Image Classification

by Synced 2021-12-16 1

NVIDIA’s AdaViT Halts Token Computation to Adaptively Adjust ViT Inference Cost on Images of Different Complexity

Nvidia researchers propose AdaViT, an input-dependent mechanism that adaptively adjusts vision transformers’ inference cost by halting the compute of different tokens at different depths to reserve compute for discriminative tokens.

by Synced 2021-08-27 5

AI Computer Vision & Graphics Machine Learning & Data Science Research

Google Brain Uncovers Representation Structure Differences Between CNNs and Vision Transformers

A Google Brain research team explores the internal representation structures of ViTs and CNNs on image classification tasks, providing insights on key differences between the two approaches.

by Synced 2020-11-03 3

AI China Research

SJTU’s MedMNIST Classification Decathlon: Lightweight AutoML Benchmarking for Medical Image Analysis

A team of researchers from Shanghai Jiao Tong University (SJTU) has built a lightweight benchmark suite designed to help make life-saving models of medical image analysis even stronger.

by Synced 2019-08-09 0

AI Research

Semantic Based Adversarial Examples Fool Face Recognition

Researchers have proposed a new adversarial attack approach, SemanticAdv, which generates adversarial perturbations by manipulating not pixels but rather an image’s semantic attributes.