17 citations · 60 across the 34 of their papers we have counts for
37 papers
Exact Combinatorial Optimization with Temporo-Attentional Graph Neural Networks
Mehdi Seyfi, Amin Banitalebi-Dehkordi, Zirui Zhou +1
Combinatorial optimization finds an optimal solution within a discrete set of variables and constraints. The field has seen tremendous progress both in research and industry. With…
ArchBERT: Bi-Modal Understanding of Neural Architectures and Natural Languages
Mohammad Akbari, Saeed Ranjbar Alvar, Behnam Kamranian +2
Building multi-modal language models has been a trend in the recent years, where additional modalities such as image, video, speech, etc. are jointly learned along with natural lan…
NL4Opt Competition: Formulating Optimization Problems Based on Their Natural Language Descriptions
Rindranirina Ramamonjison, Timothy T. Yu, Raymond Li +8
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…
Augmenting Operations Research with Auto-Formulation of Optimization Models from Problem Descriptions
Rindranirina Ramamonjison, Haley Li, Timothy T. Yu +5
We describe an augmented intelligence system for simplifying and enhancing the modeling experience for operations research. Using this system, the user receives a suggested formula…
SemAug: Semantically Meaningful Image Augmentations for Object Detection Through Language Grounding
Morgan Heisler, Amin Banitalebi-Dehkordi, Yong Zhang
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 an…
Deep Reinforcement Learning for Exact Combinatorial Optimization: Learning to Branch
Tianyu Zhang, Amin Banitalebi-Dehkordi, Yong Zhang
Branch-and-bound is a systematic enumerative method for combinatorial optimization, where the performance highly relies on the variable selection strategy. State-of-the-art handcra…
AuxMix: Semi-Supervised Learning with Unconstrained Unlabeled Data
Amin Banitalebi-Dehkordi, Pratik Gujjar, Yong Zhang
Semi-supervised learning (SSL) has seen great strides when labeled data is scarce but unlabeled data is abundant. Critically, most recent work assume that such unlabeled data is dr…
Spatial Cross-Attention Improves Self-Supervised Visual Representation Learning
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. The main idea behind these methods is that diffe…
Extending Momentum Contrast with Cross Similarity Consistency Regularization
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 neg…
Asynchronous, Option-Based Multi-Agent Policy Gradient: A Conditional Reasoning Approach
Xubo Lyu, Amin Banitalebi-Dehkordi, Mo Chen +1
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 g…
E-LANG: Energy-Based Joint Inferencing of Super and Swift Language Models
Mohammad Akbari, Amin Banitalebi-Dehkordi, Yong Zhang
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 ap…
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
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…
Model Composition: Can Multiple Neural Networks Be Combined into a Single Network Using Only Unlabeled Data?
Amin Banitalebi-Dehkordi, Xinyu Kang, Yong Zhang
The diversity of deep learning applications, datasets, and neural network architectures necessitates a careful selection of the architecture and data that match best to a target ap…
Repaint: Improving the Generalization of Down-Stream Visual Tasks by Generating Multiple Instances of Training Examples
Amin Banitalebi-Dehkordi, Yong Zhang
Convolutional Neural Networks (CNNs) for visual tasks are believed to learn both the low-level textures and high-level object attributes, throughout the network depth. This paper f…
EBJR: Energy-Based Joint Reasoning for Adaptive Inference
Mohammad Akbari, Amin Banitalebi-Dehkordi, Yong Zhang
State-of-the-art deep learning models have achieved significant performance levels on various benchmarks. However, the excellent performance comes at a cost of inefficient computat…
Auto-Split: A General Framework of Collaborative Edge-Cloud AI
Amin Banitalebi-Dehkordi, Naveen Vedula, Jian Pei +3
In many industry scale applications, large and resource consuming machine learning models reside in powerful cloud servers. At the same time, large amounts of input data are collec…
SimROD: A Simple Adaptation Method for Robust Object Detection
Rindra Ramamonjison, Amin Banitalebi-Dehkordi, Xinyu Kang +2
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…
Revisiting Knowledge Distillation for Object Detection
Amin Banitalebi-Dehkordi
The existing solutions for object detection distillation rely on the availability of both a teacher model and ground-truth labels. We propose a new perspective to relax this constr…
A Study on the Relationship Between Depth Map Quality and the Overall 3D Video Quality OF Experience
Amin Banitalebi-Dehkordi, Mahsa T. Pourazad, Panos Nasiopoulos
The emergence of multiview displays has made the need for synthesizing virtual views more pronounced, since it is not practical to capture all of the possible views when filming mu…
3D Video Quality Metric for Mobile Applications
Amin Banitalebi-Dehkordi, Mahsa T. Pourazad, Panos Nasiopoulos
In this paper, we propose a new full-reference quality metric for mobile 3D content. Our method is modeled around the Human Visual System, fusing the information of both left and r…
ISO/IEC JTC1/SC29/WG11 MPEG2014/ m34661: Quality Assessment of High Dynamic Range (HDR) Video Content Using Existing Full-Reference Metrics
Amin Banitalebi-Dehkordi, Maryam Azimi, Yuanyuan Dong +2
The main focus of this document is to evaluate the performance of the existing LDR and HDR metrics on HDR video content which in turn will allow for a better understanding of how w…
ITU-T SG 16 WP 3 and ISO/IEC JTC 1/SC 29/WG 11 - JCT3V-C0032: A human visual system based 3D video quality metric
Amin Banitalebi-Dehkordi, Mahsa T. Pourazad, Panos Nasiopoulos
This contribution proposes a full-reference Human-Visual-System based 3D video quality metric. In this report, the presented metric is used to evaluate the quality of compressed st…
An Improvement Technique based on Structural Similarity Thresholding for Digital Watermarking
Amin Banitalebi-Dehkordi, Mehdi Banitalebi-Dehkordi, Jamshid Abouei +1
Digital watermarking is extensively used in ownership authentication and copyright protection. In this paper, we propose an efficient thresholding scheme to improve the watermark e…
Introducing A Public Stereoscopic 3D High Dynamic Range (SHDR) Video Database
Amin Banitalebi-Dehkordi
High Dynamic Range (HDR) displays and cameras are paving their ways through the consumer market at a rapid growth rate. Thanks to TV and camera manufacturers, HDR systems are now b…