paper-with-me

홈 › Papers

Solution for Large-scale Long-tailed Recognition with Noisy Labels

2021-06-20 · Yuqiao Xian, Jia-Xin Zhuang, Fufu Yu

This is a technical report for CVPR 2021 AliProducts Challenge. AliProducts Challenge is a competition proposed for studying the large-scale and fine-grained commodity image recognition problem encountered by worldleading ecommerce companies. The large-scale product recognition simultaneously meets the challenge of noisy annotations, imbalanced (long-tailed) data distribution and fine-grained classification. In our solution, we adopt stateof-the-art model architectures of both CNNs and Transformer, including ResNeSt, EfficientNetV2, and DeiT. We found that iterative data cleaning, classifier weight normalization, high-resolution finetuning, and test time augmentation are key components to improve the performance of training with the noisy and imbalanced dataset. Finally, we obtain 6.4365% mean class error rate in the leaderboard with our ensemble model.

📄 PDF Abstract BibTeX arXiv:2106.10683

Code (1)

JiaxinZhuang/Large-scale-Product-Recognition.Pytorch 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Pointwise Convolution Pointwise Convolution is a type of convolution that uses a 1x1 kernel: a kernel that iterates through every single point. This…
Depthwise Convolution Depthwise Convolution is a type of convolution where we apply a single convolutional filter for each input channel. In the regular 2D…
Depthwise Separable Convolution While standard convolution performs the channelwise and spatial-wise computation in one step, Depthwise Separable Convolution …
Inverted Residual Block 설명 없음
EfficientNetV2 EfficientNetV2 is a type convolutional neural network that has faster training speed and better parameter efficiency than [previous…

Similar Papers 제목 키워드 기반

VideoLT: Large-scale Long-tailed Video Recognition

2021-05-06 · ICCV 2021 10 · Xing Zhang, Zuxuan Wu, Zejia Weng, Huazhu Fu 외

Label distributions in real-world are oftentimes long-tailed and imbalanced, resulting in biased models towards dominant labels. While long-tailed recognition has been extensively studied for image classification tasks, …

image-classificationImage ClassificationVideo Recognition

Towards long-tailed, multi-label disease classification from chest X-ray: Overview of the CXR-LT challenge

2023-10-24 · Gregory Holste, Yiliang Zhou, Song Wang, Ajay Jaiswal 외

Many real-world image recognition problems, such as diagnostic medical imaging exams, are "long-tailed" $\unicode{x2013}$ there are a few common findings followed by many more relatively rare conditions. In chest radiogr…

ClassificationDiagnosticimage-classificationImage Classification+1

Self Supervision to Distillation for Long-Tailed Visual Recognition

2021-09-09 · ICCV 2021 10 · TianHao Li, LiMin Wang, Gangshan Wu

Deep learning has achieved remarkable progress for visual recognition on large-scale balanced datasets but still performs poorly on real-world long-tailed data. Previous methods often adopt class re-balanced training str…

Long-tail Learning

Investigate the Essence of Long-Tailed Recognition from a Unified Perspective

2021-07-08 · Lei Liu, Li Liu

As the data scale grows, deep recognition models often suffer from long-tailed data distributions due to the heavy imbalanced sample number across categories. Indeed, real-world data usually exhibit some similarity relat…

Self-Supervised Learning

Range Loss for Deep Face Recognition With Long-Tailed Training Data

2017-10-01 · ICCV 2017 10 · Xiao Zhang, Zhiyuan Fang, Yandong Wen, Zhifeng Li 외

Deep convolutional neural networks have achieved significant improvements on face recognition task due to their ability to learn highly discriminative features from tremendous amounts of face images. Many large scale fac…

Face Recognition