Search Results for author:
Found 13 papers, 7 papers with code
Elucidating the Design Space of Dataset Condensation
Dataset condensation, a concept within data-centric learning, efficiently transfers critical attributes from an original dataset to a synthetic version, maintaining both diversity and realism.
Self-supervised Dataset Distillation: A Good Compression Is All You Need
In this work, we consider addressing this task through the new lens of model informativeness in the compression stage on the original dataset pretraining.
Your Diffusion Model is Secretly a Certifiably Robust Classifier
Diffusion models are recently employed as generative classifiers for robust classification.
Precise Knowledge Transfer via Flow Matching
We name this framework Knowledge Transfer with Flow Matching (FM-KT), which can be integrated with a metric-based distillation method with any form (\textit{e. g.} vanilla KD, DKD, PKD and DIST) and a meta-encoder with any available architecture (\textit{e. g.} CNN, MLP and Transformer).
Rethinking Centered Kernel Alignment in Knowledge Distillation
This paper first provides a theoretical perspective to illustrate the effectiveness of CKA, which decouples CKA to the upper bound of Maximum Mean Discrepancy~(MMD) and a constant term.
Generalized Large-Scale Data Condensation via Various Backbone and Statistical Matching
We call this perspective "generalized matching" and propose Generalized Various Backbone and Statistical Matching (G-VBSM) in this work, which aims to create a synthetic dataset with densities, ensuring consistency with the complete dataset across various backbones, layers, and statistics.
Catch-Up Distillation: You Only Need to Train Once for Accelerating Sampling
On CIFAR-10, we obtain a FID of 2. 80 by sampling in 15 steps under one-session training and the new state-of-the-art FID of 3. 37 by sampling in one step with additional training.
Black-box Source-free Domain Adaptation via Two-stage Knowledge Distillation
In Stage \uppercase\expandafter{\romannumeral1}, we train the target model from scratch with soft pseudo-labels generated by the source model in a knowledge distillation manner.
PELE scores: Pelvic X-ray Landmark Detection by Pelvis Extraction and Enhancement
The pelvis, the lower part of the trunk, supports and balances the trunk.
DiffuseExpand: Expanding dataset for 2D medical image segmentation using diffusion models
Based on this insight, we propose an approach called DiffuseExpand for expanding datasets for 2D medical image segmentation using DPM, which first samples a variety of masks from Gaussian noise to ensure the diversity, and then synthesizes images to ensure the alignment of images and masks.
AIIR-MIX: Multi-Agent Reinforcement Learning Meets Attention Individual Intrinsic Reward Mixing Network
The results show that AIIR-MIX can dynamically assign each agent a real-time intrinsic reward in accordance with their actual contribution.
Teaching What You Should Teach: A Data-Based Distillation Method
To be specific, we design a neural network-based data augmentation module with priori bias, which assists in finding what meets the teacher's strengths but the student's weaknesses, by learning magnitudes and probabilities to generate suitable data samples.
Bootstrap Generalization Ability from Loss Landscape Perspective
Domain generalization aims to learn a model that can generalize well on the unseen test dataset, i. e., out-of-distribution data, which has different distribution from the training dataset.
