Task-wise attention guided part complementary learning for few-shot image classification

Cheng, Gong; Li, Ruimin; Lang, Chunbo; Han, Junwei

doi:10.1007/s11432-020-3156-7

Cited by 54 publications

(10 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Classification is one of the most basic tasks in machine learning, and it has been applied to many fields such as natural image classification [11] , [34] , handwriting recognition [35] , medical image classification [36] , etc. In the early days, some simple methods like logistic regression [37] and naive bayes classifier [38] were proposed to solve the linear classification problem.…”

Section: Related Workmentioning

confidence: 99%

Eliminating Indefiniteness of Clinical Spectrum for Better Screening COVID-19

Guo

Liu

Zhao

et al. 2021

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

The coronavirus disease 2019 (COVID-19) has swept all over the world in the last few months. Due to the limited detection facilities and medical resources, especially in developing countries, a large number of suspected cases can only receive common clinical diagnosis rather than more effective detections like Reverse Transcription Polymerase Chain Reaction (RT-PCR) tests or CT scans. This motivates us to develop a quick screening method on suspected patients via common clinical diagnosis results. However, the diagnostic items of different patients may vary greatly and there is a huge variation in the dimension of the diagnosis data among different suspected patients, which makes it hard to process these indefinite dimension data via classical classification algorithms. To resolve this problem, we propose an Indefiniteness Elimination Network (IE-Net) to eliminate the influence of the varied dimensions and make predictions about the COVID-19 cases. The IE-Net is in an encoder-decoder framework fashion and an indefiniteness elimination operation is proposed to transfer the indefinite dimension feature into a fixed dimension feature. Comprehensive experiments were conducted on the public available COVID-19 Clinical Spectrum dataset. Experimental results show that the proposed indefiniteness elimination operation greatly improves the classification performance and the IE-Net achieves 94.80% accuracy, 92.79% recall, 92.97% precision and 94.93% AUC for distinguishing COVID-19 cases from non-COVID-19 cases with only common clinical diagnose data. We further compared our methods with 3 classical classification algorithms: random forest, gradient boosting and multi-layer perceptron (MLP). Compared with traditional classification methods, the proposed IE-Net can bring at least 9.40% accuracy gains, 12.17% recall gains, 3.66% precision and 9.71% AUC gains. To explore the specificity of each clinical test item, we further analyzed the possible relationship between each clinical test item and COVID-19. In general, we proposed a novel image complementary method for COVID-19 screen-

show abstract

Section: Related Workmentioning

confidence: 99%

Eliminating Indefiniteness of Clinical Spectrum for Better Screening COVID-19

Guo

Liu

Zhao

et al. 2021

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

show abstract

“…Feature-based attention has proved its effectiveness in many computer vision tasks as a perception-adapted mechanism [49]. For instance, Squeezeand-Excitation network (SENet) [50] proposed by Hu et al adaptively recalibrates channel relationships by global information embedding and fully connected (FC) layers.…”

Section: Attention Mechanismmentioning

confidence: 99%

Feature Enhancement Network for Object Detection in Optical Remote Sensing Images

Cheng

Lang

et al. 2021

J Remote Sens

Self Cite

View full text Add to dashboard Cite

Automatic and robust object detection in remote sensing images is of vital significance in real-world applications such as land resource management and disaster rescue. However, poor performance arises when the state-of-the-art natural image detection algorithms are directly applied to remote sensing images, which largely results from the variations in object scale, aspect ratio, indistinguishable object appearances, and complex background scenario. In this paper, we propose a novel Feature Enhancement Network (FENet) for object detection in optical remote sensing images, which consists of a Dual Attention Feature Enhancement (DAFE) module and a Context Feature Enhancement (CFE) module. Specifically, the DAFE module is introduced to highlight the network to focus on the distinctive features of the objects of interest and suppress useless ones by jointly recalibrating the spatial and channel feature responses. The CFE module is designed to capture global context cues and selectively strengthen class-aware features by leveraging image-level contextual information that indicates the presence or absence of the object classes. To this end, we employ a context encoding loss to regularize the model training which promotes the object detector to understand the scene better and narrows the probable object categories in prediction. We achieve our proposed FENet by unifying DAFE and CFE into the framework of Faster R-CNN. In the experiments, we evaluate our proposed method on two large-scale remote sensing image object detection datasets including DIOR and DOTA and demonstrate its effectiveness compared with the baseline methods.

show abstract

“…humans can easily recognize new concepts or patterns from a handful of examples, which greatly stimulates the research interest of the community [39,52,53]. Thus, few-shot learning (FSL) is proposed to address this problem by building a network that can be generalized to unseen domains with scarce annotated samples available [7,42,54,57].…”

Section: Introductionmentioning

confidence: 99%

Learning What Not to Segment: A New Perspective on Few-Shot Segmentation

Lang¹,

Chen²,

Tu³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Recently few-shot segmentation (FSS) has been extensively developed. Most previous works strive to achieve generalization through the meta-learning framework derived from classification tasks; however, the trained models are biased towards the seen classes instead of being ideally class-agnostic, thus hindering the recognition of new concepts. This paper proposes a fresh and straightforward insight to alleviate the problem. Specifically, we apply an additional branch (base learner) to the conventional FSS model (meta learner) to explicitly identify the targets of base classes, i.e., the regions that do not need to be segmented. Then, the coarse results output by these two learners in parallel are adaptively integrated to yield precise segmentation prediction. Considering the sensitivity of meta learner, we further introduce an adjustment factor to estimate the scene differences between the input image pairs for facilitating the model ensemble forecasting. The substantial performance gains on PASCAL-5 i and COCO-20 i verify the effectiveness, and surprisingly, our versatile scheme sets a new state-of-the-art even with two plain learners. Moreover, in light of the unique nature of the proposed approach, we also extend it to a more realistic but challenging setting, i.e., generalized FSS, where the pixels of both base and novel classes are required to be determined. The source code is available at github.com/chunbolang/BAM.

show abstract

Task-wise attention guided part complementary learning for few-shot image classification

Cited by 54 publications

References 37 publications

Eliminating Indefiniteness of Clinical Spectrum for Better Screening COVID-19

Eliminating Indefiniteness of Clinical Spectrum for Better Screening COVID-19

Feature Enhancement Network for Object Detection in Optical Remote Sensing Images

Learning What Not to Segment: A New Perspective on Few-Shot Segmentation

Contact Info

Product

Resources

About