Search Results for author:
Found 17 papers, 2 papers with code
Test-time Adaptation Meets Image Enhancement: Improving Accuracy via Uncertainty-aware Logit Switching
We hypothesize that enhancing the input image reduces prediction's uncertainty and increase the accuracy of TTA methods.
Test-time Similarity Modification for Person Re-identification toward Temporal Distribution Shift
However, the uncertainty cannot be computed in the same way as classification in re-id since it is an open-set task, which does not share person labels between training and testing.
Adaptive Random Feature Regularization on Fine-tuning Deep Neural Networks
To this end, AdaRand minimizes the gap between feature vectors and random reference vectors that are sampled from class conditional Gaussian distributions.
On the Limitation of Diffusion Models for Synthesizing Training Datasets
Synthetic samples from diffusion models are promising for leveraging in training discriminative models as replications of real training datasets.
Generative Semi-supervised Learning with Meta-Optimized Synthetic Samples
Instead of using real unlabeled datasets, we propose an SSL method using synthetic datasets generated from generative foundation models trained on datasets containing millions of samples in diverse domains (e. g., ImageNet).
Adversarial Finetuning with Latent Representation Constraint to Mitigate Accuracy-Robustness Tradeoff
This paper addresses the tradeoff between standard accuracy on clean examples and robustness against adversarial examples in deep neural networks (DNNs).
Revisiting Permutation Symmetry for Merging Models between Different Datasets
We also show that merged models require datasets for merging in order to achieve a high accuracy.
One-vs-the-Rest Loss to Focus on Important Samples in Adversarial Training
This paper proposes a new loss function for adversarial training.
Meta-ticket: Finding optimal subnetworks for few-shot learning within randomly initialized neural networks
Few-shot learning for neural networks (NNs) is an important problem that aims to train NNs with a few data.
Covariance-aware Feature Alignment with Pre-computed Source Statistics for Test-time Adaptation to Multiple Image Corruptions
Test-time adaptation (TTA), which aims to adapt models without accessing the training dataset, is one of the settings that can address this problem.
Transfer Learning with Pre-trained Conditional Generative Models
To transfer source knowledge without these assumptions, we propose a transfer learning method that uses deep generative models and is composed of the following two stages: pseudo pre-training (PP) and pseudo semi-supervised learning (P-SSL).
Learning Robust Convolutional Neural Networks with Relevant Feature Focusing via Explanations
Under this type of distribution shift, CNNs learn to focus on features that are not task-relevant, such as backgrounds from the training data, and degrade their accuracy on the test data.
Pruning Randomly Initialized Neural Networks with Iterative Randomization
Pruning the weights of randomly initialized neural networks plays an important role in the context of lottery ticket hypothesis.
F-Drop&Match: GANs with a Dead Zone in the High-Frequency Domain
The key idea of F-Drop is to filter out unnecessary high-frequency components from the input images of the discriminators.
Constraining Logits by Bounded Function for Adversarial Robustness
We theoretically and empirically reveal that small logits by addition of a common activation function, e. g., hyperbolic tangent, do not improve adversarial robustness since input vectors of the function (pre-logit vectors) can have large norms.
Effective Data Augmentation with Multi-Domain Learning GANs
When trained on each target dataset reduced the samples to 5, 000 images, Domain Fusion achieves better classification accuracy than the data augmentation using fine-tuned GANs.
Image Enhanced Rotation Prediction for Self-Supervised Learning
The rotation prediction (Rotation) is a simple pretext-task for self-supervised learning (SSL), where models learn useful representations for target vision tasks by solving pretext-tasks.
