VSE++: Improving Visual-Semantic Embeddings with Hard Negatives

Fartash Faghri, David J. Fleet, Jamie Kiros, +1

arXiv (Cornell University)

EngineeringMachine LearningRanking Loss FunctionsImage RetrievalHard Negatives +16

Technical Report on the CleverHans v2.1.0 Adversarial Examples Library

Nicolas Papernot, Fartash Faghri, Nicholas Carlini, +23

arXiv (Cornell University)

Artificial IntelligenceEngineeringMachine LearningData ScienceMachine Learning Model +13

VSE++: Improving Visual-Semantic Embeddings with Hard Negatives.

Fartash Faghri, David J. Fleet, Jamie Kiros, +1

British Machine Vision Conference

EngineeringMachine LearningRanking Loss FunctionsImage RetrievalHard Negatives +16

VSE++: Improved Visual-Semantic Embeddings.

Fartash Faghri, David J. Fleet, Jamie Kiros, +1

arXiv (Cornell University)

EngineeringMachine LearningImage RetrievalImage SearchNatural Language Processing +16

Adversarial Manipulation of Deep Representations

Sara Sabour, Yanshuai Cao, Fartash Faghri, +1

arXiv (Cornell University)

EngineeringMachine LearningGenerative Adversarial NetworkPattern RecognitionAutoencoders +11

SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding

Haoxiang Wang, Pavan Kumar Anasosalu Vasu, Fartash Faghri, +6

Adversarial Spheres

Justin Gilmer, Luke Metz, Fartash Faghri, +4

arXiv (Cornell University)

Geometric LearningImage ClassificationImage AnalysisMachine VisionDeep Learning +13

Adaptive Gradient Quantization for Data-Parallel SGD

Fartash Faghri, Iman Tabrizian, Ilia Markov, +3

arXiv (Cornell University)

Convolutional Neural NetworkEngineeringMachine LearningData ScienceParallel Learning +13

MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training

Pavan Kumar Anasosalu Vasu, Hadi Pouransari, Fartash Faghri, +2

NUQSGD: Improved Communication Efficiency for Data-parallel SGD via Nonuniform Quantization.

Ali Ramezani-Kebrya, Fartash Faghri, Daniel M. Roy

arXiv (Cornell University)

Cluster ComputingEngineeringMachine LearningDistributed AlgorithmsComputer Architecture +17