List your company

Research

Papers for “imagenet”

Find papers, implementations, and the benchmark evidence behind state-of-the-art AI systems.

Search results

TitleAuthorsYearSource
TRT-ViT: TensorRT-oriented Vision TransformerXin Xia, Jiashi Li, Jie Wu2022arxiv 2205.09579
Novel Class Discovery without ForgettingK J Joseph, Sujoy Paul, Gaurav Aggarwal2022arxiv 2207.10659
RepBNN: towards a precise Binary Neural Network with Enhanced Feature Map via RepeatingXulong Shi, Zhi Qi, Jiaxuan Cai2022arxiv 2207.09049
StolenEncoder: Stealing Pre-trained Encoders in Self-supervised LearningYupei Liu, Jinyuan Jia, Hongbin Liu2022arxiv 2201.05889
Tip-Adapter: Training-free Adaption of CLIP for Few-shot ClassificationRenrui Zhang, Zhang Wei, Rongyao Fang2022arxiv 2207.09519
Improving Vision Transformers by Revisiting High-frequency ComponentsJiawang Bai, Li Yuan, Shu-Tao Xia2022arxiv 2204.00993
Abutting Grating Illusion: Cognitive Challenge to Neural Network ModelsJinyu Fan, Yi Zeng2022arxiv 2208.03958
Towards Adversarial Purification using Denoising AutoEncodersDvij Kalaria, Aritra Hazra, Partha Pratim Chakrabarti2022arxiv 2208.13838
ViTKD: Practical Guidelines for ViT feature knowledge distillationZhendong Yang, Zhe Li, Ailing Zeng2022arxiv 2209.02432
Distributed Adversarial Training to Robustify Deep Neural Networks at ScaleGaoyuan Zhang, Songtao Lu, Yihua Zhang2022arxiv 2206.06257
Altering Backward Pass Gradients improves ConvergenceBishshoy Das, Milton Mondal, Brejesh Lall2021arxiv 2111.12495
Making Sense of Dependence: Efficient Black-box Explanations Using Dependence MeasurePaul Novello, Thomas Fel, David Vigouroux2022arxiv 2206.06219
CLIP model is an Efficient Continual LearnerVishal Thengane, Salman Khan, Munawar Hayat2022arxiv 2210.03114
Self-supervised Pre-training for Semantic Segmentation in an Indoor SceneSulabh Shrestha, Yimeng Li, Jana Kosecka2022arxiv 2210.01884
Patching open-vocabulary models by interpolating weightsGabriel Ilharco, Mitchell Wortsman, Samir Yitzhak Gadre2022arxiv 2208.05592
Black-box Safety Analysis and Retraining of DNNs based on Feature Extraction and ClusteringMohammed Oualid Attaoui, Hazem Fahmy, Fabrizio Pastore2022arxiv 2201.05077
CWP: Instance complexity weighted channel-wise soft masks for network pruningJiapeng Wang, Ming Ma, Zhenhua Yu2022arxiv 2209.03534
Self-supervised Model Based on Masked Autoencoders Advance CT Scans ClassificationJiashu Xu, Sergii Stirenko2022arxiv 2210.05073
On the Adversarial Robustness of Mixture of ExpertsJoan Puigcerver, Rodolphe Jenatton, Carlos Riquelme2022arxiv 2210.10253
ZO-AdaMM: Zeroth-Order Adaptive Momentum Method for Black-Box OptimizationXiangyi Chen, Sijia Liu, Kaidi Xu2019arxiv 1910.06513