Search Results for author:
Found 17 papers, 8 papers with code
Unraveling Batch Normalization for Realistic Test-Time Adaptation
While recent test-time adaptations exhibit efficacy by adjusting batch normalization to narrow domain disparities, their effectiveness diminishes with realistic mini-batches due to inaccurate target estimation.
Polar-Doc: One-Stage Document Dewarping with Multi-Scope Constraints under Polar Representation
While Cartesian coordinates are typically leveraged by state-of-the-art approaches to learn a group of deformation control points, such representation is not efficient for dewarping model to learn the deformation information.
Generating Valid and Natural Adversarial Examples with Large Language Models
Deep learning-based natural language processing (NLP) models, particularly pre-trained language models (PLMs), have been revealed to be vulnerable to adversarial attacks.
Context Does Matter: End-to-end Panoptic Narrative Grounding with Deformable Attention Refined Matching Network
The current state-of-the-art methods first refine the representation of phrase by aggregating the most similar $k$ image pixels, and then match the refined text representations with the pixels of the image feature map to generate segmentation results.
MathAttack: Attacking Large Language Models Towards Math Solving Ability
Instead of attacking prompts in the use of LLMs, we propose a MathAttack model to attack MWP samples which are closer to the essence of security in solving math problems.
Solving Math Word Problem with Problem Type Classification
Firstly, We propose a problem type classifier that combines the strengths of the tree-based solver and the LLM solver.
Learning by Analogy: Diverse Questions Generation in Math Word Problem
We then feed them to a question generator together with the scenario to obtain the corresponding diverse questions, forming a new MWP with a variety of questions and equations.
Learngene: Inheriting Condensed Knowledge from the Ancestry Model to Descendant Models
(i) Accumulating: the knowledge is accumulated during the continuous learning of an ancestry model.
Rethinking Data Augmentation for Single-source Domain Generalization in Medical Image Segmentation
Single-source domain generalization (SDG) in medical image segmentation is a challenging yet essential task as domain shifts are quite common among clinical image datasets.
SSD: Towards Better Text-Image Consistency Metric in Text-to-Image Generation
Generating consistent and high-quality images from given texts is essential for visual-language understanding.
Mind The Gap: Alleviating Local Imbalance for Unsupervised Cross-Modality Medical Image Segmentation
This combination of global and local alignment can precisely localize the crucial regions in segmentation target while preserving the overall semantic consistency.
Unified Question Generation with Continual Lifelong Learning
To solve the problems, we propose a model named Unified-QG based on lifelong learning techniques, which can continually learn QG tasks across different datasets and formats.
Perturbation Diversity Certificates Robust Generalisation
It is possibly due to the fact that the conventional adversarial training methods generate adversarial perturbations usually in a supervised way, so that the adversarial samples are highly biased towards the decision boundary, resulting in an inhomogeneous data distribution.
Improving Model Robustness with Latent Distribution Locally and Globally
The proposed adversarial training with latent distribution (ATLD) method defends against adversarial attacks by crafting LMAEs with the latent manifold in an unsupervised manner.
Learngene: From Open-World to Your Learning Task
Moreover, the learngene, i. e., the gene for learning initialization rules of the target model, is proposed to inherit the meta-knowledge from the collective model and reconstruct a lightweight individual model on the target task.
Gradient Distribution Alignment Certificates Better Adversarial Domain Adaptation
In particular, we show that the distribution discrepancy can be reduced by constraining feature gradients of two domains to have similar distributions.
Generative Adversarial Classifier for Handwriting Characters Super-Resolution
Generative Adversarial Networks (GAN) receive great attentions recently due to its excellent performance in image generation, transformation, and super-resolution.
