Related papers: Spread Spurious Attribute: Improving Worst-group A…
While neural networks have shown remarkable success on classification tasks in terms of average-case performance, they often fail to perform well on certain groups of the data. Such group information may be expensive to obtain; thus, recent…
Models prone to spurious correlations in training data often produce brittle predictions and introduce unintended biases. Addressing this challenge typically involves methods relying on prior knowledge and group annotation to remove…
This work proposes a robust Partial Domain Adaptation (PDA) framework that mitigates the negative transfer problem by incorporating a robust target-supervision strategy. It leverages ensemble learning and includes diverse, complementary…
Diagnostic and intervention methodologies for skill assessment of autism typically requires a clinician repetitively initiating several stimuli and recording the child's response. In this paper, we propose to automate the response…
This paper presents a model-agnostic ensemble approach for supervised learning. The proposed approach is based on a parametric version of Random Subspace, in which each base model is learned from a feature subset sampled according to a…
To avoid failures on out-of-distribution data, recent works have sought to extract features that have an invariant or stable relationship with the label across domains, discarding "spurious" or unstable features whose relationship with the…
Supervised machine learning often encounters concept drift, where the data distribution changes over time, degrading model performance. Existing drift detection methods focus on identifying these shifts but often overlook the challenge of…
We propose a method for generating spurious features by leveraging large-scale text-to-image diffusion models. Although the previous work detects spurious features in a large-scale dataset like ImageNet and introduces Spurious ImageNet, we…
Despite the remarkable performance of supervised medical image segmentation models, relying on a large amount of labeled data is impractical in real-world situations. Semi-supervised learning approaches aim to alleviate this challenge using…
Given an unlabeled dataset and an annotation budget, we study how to selectively label a fixed number of instances so that semi-supervised learning (SSL) on such a partially labeled dataset is most effective. We focus on selecting the right…
Designing learning-based no-reference (NR) video quality assessment (VQA) algorithms for camera-captured videos is cumbersome due to the requirement of a large number of human annotations of quality. In this work, we propose a…
In this work, we propose a novel complementary learning approach to enhance test-time adaptation (TTA), which has been proven to exhibit good performance on testing data with distribution shifts such as corruptions. In test-time adaptation…
Semi-Supervised Domain Adaptation (SSDA) is a recently emerging research topic that extends from the widely-investigated Unsupervised Domain Adaptation (UDA) by further having a few target samples labeled, i.e., the model is trained with…
Recent advances in semi-supervised object detection (SSOD) are largely driven by consistency-based pseudo-labeling methods for image classification tasks, producing pseudo labels as supervisory signals. However, when using pseudo labels,…
Self-training is a simple yet effective method within semi-supervised learning. The idea is to iteratively enhance training data by adding pseudo-labeled data. Its generalization performance heavily depends on the selection of these…
By inferring latent groups in the training data, recent works introduce invariant learning to the case where environment annotations are unavailable. Typically, learning group invariance under a majority/minority split is empirically shown…
Classification predicts classes of objects using the knowledge learned during the training phase. This process requires learning from labeled samples. However, the labeled samples usually limited. Annotation process is annoying, tedious,…
Recent domain adaptation methods have demonstrated impressive improvement on unsupervised domain adaptation problems. However, in the semi-supervised domain adaptation (SSDA) setting where the target domain has a few labeled instances…
Semi-Supervised Learning (SSL) has become a preferred paradigm in many deep learning tasks, which reduces the need for human labor. Previous studies primarily focus on effectively utilising the labelled and unlabeled data to improve…
Semi-supervised learning is attracting blooming attention, due to its success in combining unlabeled data. To mitigate potentially incorrect pseudo labels, recent frameworks mostly set a fixed confidence threshold to discard uncertain…