P
Priya Goyal
Researcher at Facebook
Publications - 16
Citations - 31581
Priya Goyal is an academic researcher from Facebook. The author has contributed to research in topics: Object detection & Computer science. The author has an hindex of 11, co-authored 13 publications receiving 15789 citations.
Papers
More filters
Posted Content
Self-supervised Pretraining of Visual Features in the Wild
Priya Goyal,Mathilde Caron,Benjamin Lefaudeux,Min Xu,Pengchao Wang,Vivek S. Pai,Mannat Singh,Vitaliy Liptchinsky,Ishan Misra,Armand Joulin,Piotr Bojanowski +10 more
TL;DR: Recently, self-supervised learning methods like MoCo, SimCLR, BYOL and SwAV have reduced the gap with supervised methods as mentioned in this paper. But self-learning cannot learn from any random image and from any unbounded dataset.
Journal ArticleDOI
The Next 700 Accelerated Layers: From Mathematical Expressions of Network Computation Graphs to Accelerated GPU Kernels, Automatically
Nicolas Vasilache,Oleksandr Zinenko,Theodoros Theodoridis,Priya Goyal,Zachary DeVito,William S. Moses,Sven Verdoolaege,Andrew Adams,Albert Cohen +8 more
TL;DR: A domain-specific language with a tensor notation close to the mathematics of deep learning; a Just-In-Time optimizing compiler based on the polyhedral framework; carefully coordinated linear optimization and evolutionary algorithms to synthesize high-performance CUDA kernels; the transparent integration of the flow into PyTorch and Caffe2, providing the fully automatic synthesis of high- performance GPU kernels from simple tensor algebra.
Proceedings ArticleDOI
A Self-Supervised Descriptor for Image Copy Detection
TL;DR: This work introduces SSCD, a model that builds on a recent self-supervised contrastive training objective, and adapts this method to the copy detection task, including a pooling operator from the instance matching literature, and adapting contrastive learning to augmentations that combine images.
Proceedings ArticleDOI
Fairness Indicators for Systematic Assessments of Visual Feature Extractors
TL;DR: Three fairness indicators are proposed, which aim at quantifying harms and biases of visual systems, and are applied to “off-the-shelf” models built using widely adopted model training paradigms which vary in their ability to whether they can predict labels on a given image or only produce the embeddings.
Patent
Target phrase classifier
Matthias Eck,Priya Goyal +1 more
TL;DR: In this article, a classifier identifies translations containing target words or phrases and applies it to the output translation to remove target words and phrases from the translation, or to prevent target words from being automatically presented.