Search Results for author:
Found 11 papers, 6 papers with code
Towards Open-Set Test-Time Adaptation Utilizing the Wisdom of Crowds in Entropy Minimization
To be more specific, entropy minimization attempts to raise the confidence values of an individual sample's prediction, but individual confidence values may rise or fall due to the influence of signals from numerous other predictions (i. e., wisdom of crowds).
Improving Scene Text Recognition for Character-Level Long-Tailed Distribution
However, STR models show a large performance degradation on languages with a numerous number of characters (e. g., Chinese and Korean), especially on characters that rarely appear due to the long-tailed distribution of characters in such languages.
EcoTTA: Memory-Efficient Continual Test-time Adaptation via Self-distilled Regularization
Second, our novel self-distilled regularization controls the output of the meta networks not to deviate significantly from the output of the frozen original networks, thereby preserving well-trained knowledge from the source domain.
Deep Imbalanced Time-series Forecasting via Local Discrepancy Density
Based on our findings, we propose a reweighting framework that down-weights the losses incurred by abrupt changes and up-weights those by normal states.
DASH: Visual Analytics for Debiasing Image Classification via User-Driven Synthetic Data Augmentation
We call the unwanted correlations "data biases," and the visual features causing data biases "bias factors."
Improving Evaluation of Debiasing in Image Classification
Based on such issues, this paper 1) proposes an evaluation metric `Align-Conflict (AC) score' for the tuning criterion, 2) includes experimental settings with low bias severity and shows that they are yet to be explored, and 3) unifies the standardized experimental settings to promote fair comparisons between debiasing methods.
CAFA: Class-Aware Feature Alignment for Test-Time Adaptation
That is, a model does not have a chance to learn test data in a class-discriminative manner, which was feasible in other adaptation tasks (\textit{e. g.,} unsupervised domain adaptation) via supervised losses on the source data.
Revisiting the Importance of Amplifying Bias for Debiasing
$f_B$ is trained to focus on bias-aligned samples (i. e., overfitted to the bias) while $f_D$ is mainly trained with bias-conflicting samples by concentrating on samples which $f_B$ fails to learn, leading $f_D$ to be less susceptible to the dataset bias.
Improving Face Recognition with Large Age Gaps by Learning to Distinguish Children
Despite the unprecedented improvement of face recognition, existing face recognition models still show considerably low performances in determining whether a pair of child and adult images belong to the same identity.
Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene Segmentation
However, the distribution of max logits of each predicted class is significantly different from each other, which degrades the performance of identifying unexpected objects in urban-scene segmentation.
Ranked #4 on
Anomaly Detection
on Lost and Found
Learning Debiased Representation via Disentangled Feature Augmentation
To this end, our method learns the disentangled representation of (1) the intrinsic attributes (i. e., those inherently defining a certain class) and (2) bias attributes (i. e., peripheral attributes causing the bias), from a large number of bias-aligned samples, the bias attributes of which have strong correlation with the target variable.
