Search Results for author:
Found 16 papers, 6 papers with code
Rewarded meta-pruning: Meta Learning with Rewards for Channel Pruning
Convolutional Neural Networks (CNNs) have a large number of parameters and take significantly large hardware resources to compute, so edge devices struggle to run high-level networks.
Fair Comparison between Efficient Attentions
Transformers have been successfully used in various fields and are becoming the standard tools in computer vision.
Rethinking Query, Key, and Value Embedding in Vision Transformer under Tiny Model Constraints
The proposed method achieved $71. 4\%$ with a few parameters (of $3. 1M$) on the ImageNet-1k dataset compared to that required by the original transformer model of XCiT-N12 ($69. 9\%$).
Training Domain-invariant Object Detector Faster with Feature Replay and Slow Learner
In deep learning-based object detection on remote sensing domain, nuisance factors, which affect observed variables while not affecting predictor variables, often matters because they cause domain changes.
Extending Contrastive Learning to Unsupervised Coreset Selection
Self-supervised contrastive learning offers a means of learning informative features from a pool of unlabeled data.
FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptation
However, most of the studies were based on direct adaptation from the source domain to the target domain and have suffered from large domain discrepancies.
Ranked #3 on
Domain Adaptation
on Office-31
Development of Fast Refinement Detectors on AI Edge Platforms
With the improvements in the object detection networks, several variations of object detection networks have been achieved impressive performance.
Co-occurrence matrix analysis-based semi-supervised training for object detection
We used an MS-COCO detection dataset to verify the performance of the proposed SSL method and deformable neural networks (D-ConvNets) as an object detector for basic training.
Less-forgetful Learning for Domain Expansion in Deep Neural Networks
Expanding the domain that deep neural network has already learned without accessing old domain data is a challenging task because deep neural networks forget previously learned information when learning new data from a new domain.
Can Deep Neural Networks Match the Related Objects?: A Survey on ImageNet-trained Classification Models
To verify how DNNs understand the relatedness between object classes, we conducted experiments on the image database provided in cognitive psychology.
End-to-End Pedestrian Collision Warning System based on a Convolutional Neural Network with Semantic Segmentation
Traditional pedestrian collision warning systems sometimes raise alarms even when there is no danger (e. g., when all pedestrians are walking on the sidewalk).
Less-forgetting Learning in Deep Neural Networks
Surprisingly, our method is very effective to forget less of the information in the source domain, and we show the effectiveness of our method using several experiments.
Joint Fine-Tuning in Deep Neural Networks for Facial Expression Recognition
Furthermore, we show that our new integration method gives more accurate results than traditional methods, such as a weighted summation and a feature concatenation method.
Rotating Your Face Using Multi-Task Deep Neural Network
This paper proposes a new deep architecture based on a novel type of multitask learning, which can achieve superior performance in rotating to a target-pose face image from an arbitrary pose and illumination image while preserving identity.
Deep Temporal Appearance-Geometry Network for Facial Expression Recognition
Furthermore, one of the main contributions of this paper is that our deep network catches the facial action points automatically.
Rigid Motion Segmentation using Randomized Voting
For evaluation of our algorithm, Hopkins 155 dataset, which is a representative test set for rigid motion segmentation, is adopted; it consists of two and three rigid motions.
