paper-with-me

Papers

Solving ImageNet: a Unified Scheme for Training any Backbone to Top Results

2022-04-07 · Tal Ridnik, Hussam Lawen, Emanuel Ben-Baruch, Asaf Noy

ImageNet serves as the primary dataset for evaluating the quality of computer-vision models. The common practice today is training each architecture with a tailor-made scheme, designed and tuned by an expert. In this paper, we present a unified scheme for training any backbone on ImageNet. The scheme, named USI (Unified Scheme for ImageNet), is based on knowledge distillation and modern tricks. It requires no adjustments or hyper-parameters tuning between different models, and is efficient in terms of training times. We test USI on a wide variety of architectures, including CNNs, Transformers, Mobile-oriented and MLP-only. On all models tested, USI outperforms previous state-of-the-art results. Hence, we are able to transform training on ImageNet from an expert-oriented task to an automatic seamless routine. Since USI accepts any backbone and trains it to top results, it also enables to perform methodical comparisons, and identify the most efficient backbones along the speed-accuracy Pareto curve. Implementation is available at:https://github.com/Alibaba-MIIL/Solving_ImageNet

📄 PDF Abstract BibTeX arXiv:2204.03475

Code (2)

alibaba-miil/solving_imagenet 공식 구현 pytorch
mmaaz60/EdgeNeXt pytorch

Tasks

Image ClassificationKnowledge Distillation

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

Class-Incremental Learning with Strong Pre-trained Models

2022-04-07 · CVPR 2022 1 · Tz-Ying Wu, Gurumurthy Swaminathan, Zhizhong Li, Avinash Ravichandran 외

Class-incremental learning (CIL) has been widely studied under the setting of starting from a small number of classes (base classes). Instead, we explore an understudied real-world setting of CIL that starts with a stron…

class-incremental learningClass Incremental LearningIncremental Learning

Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet

2021-01-28 · ICCV 2021 10 · Li Yuan, Yunpeng Chen, Tao Wang, Weihao Yu 외

Transformers, which are popular for language modeling, have been explored for solving vision tasks recently, e.g., the Vision Transformer (ViT) for image classification. The ViT model splits each image into a sequence of…

image-classificationImage ClassificationLanguage ModelingLanguage Modelling

DreamTeacher: Pretraining Image Backbones with Deep Generative Models

2023-07-14 · ICCV 2023 1 · Daiqing Li, Huan Ling, Amlan Kar, David Acuna 외

In this work, we introduce a self-supervised feature representation learning framework DreamTeacher that utilizes generative networks for pre-training downstream image backbones. We propose to distill knowledge from a tr…

Knowledge DistillationRepresentation Learning

Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers

2026-07-01 · Aravind Pradeep, Samira Nazari, Mahdi Taheri, Christian Herglotz arxiv

Vision Transformers achieve strong image classification accuracy but process all image regions with nearly the same computation, even when many regions are redundant or uninformative. Recent adaptive inference methods re…

Image Classification

CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows

2021-07-01 · CVPR 2022 1 · Xiaoyi Dong, Jianmin Bao, Dongdong Chen, Weiming Zhang 외

We present CSWin Transformer, an efficient and effective Transformer-based backbone for general-purpose vision tasks. A challenging issue in Transformer design is that global self-attention is very expensive to compute w…

Image ClassificationSemantic Segmentation