Search Results for author:
Found 19 papers, 11 papers with code
MAP: MAsk-Pruning for Source-Free Model Intellectual Property Protection
In this paper, we target a practical setting where only a well-trained source model is available and investigate how we can realize IP protection.
LEAD: Learning Decomposition for Source-free Universal Domain Adaptation
Besides, LEAD is also appealing in that it is complementary to most existing methods.
Ranked #1 on
Universal Domain Adaptation
on VisDA2017
AdaTreeFormer: Few Shot Domain Adaptation for Tree Counting from a Single High-Resolution Image
For the latter, an attention-to-adapt mechanism is introduced to distill relevant information from different domains while generating tree density maps; a hierarchical cross-domain feature alignment scheme is proposed that progressively aligns the features from the source and target domains.
FeaInfNet: Diagnosis in Medical Image with Feature-Driven Inference and Visual Explanations
Due to the unique multi-instance learning of medical images and the difficulty in identifying decision-making regions, many interpretability models that have been proposed still have problems of insufficient accuracy and interpretability in medical image disease diagnosis.
Mutually Guided Few-shot Learning for Relational Triple Extraction
Specifically, our method consists of an entity-guided relation proto-decoder to classify the relations firstly and a relation-guided entity proto-decoder to extract entities based on the classified relations.
Explainability of Speech Recognition Transformers via Gradient-based Attention Visualization
In addition, we demonstrate the utilization of visualization result in three ways: (1) We visualize attention with respect to connectionist temporal classification (CTC) loss to train an ASR model with adversarial attention erasing regularization, which effectively decreases the word error rate (WER) of the model and improves its generalization capability.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Hierarchical Dynamic Masks for Visual Explanation of Neural Networks
Saliency methods generating visual explanatory maps representing the importance of image pixels for model classification is a popular technique for explaining neural network decisions.
SCConv: Spatial and Channel Reconstruction Convolution for Feature Redundancy
The proposed SCConv consists of two units: spatial reconstruction unit (SRU) and channel reconstruction unit (CRU).
Decoupling Deep Learning for Interpretable Image Recognition
It decouples the inference and interpretation modules of a prototype-based network by avoiding the use of prototype activation to explain the network's decisions in order to simultaneously improve the accuracy and interpretability of the neural network.
MDM: Multiple Dynamic Masks for Visual Explanation of Neural Networks
We applied the MDM method to the interpretable neural networks ProtoPNet and XProtoNet, which improved the performance of model in the explainable prototype search.
Variational Transformer: A Framework Beyond the Trade-off between Accuracy and Diversity for Image Captioning
In this work, we will show that the inferior standard of accuracy draws from human annotations (leave-one-out) are not appropriate for machine-generated captions.
Revitalize Region Feature for Democratizing Video-Language Pre-training of Retrieval
Recent dominant methods for video-language pre-training (VLP) learn transferable representations from the raw pixels in an end-to-end manner to achieve advanced performance on downstream video-language retrieval.
Unsupervised Adaptive Semantic Segmentation with Local Lipschitz Constraint
In the first stage, we propose the local Lipschitzness regularization as the objective function to align different domains by exploiting intra-domain knowledge, which explores a promising direction for non-adversarial adaptive semantic segmentation.
Ask&Confirm: Active Detail Enriching for Cross-Modal Retrieval with Partial Query
However, the performance of existing methods suffers in real life since the user is likely to provide an incomplete description of an image, which often leads to results filled with false positives that fit the incomplete description.
Segmenting Medical MRI via Recurrent Decoding Cell
The encoder-decoder networks are commonly used in medical image segmentation due to their remarkable performance in hierarchical feature fusion.
Adaptive Routing Between Capsules
Capsule network is the most recent exciting advancement in the deep learning field and represents positional information by stacking features into vectors.
Learning Smooth Representation for Unsupervised Domain Adaptation
When constructing a deep end-to-end model, to ensure the effectiveness and stability of unsupervised domain adaptation, three critical factors are considered in our proposed optimization strategy, i. e., the sample amount of a target domain, dimension and batchsize of samples.
Ranked #1 on
Domain Adaptation
on SVNH-to-MNIST
Virtual Conditional Generative Adversarial Networks
All the generative paths share the same decoder network while in each path the decoder network is fed with a concatenation of a different pre-computed amplified one-hot vector and the inputted Gaussian noise.
Unsupervised Domain Adaptation with Adversarial Residual Transform Networks
Domain adaptation is widely used in learning problems lacking labels.
