Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleMarch 2024
ECLAD: Extracting Concepts with Local Aggregated Descriptors
AbstractConvolutional neural networks (CNNs) are increasingly being used in critical systems, where robustness and alignment are crucial. In this context, the field of explainable artificial intelligence has proposed the generation of high-level ...
Graphical abstractDisplay Omitted
Highlights- we propose the concept extraction and localization method ECLAD.
- Concepts extracted with ECLAD are closely related to the relevant features in models.
- ECLAD outperforms state of the art (ACE and ConceptShap) in our experiments.
- research-articleMarch 2024
CS-net: Conv-simpleformer network for agricultural image segmentation
Highlights- The proposed conv-simpleformer network (CS-Net) for agricultural image segmentation.
- Simple-attention block (SIAB) is designed to reduce the network's computational complexity.
- The comparison and ablation experiments verify the ...
Agricultural image segmentation needs to catch up to the development speed of deep learning, and the explosive computational overhead and limited high-quality labeled datasets are the main reasons preventing the application of Transformers to ...
- research-articleMarch 2024
ConvGeN: A convex space learning approach for deep-generative oversampling and imbalanced classification of small tabular datasets
AbstractOversampling is commonly used to improve classifier performance for small tabular imbalanced datasets. State-of-the-art linear interpolation approaches can be used to generate synthetic samples from the convex space of the minority class. ...
Highlights- Deep adversarial learning isn’t apt for oversampling on small tabular imbalanced data.
- ConvGeN learns appropriate convex coefficients from each minority data neighborhood.
- ConvGeN is the first deep learning architecture for ...
- research-articleMarch 2024
H-CapsNet: A capsule network for hierarchical image classification
AbstractIn this paper, we present H-CapsNet, a capsule network for hierarchical image classification. Our network makes use of the natural capacity of CapsNets (capsule networks) to capture hierarchical relationships. Thus, our network is such that each ...
Highlights- Propose H-CapsNet for hierarchical classification with dedicated capsules per level.
- Enforce hierarchical consistency with label-tree guided modified hinge-loss.
- Adjust training parameters dynamically to balance hierarchical level ...
- research-articleMarch 2024
Joint Feature Generation and Open-set Prototype Learning for generalized zero-shot open-set classification
AbstractIn generalized zero-shot classification, test samples can belong to either seen or unseen classes. However, in real-world situations, there may be many open-set samples in the test set where neither visual nor semantic representations of the ...
Highlights- A new problem of the generalized zero-shot open-set classification is proposed.
- Feature generation model and open-set prototype learning are unified for GZSOSC.
- A novel open-set prototype learning method is proposed.
- The ...
-
- research-articleMarch 2024
HairManip: High quality hair manipulation via hair element disentangling
AbstractHair editing is challenging due to the complexity and variety of hair materials and shapes. Existing methods employ reference images or user-painted masks to edit hair and have achieved promising results. However, discrepancies in color and shape ...
- research-articleMarch 2024
Topological safeguard for evasion attack interpreting the neural networks’ behavior
AbstractIn the last years, Deep Learning technology has been proposed in different fields, bringing many advances in each of them, but raising new threats in these solutions regarding cybersecurity. Those implemented models have brought several ...
Highlights- We present a novel evasion attack detector based on graph neural network technology.
- We define several attributes for the neurons to describe the topological information.
- We analyze the attributes’ contribution to the adversarial ...
- review-articleMarch 2024
Disturbance rejection with compensation on features
AbstractIn pattern recognition tasks, the information from system input is modeled through a series of nonlinear operations, which include but not limited to feature extraction, regression, and classification. Both theoretically and practically, these ...
Highlights- The pattern recognition process is inevitably subject to internal modeling error and external disturbance.
- The shortcomings of existing disturbance rejection technologies are summarized.
- The bottleneck of performances in those ...
- research-articleMarch 2024
A unified and efficient semi-supervised learning framework for stereo matching
AbstractRecently, stereo matching algorithms have made tremendous progress in terms of both accuracy and efficiency. However, it remains a great challenge to train a practical model due to the scarcity of ground truth disparity. In this paper, we propose ...
Highlights- We propose the first semi-supervised stereo matching framework.
- We integrate entropy minimization and consistent regularization for unlabeled data.
- We achieve 1st on KITTI 2012 benchmark and 4th on KITTI 2015 benchmark.
- research-articleMarch 2024
A lightweight unsupervised adversarial detector based on autoencoder and isolation forest
AbstractAlthough deep neural networks (DNNs) have performed well on many perceptual tasks, they are vulnerable to adversarial examples that are generated by adding slight but maliciously crafted perturbations to benign images. Adversarial detection is an ...
Highlights- We observe that adversarial detection is sensitive to the perturbation level.
- We train a shallow autoencoder to find two key features from adversarial examples.
- We propose a lightweight and unsupervised adversarial detector.
- research-articleMarch 2024
When IC meets text: Towards a rich annotated integrated circuit text dataset
AbstractAutomated Optical Inspection (AOI) is a process that uses cameras to autonomously scan printed circuit boards for quality control. Text is often printed on chip components, and it is crucial that this text is correctly recognized during AOI, as ...
Highlights- We present a large-scale ICText dataset labeled with multi-label quality attributes.
- We propose a two-stage AGCL loss to reweight the loss in a plug-and-play fashion.
- AGCL trains from easy to hard samples given low contrast, blurry,...
- research-articleMarch 2024
Scalable and accurate subsequence transform for time series classification
AbstractTime series classification using phase-independent subsequences called shapelets is one of the best approaches in the state of the art. This approach is especially characterized by its interpretable property and its fast prediction time. However, ...
Highlights- We introduce the core shapelet recognition task.
- We claim that time series classification by shapelets is a core shapelet recognition task.
- We propose the SAST method to successfully performs the core shapelet recognition task in O ...
- research-articleMarch 2024
Distance-based Weighted Transformer Network for image completion
AbstractThe challenge of image generation has been effectively modeled as a problem of structure priors or transformation. However, existing models have unsatisfactory performance in understanding the global input image structures because of particular ...
Highlights- Proposed a generative model for coherent image completion.
- Proposed Distance-based Weighted Transformer to encode global dependencies.
- Proposed a norm-regularization method to stabilize training.
- research-articleMarch 2024
Adversarial and focused training of abnormal videos for weakly-supervised anomaly detection
AbstractDue to the sparsity and scarcity of abnormal events, intra-video and inter-video data imbalance problems are fundamental issues for the weakly supervised video anomaly detection (WS-VAD) task. Many previous works have made great progress in the ...
Highlights- The present study aims to address a long-standing issue in weakly supervised video anomaly detection (WS-VAD), by identifying and highlighting the inter-video data imbalance problem.
- In order to address the issue of inter-video data ...
- research-articleMarch 2024
PWDformer: Deformable transformer for long-term series forecasting
AbstractLong-term forecasting is of paramount importance in numerous scenarios, including predicting future energy, water, and food consumption. For instance, extreme weather events and natural disasters can profoundly impact infrastructure operations ...
Highlights
- Empirical Evaluation of High-Performance Time Series Forecasting Techniques for Single and Multivariate Data.
- Our deformable mechanism-based module significantly enhances the performance of the model.
- Our position-sensitive ...
- research-articleMarch 2024
MSA-GCN: Multiscale Adaptive Graph Convolution Network for gait emotion recognition
AbstractGait emotion recognition plays a crucial role in the intelligent system. Most existing approaches identify emotions by focusing on local actions over time. However, some valuable observational facts that the effective distances of different ...
Highlights- Explore ways to express gait emotion.
- Introduce multiscale graphs to obtain a complete representation of emotions.
- Propose a framework for gait emotion recognition by extracting multi-scale emotional features.
- Achieve ...
- research-articleMarch 2024
JoyPose: Jointly learning evolutionary data augmentation and anatomy-aware global–local representation for 3D human pose estimation
AbstractVideo-based 3D human pose estimation is an important yet challenging task for many human-involved pattern recognition systems. Existing deep learning-based 3D human pose estimation methods are faced with the problems of lacking large-scale ...
Highlights- JoyPose simultaneously leverages 3D human pose augmentation and pose estimation.
- The distributions of crossover and mutation are learned for human pose augmentation.
- Pose estimation quality is utilized to guide the distribution ...
- research-articleMarch 2024
UniG-Encoder: A universal feature encoder for graph and hypergraph node classification
AbstractDespite the decent performance and fruitful applications of Graph Neural Networks (GNNs), Hypergraph Neural Networks (HGNNs), and their well-designed variants, on some commonly used benchmark graphs and hypergraphs, they are outperformed by even ...
Highlights- UniG-Encoder is proposed towards representation learning for graphs and hypergraphs.
- Heterophilic and homophilic graphs can both be addressed.
- The architecture is realized via an intuitive and interpretable projection matrix.
- ...
- research-articleMarch 2024
Learning conditional variational autoencoders with missing covariates
AbstractConditional variational autoencoders (CVAEs) are versatile deep latent variable models that extend the standard VAE framework by conditioning the generative model with auxiliary covariates. The original CVAE model assumes that the data samples ...
Graphical abstractDisplay Omitted
Highlights- An improved learning method for conditional VAEs and Gaussian process prior VAEs.
- The method is designed for non-temporal, temporal, and longitudinal data.
- Used an amortised variational distribution for learning missing auxiliary ...
- research-articleMarch 2024
Feature fusion method based on spiking neural convolutional network for edge detection
AbstractNSNP-type neuron is a new type of neuron model inspired by nonlinear spiking mechanisms in nonlinear spiking neural P systems. In order to address the loss problem of edge detail information in edge detection methods based on deep learning, we ...
Highlights- Nonlinear mechanism in spiking neurons inspires the NSNP-type neuron model.
- NSNP-like neuron model is used to construct a feature fusion module for fusing edge feature maps.
- This feature fusion module can effectively fuse the ...