activity
20122024
most citedDeFINE: DEep Factorized INput Token Embeddings for Neural Sequence Modeling

13 citations · 24 across the 5 of their papers we have counts for

collaborators
Showing cs.CVShow all

12 papers · 1 filter

cs.CV2019

What's Hidden in a Randomly Weighted Neural Network?

Vivek Ramanujan, Mitchell Wortsman, Aniruddha Kembhavi +2

Training a neural network is synonymous with learning the values of the weights. By contrast, we demonstrate that randomly weighted neural networks contain subnetworks which achiev…

cs.CV2019

Assisted Excitation of Activations: A Learning Technique to Improve Object Detectors

Mohammad Mahdi Derakhshani, Saeed Masoudnia, Amir Hossein Shaker +4

We present a simple and effective learning technique that significantly improves mAP of YOLO object detectors without compromising their speed. During network training, we carefull…

cs.CV2019

DiCENet: Dimension-wise Convolutions for Efficient Networks

Sachin Mehta, Hannaneh Hajishirzi, Mohammad Rastegari

We introduce a novel and generic convolutional unit, DiCE unit, that is built using dimension-wise convolutions and dimension-wise fusion. The dimension-wise convolutions apply lig…

cs.CV2019

Butterfly Transform: An Efficient FFT Based Neural Architecture Design

Keivan Alizadeh Vahid, Anish Prabhu, Ali Farhadi +1

In this paper, we show that extending the butterfly operations from the FFT algorithm to a general Butterfly Transform (BFT) can be beneficial in building an efficient block struct…

cs.CV2019

OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge

Kenneth Marino, Mohammad Rastegari, Ali Farhadi +1

Visual Question Answering (VQA) in its ideal form lets us study reasoning in the joint space of vision and language and serves as a proxy for the AI task of scene understanding. Ho…

cs.CV2019

Two Body Problem: Collaborative Visual Task Completion

Unnat Jain, Luca Weihs, Eric Kolve +5

Collaboration is a necessary skill to perform tasks that are beyond one agent's capabilities. Addressed extensively in both conventional and modern AI, multi-agent collaboration ha…