Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userRSG: A Simple but Effective Module for Learning Imbalanced Datasets
76
0
0.0
(
0
)
Added by
Jianfeng Wang
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Imbalanced datasets widely exist in practice and area great challenge for training deep neural models with agood generalization on infrequent classes. In this work, wepropose a new rare-class sample generator (RSG) to solvethis problem. RSG aims to generate some new samplesfor rare classes during training, and it has in particularthe following advantages: (1) it is convenient to use andhighly versatile, because it can be easily integrated intoany kind of convolutional neural network, and it works wellwhen combined with different loss functions, and (2) it isonly used during the training phase, and therefore, no ad-ditional burden is imposed on deep neural networks duringthe testing phase. In extensive experimental evaluations, weverify the effectiveness of RSG. Furthermore, by leveragingRSG, we obtain competitive results on Imbalanced CIFARand new state-of-the-art results on Places-LT, ImageNet-LT, and iNaturalist 2018. The source code is available at https://github.com/Jianf-Wang/RSG.
rate research
Read More
Deep learning models are notoriously data-hungry. Thus, there is an urging need for data-efficient techniques in medical image analysis, where well-annotated data are costly and time consuming to collect. Motivated by the recently revived Copy-Paste augmentation, we propose TumorCP, a simple but effective object-level data augmentation method tailored for tumor segmentation. TumorCP is online and stochastic, providing unlimited augmentation possibilities for tumors subjects, locations, appearances, as well as morphologies. Experiments on kidney tumor segmentation task demonstrate that TumorCP surpasses the strong baseline by a remarkable margin of 7.12% on tumor Dice. Moreover, together with image-level data augmentation, it beats the current state-of-the-art by 2.32% on tumor Dice. Comprehensive ablation studies are performed to validate the effectiveness of TumorCP. Meanwhile, we show that TumorCP can lead to striking improvements in extremely low-data regimes. Evaluated with only 10% labeled data, TumorCP significantly boosts tumor Dice by 21.87%. To the best of our knowledge, this is the very first work exploring and extending the Copy-Paste design in medical imaging domain. Code is available at: https://github.com/YaoZhang93/TumorCP.
Many optimization methods for generating black-box adversarial examples have been proposed, but the aspect of initializing said optimizers has not been considered in much detail. We show that the choice of starting points is indeed crucial, and that the performance of state-of-the-art attacks depends on it. First, we discuss desirable properties of starting points for attacking image classifiers, and how they can be chosen to increase query efficiency. Notably, we find that simply copying small patches from other images is a valid strategy. We then present an evaluation on ImageNet that clearly demonstrates the effectiveness of this method: Our initialization scheme reduces the number of queries required for a state-of-the-art Boundary Attack by 81%, significantly outperforming previous results reported for targeted black-box adversarial examples.
Zero-Shot Learning (ZSL) is a classification task where we do not have even a single training labeled example from a set of unseen classes. Instead, we only have prior information (or description) about seen and unseen classes, often in the form of physically realizable or descriptive attributes. Lack of any single training example from a set of classes prohibits use of standard classification techniques and losses, including the popular crossentropy loss. Currently, state-of-the-art approaches encode the prior class information into dense vectors and optimize some distance between the learned projections of the input vector and the corresponding class vector (collectively known as embedding models). In this paper, we propose a novel architecture of casting zero-shot learning as a standard neural-network with crossentropy loss. During training our approach performs soft-labeling by combining the observed training data for the seen classes with the similarity information from the attributes for which we have no training data or unseen classes. To the best of our knowledge, such similarity based soft-labeling is not explored in the field of deep learning. We evaluate the proposed model on the four benchmark datasets for zero-shot learning, AwA, aPY, SUN and CUB datasets, and show that our model achieves significant improvement over the state-of-the-art methods in Generalized-ZSL and ZSL settings on all of these datasets consistently.
In this paper, we tackle a fully unsupervised super-resolution problem, i.e., neither paired images nor ground truth HR images. We assume that low resolution (LR) images are relatively easy to collect compared to high resolution (HR) images. By allowing multiple LR images, we build a set of pseudo pairs by denoising and downsampling LR images and cast the original unsupervised problem into a supervised learning problem but in one level lower. Though this line of study is easy to think of and thus should have been investigated prior to any complicated unsupervised methods, surprisingly, there are currently none. Even more, we show that this simple method outperforms the state-of-the-art unsupervised method with a dramatically shorter latency at runtime, and significantly reduces the gap to the HR supervised models. We submitted our method in NTIRE 2020 super-resolution challenge and won 1st in PSNR, 2nd in SSIM, and 13th in LPIPS. This simple method should be used as the baseline to beat in the future, especially when multiple LR images are allowed during the training phase. However, even in the zero-shot condition, we argue that this method can serve as a useful baseline to see the gap between supervised and unsupervised frameworks.
Rating prediction is a core problem in recommender systems to quantify users preferences towards different items. Due to the imbalanced rating distributions in training data, existing recommendation methods suffer from the biased prediction problem that generates biased prediction results. Thus, their performance on predicting ratings which rarely appear in training data is unsatisfactory. In this paper, inspired by the superior capability of Extreme Value Distribution (EVD)-based methods in modeling the distribution of rare data, we propose a novel underline{emph{G}}umbel Distribution-based underline{emph{R}}ating underline{emph{P}}rediction framework (GRP) which can accurately predict both frequent and rare ratings between users and items. In our approach, we first define different Gumbel distributions for each rating level, which can be learned by historical rating statistics of users and items. Second, we incorporate the Gumbel-based representations of users and items with their original representations learned from the rating matrix and/or reviews to enrich the representations of users and items via a proposed multi-scale convolutional fusion layer. Third, we propose a data-driven rating prediction module to predict the ratings of user-item pairs. Its worthy to note that our approach can be readily applied to existing recommendation methods for addressing their biased prediction problem. To verify the effectiveness of GRP, we conduct extensive experiments on eight benchmark datasets. Compared with several baseline models, the results show that: 1) GRP achieves state-of-the-art overall performance on all eight datasets; 2) GRP makes a substantial improvement in predicting rare ratings, which shows the effectiveness of our model in addressing the bias prediction problem.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
