Related papers: Multi Attribute Bias Mitigation via Representation…

Lightweight vision networks have witnessed remarkable progress in recent years, yet achieving a satisfactory balance among parameter scale, computational overhead, and task performance remains difficult. Although many existing lightweight…

When a subgroup is identified from the data, it must be evaluated in a replicable way. The usual in-sample approach, which evaluates the post-hoc identified subgroup as predefined, might suffer from selection bias. This issue of in-sample…

Various multi-instance learning (MIL) based approaches have been developed and successfully applied to whole-slide pathological images (WSI). Existing MIL methods emphasize the importance of feature aggregators, but largely neglect the…

Recognizing implicit visual and textual patterns is essential in many real-world applications of modern AI. However, tackling long-tail pattern recognition tasks remains challenging for current pre-trained foundation models such as LLMs and…

Dataset bias is a well-known problem in the field of computer vision. The presence of implicit bias in any image collection hinders a model trained and validated on a particular dataset to yield similar accuracies when tested on other…

The task of multi-label image recognition is to predict a set of object labels that present in an image. As objects normally co-occur in an image, it is desirable to model the label dependencies to improve the recognition performance. To…

Meta-learning has recently been an emerging data-efficient learning technique for various medical imaging operations and has helped advance contemporary deep learning models. Furthermore, meta-learning enhances the knowledge generalization…

Generating high fidelity identity-preserving faces with different facial attributes has a wide range of applications. Although a number of generative models have been developed to tackle this problem, there is still much room for further…

Neural networks produced by standard training are known to suffer from poor accuracy on rare subgroups despite achieving high accuracy on average, due to the correlations between certain spurious features and labels. Previous approaches…

Mitigating biases in computer vision models is an essential step towards the trustworthiness of artificial intelligence models. Existing bias mitigation methods focus on a small set of predefined biases, limiting their applicability in…

Image matching is a fundamental computer vision problem. While learning-based methods achieve state-of-the-art performance on existing benchmarks, they generalize poorly to in-the-wild images. Such methods typically need to train separate…

In class-incremental learning (CIL) scenarios, the phenomenon of catastrophic forgetting caused by the classifier's bias towards the current task has long posed a significant challenge. It is mainly caused by the characteristic of…

Mitigating bias in machine learning models is a critical endeavor for ensuring fairness and equity. In this paper, we propose a novel approach to address bias by leveraging pixel image attributions to identify and regularize regions of…

Multi-instance multi-label (MIML) learning is widely applicated in numerous domains, such as the image classification where one image contains multiple instances correlated with multiple logic labels simultaneously. The related labels in…

Multi-view evidential learning aims to integrate information from multiple views to improve prediction performance and provide trustworthy uncertainty esitimation. Most previous methods assume that view-specific evidence learning is…

In this paper, the problem of multi-view embedding from different visual cues and modalities is considered. We propose a unified solution for subspace learning methods using the Rayleigh quotient, which is extensible for multiple views,…

This paper presents a study on semi-supervised learning to solve the visual attribute prediction problem. In many applications of vision algorithms, the precise recognition of visual attributes of objects is important but still challenging.…

Graph Neural Networks (GNNs) have shown remarkable performance across various domains, yet they often struggle with model bias, particularly in the presence of class imbalance. This bias can lead to suboptimal performance and unfair…

Human perception integrates multiple modalities, such as vision, hearing, and language, into a unified understanding of the surrounding reality. While recent multimodal models have achieved significant progress by aligning pairs of…

Image clustering aims to partition unlabeled image datasets into distinct groups. A core aspect of this task is constructing and leveraging prior knowledge to guide the clustering process. Recent approaches introduce semantic descriptions…