Related papers: Multi Attribute Bias Mitigation via Representation…
Pre-trained language models encode undesirable social biases, which are further exacerbated in downstream use. To this end, we propose MABEL (a Method for Attenuating Gender Bias using Entailment Labels), an intermediate pre-training…
We present MBIS (Multivariate Bayesian Image Segmentation tool), a clustering tool based on the mixture of multivariate normal distributions model. MBIS supports multi-channel bias field correction based on a B-spline model. A second…
Since annotating medical images for segmentation tasks commonly incurs expensive costs, it is highly desirable to design an annotation-efficient method to alleviate the annotation burden. Recently, contrastive learning has exhibited a great…
There currently exist two main approaches to reproducing visual appearance using Machine Learning (ML): The first is training models that generalize over different instances of a problem, e.g., different images of a dataset. As one-shot…
Deep learning models suffer from catastrophic forgetting when learning new tasks incrementally. Incremental learning has been proposed to retain the knowledge of old classes while learning to identify new classes. A typical approach is to…
Vision-Language Models (VLMs) and generative image models have achieved remarkable performance across multimodal tasks, yet their robustness and fairness under input transformations remain insufficiently explored. This work investigates…
With the rapid emergence of multi-behavior learning in recommender systems, leveraging auxiliary user behaviors has proven effective for mitigating target-behavior data sparsity. Yet auxiliary behavior graphs frequently contain noisy or…
RGB-Infrared person re-identification (RGB-IR ReID) aims to associate people across disjoint RGB and IR camera views. Currently, state-of-the-art performance of RGB-IR ReID is not as impressive as that of conventional ReID. Much of that is…
We study the problem of distributed multi-view representation learning. In this problem, $K$ agents observe each one distinct, possibly statistically correlated, view and independently extracts from it a suitable representation in a manner…
Multi-label image recognition aims to predict a set of labels that present in an image. The key to deal with such problem is to mine the associations between image contents and labels, and further obtain the correct assignments between…
LiDAR bundle adjustment (BA) is an effective approach to reduce the drifts in pose estimation from the front-end. Existing works on LiDAR BA usually rely on predefined geometric features for landmark representation. This reliance restricts…
Multimodal learning, which integrates data from diverse sensory modes, plays a pivotal role in artificial intelligence. However, existing multimodal learning methods often struggle with challenges where some modalities appear more dominant…
Image/video data is usually represented with multiple visual features. Fusion of multi-source information for establishing the attributes has been widely recognized. Multi-feature visual recognition has recently received much attention in…
Machine learning models have been found to learn shortcuts -- unintended decision rules that are unable to generalize -- undermining models' reliability. Previous works address this problem under the tenuous assumption that only a single…
This paper strives to address image classifier bias, with a focus on both feature and label embedding spaces. Previous works have shown that spurious correlations from protected attributes, such as age, gender, or skin tone, can cause…
For many computer vision applications, such as image description and human identification, recognizing the visual attributes of humans is an essential yet challenging problem. Its challenges originate from its multi-label nature, the large…
Medical multimodal representation learning aims to integrate heterogeneous data into unified patient representations to support clinical outcome prediction. However, real-world medical datasets commonly contain systematic biases from…
Vision-language models (VLMs) are intensively used in many downstream tasks, including those requiring assessments of individuals appearing in the images. While VLMs perform well in simple single-person scenarios, in real-world…
Deep learning model effectiveness in classification tasks is often challenged by the quality and quantity of training data whenever they are affected by strong spurious correlations between specific attributes and target labels. This…
Partial label learning (PLL) is a complicated weakly supervised multi-classification task compounded by class imbalance. Currently, existing methods only rely on inter-class pseudo-labeling from inter-class features, often overlooking the…