Related papers: Extending the WILDS Benchmark for Unsupervised Ada…
Our goal is to improve reliability of Machine Learning (ML) systems deployed in the wild. ML models perform exceedingly well when test examples are similar to train examples. However, real-world applications are required to perform on any…
Semi-supervised learning (SSL) leverages both labeled and unlabeled data for training models when the labeled data is limited and the unlabeled data is vast. Frequently, the unlabeled data is more widely available than the labeled data,…
Modeling non-stationary data is a challenging problem in the field of continual learning, and data distribution shifts may result in negative consequences on the performance of a machine learning model. Classic learning tools are often…
Using unlabeled wild data containing both in-distribution (ID) and out-of-distribution (OOD) data to improve the safety and reliability of models has recently received increasing attention. Existing methods either design customized losses…
In the context of supervised statistical learning, it is typically assumed that the training set comes from the same distribution that draws the test samples. When this is not the case, the behavior of the learned model is unpredictable and…
Wildlife re-identification aims to match individuals of the same species across different observations. Current state-of-the-art (SOTA) models rely on class labels to train supervised models for individual classification. This dependence on…
Lifelong learning with deep neural networks is well-known to suffer from catastrophic forgetting: the performance on previous tasks drastically degrades when learning a new task. To alleviate this effect, we propose to leverage a large…
Unsupervised multi-domain adaptation plays a key role in transfer learning by leveraging acquired rich source information from multiple source domains to solve target task from an unlabeled target domain. However, multiple source domains…
Existing semi-supervised learning algorithms adopt pseudo-labeling and consistency regulation techniques to introduce supervision signals for unlabeled samples. To overcome the inherent limitation of threshold-based pseudo-labeling, prior…
Generalising deep networks to novel domains without manual labels is challenging to deep learning. This problem is intrinsically difficult due to unpredictable changing nature of imagery data distributions in novel domains. Pre-learned…
Training language models to learn from human instructions for zero-shot cross-task generalization has attracted much attention in NLP communities. Recently, instruction tuning (IT), which fine-tunes a pre-trained language model on a massive…
We develop a methodology for assessing the robustness of models to subpopulation shift---specifically, their ability to generalize to novel data subpopulations that were not observed during training. Our approach leverages the class…
To address semi-supervised learning from both labeled and unlabeled data, we present a novel meta-learning scheme. We particularly consider that labeled and unlabeled data share disjoint ground truth label sets, which can be seen tasks like…
Existing unsupervised domain adaptation methods aim to transfer knowledge from a label-rich source domain to an unlabeled target domain. However, obtaining labels for some source domains may be very expensive, making complete labeling as…
For semi-supervised learning with imbalance classes, the long-tailed distribution of data will increase the model prediction bias toward dominant classes, undermining performance on less frequent classes. Existing methods also face…
Identification and categorization of social media posts generated during disasters are crucial to reduce the sufferings of the affected people. However, lack of labeled data is a significant bottleneck in learning an effective…
When learning a mapping from an input space to an output space, the assumption that the sample distribution of the training data is the same as that of the test data is often violated. Unsupervised domain shift methods adapt the learned…
Semantic understanding of 3D point cloud relies on learning models with massively annotated data, which, in many cases, are expensive or difficult to collect. This has led to an emerging research interest in semi-supervised learning (SSL)…
Current long-tailed semi-supervised learning methods assume that labeled data exhibit a long-tailed distribution, and unlabeled data adhere to a typical predefined distribution (i.e., long-tailed, uniform, or inverse long-tailed). However,…
Unsupervised domain adaptation (UDA) for semantic segmentation aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Despite the effectiveness of self-training techniques in UDA, they struggle to learn each…