Deep active learning for image classification

Ranganathan, Hiranmayi; Venkateswara, Hemanth; Chakraborty, Sudipta; Panchanathan, Sethuraman

doi:10.1109/icip.2017.8297020

Cited by 55 publications

(14 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The core of active learning is to design a selection strategy so that the labeled samples can effectively improve the model performance. The classic selection strategy is based on model uncertainty [ 22 , 23 ].…”

Section: Related Workmentioning

confidence: 99%

Deep Active Learning Framework for Lymph Node Metastasis Prediction in Medical Support System

Zhuang

Dai

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Assessing the extent of cancer spread by histopathological analysis of sentinel axillary lymph nodes is an important part of breast cancer staging. With the maturity and prevalence of deep learning technology, building auxiliary medical systems can help to relieve the burden of pathologists and increase the diagnostic precision and accuracy during this process. However, such histopathological images have complex patterns that are difficult for ordinary people to understand and require professional medical practitioners to annotate. This increases the cost of constructing such medical systems. To reduce the cost of annotating and improve the performance of the model as much as possible, in other words, using as few labeled samples as possible to obtain a greater performance improvement, we propose a deep learning framework with a three-stage query strategy and novel model update strategy. The framework first trains an auto-encoder with all the samples to obtain a global representation in a low-dimensional space. In the query stage, the unlabeled samples are first selected according to uncertainty, and then, coreset-based methods are employed to reduce sample redundancy. Finally, distribution differences between labeled samples and unlabeled samples are evaluated and samples that can quickly eliminate the distribution differences are selected. This method achieves faster iterative efficiency than the uncertainty strategies, representative strategies, or hybrid strategies on the lymph node slice dataset and other commonly used datasets. It reaches the performance of training with all data, but only uses 50% of the labeled. During the model update process, we randomly freeze some weights and only train the task model on new labeled samples with a smaller learning rate. Compared with fine-tuning task model on new samples, large-scale performance degradation is avoided. Compared with the retraining strategy or the replay strategy, it reduces the training cost of updating the task model by 79.87% and 90.07%, respectively.

show abstract

Section: Related Workmentioning

confidence: 99%

Deep Active Learning Framework for Lymph Node Metastasis Prediction in Medical Support System

Zhuang

Dai

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…are two general approaches to recognize the most appropriate samples (Dasgupta 2011) with monotonic acquisition: uncertainty sampling and diversity sampling. While uncertainty sampling efficiently searches the hypothesis space by finding difficult examples to label (Asghar et al 2017;He et al 2019;Ranganathan et al 2017), diversity sampling exploits heterogeneity in the feature space (Hu, Mac Namee, and Delany 2010;Bodó, Minier, and Csató 2011). Recently, hybrid approaches are proposed (Zhdanov 2019;Ash et al 2019).…”

Section: Data Acquisition Strategies In Almentioning

confidence: 99%

TrustAL: Trustworthy Active Learning Using Knowledge Distillation

Kwak

Kim

et al. 2022

AAAI

View full text Add to dashboard Cite

Active learning can be defined as iterations of data labeling, model training, and data acquisition, until sufficient labels are acquired. A traditional view of data acquisition is that, through iterations, knowledge from human labels and models is implicitly distilled to monotonically increase the accuracy and label consistency. Under this assumption, the most recently trained model is a good surrogate for the current labeled data, from which data acquisition is requested based on uncertainty/diversity. Our contribution is debunking this myth and proposing a new objective for distillation. First, we found example forgetting, which indicates the loss of knowledge learned across iterations. Second, for this reason, the last model is no longer the best teacher-- For mitigating such forgotten knowledge, we select one of its predecessor models as a teacher, by our proposed notion of "consistency". We show that this novel distillation is distinctive in the following three aspects; First, consistency ensures to avoid forgetting labels. Second, consistency improves both uncertainty/diversity of labeled data. Lastly, consistency redeems defective labels produced by human annotators.

show abstract

“…Once the partitions are formed, one or multiple instances are chosen to represent it. Recently, many works have implemented a combination of deep neural networks for active learning [33]- [35]. However, to the best of our knowledge, COVID-Al [36] is the only work that explores active learning for CT scan data labeling.…”

Section: Related Workmentioning

confidence: 99%