Yong Zhang

We propose a new approach for solving the data labeling and inference latency issues in combinatorial optimization based on the use of the reinforcement learning (RL) paradigm.

BIG-bench Machine Learning Combinatorial Optimization +5

AuxMix: Semi-Supervised Learning with Unconstrained Unlabeled Data

no code implementations14 Jun 2022 Amin Banitalebi-Dehkordi, Pratik Gujjar, Yong Zhang

Critically, most recent work assume that such unlabeled data is drawn from the same distribution as the labeled data.

4k Self-Supervised Learning

Extending Momentum Contrast with Cross Similarity Consistency Regularization

no code implementations7 Jun 2022 Mehdi Seyfi, Amin Banitalebi-Dehkordi, Yong Zhang

Contrastive self-supervised representation learning methods maximize the similarity between the positive pairs, and at the same time tend to minimize the similarity between the negative pairs.

Representation Learning Self-Supervised Learning

Spatial Cross-Attention Improves Self-Supervised Visual Representation Learning

no code implementations7 Jun 2022 Mehdi Seyfi, Amin Banitalebi-Dehkordi, Yong Zhang

Unsupervised representation learning methods like SwAV are proved to be effective in learning visual semantics of a target dataset.

object-detection Object Detection +1

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

no code implementations29 Mar 2022 Xubo Lyu, Amin Banitalebi-Dehkordi, Mo Chen, Yong Zhang

In complex problems with large state and action spaces, it is advantageous to extend MAPG methods to use higher-level actions, also known as options, to improve the policy search efficiency.

Hierarchical Reinforcement Learning Multi-agent Reinforcement Learning +3

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

no code implementations ACL 2022 Mohammad Akbari, Amin Banitalebi-Dehkordi, Yong Zhang

As such, it can be applied to black-box pre-trained models without a need for architectural manipulations, reassembling of modules, or re-training.

Decision Making Model Compression

ML4CO: Is GCNN All You Need? Graph Convolutional Neural Networks Produce Strong Baselines For Combinatorial Optimization Problems, If Tuned and Trained Properly, on Appropriate Data

no code implementations22 Dec 2021 Amin Banitalebi-Dehkordi, Yong Zhang

The 2021 NeurIPS Machine Learning for Combinatorial Optimization (ML4CO) competition was designed with the goal of improving state-of-the-art combinatorial optimization solvers by replacing key heuristic components with machine learning models.

BIG-bench Machine Learning Combinatorial Optimization

Model Composition: Can Multiple Neural Networks Be Combined into a Single Network Using Only Unlabeled Data?

1 code implementation20 Oct 2021 Amin Banitalebi-Dehkordi, Xinyu Kang, Yong Zhang

As an attempt to mitigate this dilemma, this paper investigates the idea of combining multiple trained neural networks using unlabeled data.

Diversity object-detection +1

Repaint: Improving the Generalization of Down-Stream Visual Tasks by Generating Multiple Instances of Training Examples

1 code implementation20 Oct 2021 Amin Banitalebi-Dehkordi, Yong Zhang

Through an extensive set of experiments, we demonstrate the usefulness of the repainted examples in training, for the tasks of image classification (ImageNet) and object detection (COCO), over several state-of-the-art network architectures at different capacities, and across different data availability regimes.

Colorization Image Classification +2

EBJR: Energy-Based Joint Reasoning for Adaptive Inference

1 code implementation20 Oct 2021 Mohammad Akbari, Amin Banitalebi-Dehkordi, Yong Zhang

To this end, we propose an Energy-Based Joint Reasoning (EBJR) framework that adaptively distributes the samples between shallow and deep models to achieve an accuracy close to the deep model, but latency close to the shallow one.

Auto-Split: A General Framework of Collaborative Edge-Cloud AI

1 code implementation30 Aug 2021 Amin Banitalebi-Dehkordi, Naveen Vedula, Jian Pei, Fei Xia, Lanjun Wang, Yong Zhang

At the same time, large amounts of input data are collected at the edge of cloud.

Revisiting Knowledge Distillation for Object Detection

no code implementations22 May 2021 Amin Banitalebi-Dehkordi

Extensive experiments demonstrate improvements over existing object detection distillation algorithms.

Domain Adaptation Knowledge Distillation +3

A Learning-Based Visual Saliency Fusion Model for High Dynamic Range Video (LBVS-HDR)

1 code implementation13 Mar 2018 Amin Banitalebi-Dehkordi, Yuanyuan Dong, Mahsa T. Pourazad, Panos Nasiopoulos

To this end we propose a learning-based visual saliency fusion method for HDR content (LVBS-HDR) to combine various visual saliency features.

Saliency Prediction

A Learning-Based Visual Saliency Prediction Model for Stereoscopic 3D Video (LBVS-3D)

1 code implementation13 Mar 2018 Amin Banitalebi-Dehkordi, Mahsa T. Pourazad, Panos Nasiopoulos

Our model starts with a rough segmentation and quantifies several intuitive observations such as the effects of visual discomfort level, depth abruptness, motion acceleration, elements of surprise, size and compactness of the salient regions, and emphasizing only a few salient objects in a scene.

Saliency Prediction Video Saliency Prediction

Cannot find the paper you are looking for? You can Submit a new open access paper.