English
Related papers

Related papers: Toward Errorless Training ImageNet-1k

200 papers

To calculate the model accuracy on a computer vision task, e.g., object recognition, we usually require a test set composing of test samples and their ground truth labels. Whilst standard usage cases satisfy this requirement, many…

Computer Vision and Pattern Recognition · Computer Science 2021-05-26 Weijian Deng , Liang Zheng

In this paper, we identify an important reproducibility challenge in the image-to-set prediction literature that impedes proper comparisons among published methods, namely, researchers use different evaluation protocols to assess their…

Computer Vision and Pattern Recognition · Computer Science 2020-05-28 Luis Pineda , Amaia Salvador , Michal Drozdzal , Adriana Romero

In deep learning era, pretrained models play an important role in medical image analysis, in which ImageNet pretraining has been widely adopted as the best way. However, it is undeniable that there exists an obvious domain gap between…

Computer Vision and Pattern Recognition · Computer Science 2020-07-23 Hong-Yu Zhou , Shuang Yu , Cheng Bian , Yifan Hu , Kai Ma , Yefeng Zheng

Deep learning has gained broad interest in remote sensing image scene classification thanks to the effectiveness of deep neural networks in extracting the semantics from complex data. However, deep networks require large amounts of training…

Computer Vision and Pattern Recognition · Computer Science 2025-10-08 Gianmarco Perantoni , Lorenzo Bruzzone

Humans can continuously learn new knowledge as their experience grows. In contrast, previous learning in deep neural networks can quickly fade out when they are trained on a new task. In this paper, we hypothesize this problem can be…

Machine Learning · Computer Science 2020-03-27 Jathushan Rajasegaran , Salman Khan , Munawar Hayat , Fahad Shahbaz Khan , Mubarak Shah

In medical image segmentation tasks, the scarcity of labeled training data poses a significant challenge when training deep neural networks. When using U-Net-style architectures, it is common practice to address this problem by pretraining…

Computer Vision and Pattern Recognition · Computer Science 2025-06-09 Gábor Hidy , Bence Bakos , András Lukács

In this research, we focus on the usage of adversarial sampling to test for the fairness in the prediction of deep neural network model across different classes of image in a given dataset. While several framework had been proposed to…

Machine Learning · Computer Science 2023-03-07 Tosin Ige , William Marfo , Justin Tonkinson , Sikiru Adewale , Bolanle Hafiz Matti

The goal of our research is to develop methods advancing automatic visual recognition. In order to predict the unique or multiple labels associated to an image, we study different kind of Deep Neural Networks architectures and methods for…

Computer Vision and Pattern Recognition · Computer Science 2016-10-19 Rémi Cadène , Nicolas Thome , Matthieu Cord

We propose a scalable photonic architecture for implementation of feedforward and recurrent neural networks to perform the classification of handwritten digits from the MNIST database. Our experiment exploits off-the-shelf optical and…

Neural and Evolutionary Computing · Computer Science 2020-04-07 Piotr Antonik , Nicolas Marsal , Damien Rontani

The keep-growing content of Web images may be the next important data source to scale up deep neural networks, which recently obtained a great success in the ImageNet classification challenge and related tasks. This prospect, however, has…

Computer Vision and Pattern Recognition · Computer Science 2016-07-19 Phong D. Vo , Alexandru Ginsca , Hervé Le Borgne , Adrian Popescu

Deep learning enables impressive performance in image recognition using large-scale artificially-balanced datasets. However, real-world datasets exhibit highly class-imbalanced distributions, yielding two main challenges: relative imbalance…

Computer Vision and Pattern Recognition · Computer Science 2020-10-20 Saurabh Sharma , Ning Yu , Mario Fritz , Bernt Schiele

In existing visual representation learning tasks, deep convolutional neural networks (CNNs) are often trained on images annotated with single tags, such as ImageNet. However, a single tag cannot describe all important contents of one image,…

Computer Vision and Pattern Recognition · Computer Science 2020-02-11 Baoyuan Wu , Weidong Chen , Yanbo Fan , Yong Zhang , Jinlong Hou , Jie Liu , Tong Zhang

Recent studies on learning with noisy labels have shown remarkable performance by exploiting a small clean dataset. In particular, model agnostic meta-learning-based label correction methods further improve performance by correcting noisy…

Machine Learning · Computer Science 2022-07-13 Seong Min Kye , Kwanghee Choi , Joonyoung Yi , Buru Chang

As researchers teach robots to perform more and more complex tasks, the need for realistic simulation environments is growing. Existing techniques for closing the reality gap by approximating real-world physics often require extensive real…

Robotics · Computer Science 2020-02-17 Adam Allevato , Elaine Schaertl Short , Mitch Pryor , Andrea L. Thomaz

Measuring the colorfulness of a natural or virtual scene is critical for many applications in image processing field ranging from capturing to display. In this paper, we propose the first deep learning-based colorfulness estimation metric.…

Multimedia · Computer Science 2019-08-23 Emin Zerman , Aakanksha Rana , Aljosa Smolic

Deep neural networks are highly susceptible to overfitting noisy labels, which leads to degraded performance. Existing methods address this issue by employing manually defined criteria, aiming to achieve optimal partitioning in each…

Computer Vision and Pattern Recognition · Computer Science 2025-02-04 Wenzhen Zhang , Debo Cheng , Guangquan Lu , Bo Zhou , Jiaye Li , Shichao Zhang

ASR models are commonly trained with the cross-entropy criterion to increase the probability of a target token sequence. While optimizing the probability of all tokens in the target sequence is sensible, one may want to de-emphasize tokens…

Computation and Language · Computer Science 2024-06-27 Gil Keren , Wei Zhou , Ozlem Kalinli

Deep neural networks can be effective means to automatically classify aerial images but is easy to overfit to the training data. It is critical for trained neural networks to be robust to variations that exist between training and test…

Computer Vision and Pattern Recognition · Computer Science 2019-09-25 Jiayun Wang , Patrick Virtue , Stella X. Yu

Deep learning is extremely computationally intensive, and hardware vendors have responded by building faster accelerators in large clusters. Training deep learning models at petaFLOPS scale requires overcoming both algorithmic and systems…

Machine Learning · Computer Science 2018-12-04 Chris Ying , Sameer Kumar , Dehao Chen , Tao Wang , Youlong Cheng

The presence of label noise often misleads the training of deep neural networks. Departing from the recent literature which largely assumes the label noise rate is only determined by the true label class, the errors in human-annotated…

Machine Learning · Computer Science 2021-03-31 Zhaowei Zhu , Tongliang Liu , Yang Liu