10 citations · 19 across the 10 of their papers we have counts for
12 papers
SCOT: Self-Supervised Contrastive Pretraining For Zero-Shot Compositional Retrieval
Bhavin Jawade, Joao V. B. Soares, Kapil Thadani +6
Compositional image retrieval (CIR) is a multimodal learning task where a model combines a query image with a user-provided text modification to retrieve a target image. CIR finds…
Salient Object-Aware Background Generation using Text-Guided Diffusion Models
Amir Erfan Eshratifar, Joao V. B. Soares, Kapil Thadani +4
Generating background scenes for salient objects plays a crucial role across various domains including creative design and e-commerce, as it enhances the presentation and context o…
Efficient Training of Deep Convolutional Neural Networks by Augmentation in Embedding Space
Mohammad Saeed Abrishami, Amir Erfan Eshratifar, David Eigen +3
Recent advances in the field of artificial intelligence have been made possible by deep neural networks. In applications where data are scarce, transfer learning and data augmentat…
Runtime Deep Model Multiplexing for Reduced Latency and Energy Consumption Inference
Amir Erfan Eshratifar, Massoud Pedram
We propose a learning algorithm to design a light-weight neural multiplexer that given the input and computational resource requirements, calls the model that will consume the mini…
Video Person Re-ID: Fantastic Techniques and Where to Find Them
Priyank Pathak, Amir Erfan Eshratifar, Michael Gormish
The ability to identify the same person from multiple camera views without the explicit use of facial recognition is receiving commercial and academic interest. The current status-…
Coarse2Fine: A Two-stage Training Method for Fine-grained Visual Classification
Amir Erfan Eshratifar, David Eigen, Michael Gormish +1
Small inter-class and large intra-class variations are the main challenges in fine-grained visual classification. Objects from different classes share visually similar structures a…
BottleNet: A Deep Learning Architecture for Intelligent Mobile Cloud Computing Services
Amir Erfan Eshratifar, Amirhossein Esmaili, Massoud Pedram
Recent studies have shown the latency and energy consumption of deep neural networks can be significantly improved by splitting the network between the mobile device and cloud. Thi…
Towards Collaborative Intelligence Friendly Architectures for Deep Learning
Amir Erfan Eshratifar, Amirhossein Esmaili, Massoud Pedram
Modern mobile devices are equipped with high-performance hardware resources such as graphics processing units (GPUs), making the end-side intelligent services more feasible. Even r…
Gradient Agreement as an Optimization Objective for Meta-Learning
Amir Erfan Eshratifar, David Eigen, Massoud Pedram
This paper presents a novel optimization method for maximizing generalization over tasks in meta-learning. The goal of meta-learning is to learn a model for an agent adapting rapid…
A Meta-Learning Approach for Custom Model Training
Amir Erfan Eshratifar, Mohammad Saeed Abrishami, David Eigen +1
Transfer-learning and meta-learning are two effective methods to apply knowledge learned from large data sources to new tasks. In few-class, few-shot target task settings (i.e. whe…
A Hardware-Friendly Algorithm for Scalable Training and Deployment of Dimensionality Reduction Models on FPGA
Mahdi Nazemi, Amir Erfan Eshratifar, Massoud Pedram
With ever-increasing application of machine learning models in various domains such as image classification, speech recognition and synthesis, and health care, designing efficient…
JointDNN: An Efficient Training and Inference Engine for Intelligent Mobile Cloud Computing Services
Amir Erfan Eshratifar, Mohammad Saeed Abrishami, Massoud Pedram
Deep learning models are being deployed in many mobile intelligent applications. End-side services, such as intelligent personal assistants, autonomous cars, and smart home service…