Attentional Kernel Encoding Networks for Fine-Grained Visual Categorization

Hu, Yutao; Yang, Yandan; Zhang, Jun; Cao, Xianbin; Zhen, Xiantong

doi:10.1109/tcsvt.2020.2978115

Cited by 31 publications

(6 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fine-grained image classification is a trending topic in the computer vision community in recent years. Most finegrained models [6]- [11], [15], [31], [32], [35]- [39] can be roughly grouped into two categories: regional feature-based models [6], [7], [15], [31], [32], [35], [37] and global featurebased methods [5], [8]- [10], [13], [36], [40]- [42]. For finegrained images, the most informative features generally lie in the discriminate parts of the object.…”

Section: A Fine-grained Image Categorizationmentioning

confidence: 99%

“…On the other hand, global feature-based fine-grained methods [5], [8]- [10], [13], [36], [40]- [42] extract the feature from the whole image without explicitly localizing the object parts. Bilinear CNN model (BCNN) [9] is the first work that adopts matrix outer product operation on the embedding to generate a second-order representation for fine-grained classification.…”

Section: A Fine-grained Image Categorizationmentioning

confidence: 99%

See 1 more Smart Citation

TOAN: Target-Oriented Alignment Network for Fine-Grained Image Categorization With Few Labeled Samples

Huang

Zhang

et al. 2022

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

In this paper, we study the fine-grained categorization problem under the few-shot setting, i.e., each fine-grained class only contains a few labeled examples, termed Fine-Grained Few-Shot classification (FGFS). The core predicament in FGFS is the high intra-class variance yet low inter-class fluctuations in the dataset. In traditional fine-grained classification, the high intra-class variance can be somewhat relieved by conducting the supervised training on the abundant labeled samples. However, with few labeled examples, it is hard for the FGFS model to learn a robust class representation with the significantly higher intra-class variance. Moreover, the inter-and intra-class variance are closely related. The significant intra-class variance in FGFS often aggravates the low inter-class variance issue.To address the above challenges, we propose a Target-Oriented Alignment Network (TOAN) to tackle the FGFS problem from both intra-and inter-class perspective. To reduce the intra-class variance, we propose a target-oriented matching mechanism to reformulate the spatial features of each support image to match the query ones in the embedding space. To enhance the inter-class discrimination, we devise discriminative fine-grained features by integrating local compositional concept representations with the global second-order pooling. We conducted extensive experiments on four public datasets for fine-grained categorization, and the results show the proposed TOAN obtains the state-of-the-art.

show abstract

Section: A Fine-grained Image Categorizationmentioning

confidence: 99%

Section: A Fine-grained Image Categorizationmentioning

confidence: 99%

TOAN: Target-Oriented Alignment Network for Fine-Grained Image Categorization With Few Labeled Samples

Huang

Zhang

et al. 2022

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

show abstract

“…In this case, larger weights indicate that the corresponding vectors are more relevant to generating the output. Due to its powerful ability, the attention mechanism has been widely used in various neural network based applications such as language understanding tasks [11], [28], computer vision problems [32], [17]. Likewise, attention mechanism in health informatics has been prevalent in predictive modelling.…”

Section: Attention Mechanism In Health Informaticsmentioning

confidence: 99%

“…In figure 6, we can observe that ′ > ′ > ′ > ′ > ′ (see details in Eq. (16)(17)(18)), which indicates the importance ranking of multi-source embeddings. Such a phenomenon further testifies that diagnosed diseases especially the disease progression with historical disease information is the most important information for the medication recommendation task, which have been proved in the ablation study shown in Table 4.…”

Section: Attention Analysis In Selective Modulementioning

confidence: 99%

MeSIN: Multilevel Selective and Interactive Network for Medication Recommendation

An,

Zhang,

You

et al. 2021

Preprint

View full text Add to dashboard Cite

Recommending medications for patients using electronic health records (EHRs) is a crucial data mining task for an intelligent healthcare system. It can assist doctors in making clinical decisions more efficiently. However, the inherent complexity of the EHR data renders it as a challenging task: (1) Multilevel structures: the EHR data typically contains multilevel structures which are closely related with the decision-making pathways, e.g., laboratory results lead to disease diagnoses, and then contribute to the prescribed medications; (2) Multiple sequences interactions: multiple sequences in EHR data are usually closely correlated with each other; (3) Abundant noise: lots of task-unrelated features or noise information within EHR data generally result in suboptimal performance. To tackle the above challenges, we propose a multilevel selective and interactive network (MeSIN) for medication recommendation. Specifically, MeSIN is designed with three components. First, an attentional selective module (ASM) is applied to assign flexible attention scores to different medical codes embeddings by their relevance to the recommended medications in every admission. Second, we incorporate a novel interactive long-short term memory network (InLSTM) to reinforce the interactions of multilevel medical sequences in EHR data with the help of the calibrated memory-augmented cell and an enhanced input gate. Finally, we employ a global selective fusion module (GSFM) to infuse the multisourced information embeddings into final patient representations for medications recommendation. To validate our method, extensive experiments have been conducted on a real-world clinical dataset. The results demonstrate a consistent superiority of our framework over several baselines and testify the effectiveness of our proposed approach.

show abstract

“…Most recent Fine-Grained (FG) models [5], [6], [11]- [14], [34], [35], [38]- [43] can be roughly grouped into two categories: regional feature-based models [5], [11], [34], [35], [38], [40], [42] and global feature-based methods [6], [10], [12], [13], [16], [39], [44]- [46]. The regional feature-based methods focus on mining the discriminative parts of the finegrained objects, as they are the most informative parts of the FG objects.…”

Section: A Fine-grained Image Categorizationmentioning

confidence: 99%

TOAN: Target-Oriented Alignment Network for Fine-Grained Image Categorization with Few Labeled Samples

Huang,

Zhang,

Zhang

et al. 2020

Preprint

View full text Add to dashboard Cite

The challenges of high intra-class variance yet low inter-class fluctuations in fine-grained visual categorization are more severe with few labeled samples, i.e., Fine-Grained categorization problems under the Few-Shot setting (FGFS). Highorder features are usually developed to uncover subtle differences between sub-categories in FGFS, but they are less effective in handling the high intra-class variance. In this paper, we propose a Target-Oriented Alignment Network (TOAN) to investigate the fine-grained relation between the target query image and support classes. The feature of each support image is transformed to match the query ones in the embedding feature space, which reduces the disparity explicitly within each category. Moreover, different from existing FGFS approaches devise the high-order features over the global image with less explicit consideration of discriminative parts, we generate discriminative fine-grained features by integrating compositional concept representations to global second-order pooling. Extensive experiments are conducted on four fine-grained benchmarks to demonstrate the effectiveness of TOAN compared with the state-of-the-art models.

show abstract

Attentional Kernel Encoding Networks for Fine-Grained Visual Categorization

Cited by 31 publications

References 43 publications

TOAN: Target-Oriented Alignment Network for Fine-Grained Image Categorization With Few Labeled Samples

TOAN: Target-Oriented Alignment Network for Fine-Grained Image Categorization With Few Labeled Samples

MeSIN: Multilevel Selective and Interactive Network for Medication Recommendation

TOAN: Target-Oriented Alignment Network for Fine-Grained Image Categorization with Few Labeled Samples

Contact Info

Product

Resources

About