Hydra Attention: Efficient Attention with Many Heads
Daniel Bolya, Cheng-Yang Fu, Xiaoliang Dai, Peizhao Zhang, Judy Hoffman
Topics & Concepts
Lernaean HydraQuadratic growthComputer scienceComputationSecurity tokenTransformerArtificial intelligenceArithmeticAlgorithmMathematicsComputer securityQuantum mechanicsVoltageHistoryClassicsPhysicsAdvanced Neural Network ApplicationsVisual Attention and Saliency DetectionImage Enhancement Techniques