相关论文: Confounder Identification-free Causal Visual Featu…

Dynamic facial expression recognition (DFER) faces significant challenges due to long-tailed category distributions and complexity of spatio-temporal feature modeling. While existing deep learning-based methods have improved DFER…

Clustering is a class of unsupervised learning methods that has been extensively applied and studied in computer vision. Little work has been done to adapt it to the end-to-end training of visual features on large scale datasets. In this…

We study the estimation of causal parameters when not all confounders are observed and instead negative controls are available. Recent work has shown how these can enable identification and efficient estimation via two so-called bridge…

Context-Aware Emotion Recognition (CAER) is a crucial and challenging task that aims to perceive the emotional states of the target person with contextual information. Recent approaches invariably focus on designing sophisticated…

The success of deep learning is partly attributed to the availability of massive data downloaded freely from the Internet. However, it also means that users' private data may be collected by commercial organizations without consent and used…

Machine learning practice is often impacted by confounders. Confounding can be particularly severe in remote digital health studies where the participants self-select to enter the study. While many different confounding adjustment…

Deep Metric Learning (DML) methods have been proven relevant for visual similarity learning. However, they sometimes lack generalization properties because they are trained often using an inappropriate sample selection strategy or due to…

Deep neural networks show great potential for automating various visual quality inspection tasks in manufacturing. However, their applicability is limited in more volatile scenarios, such as remanufacturing, where the inspected products and…

Vision-language models (VLMs) have significantly improved the generalization capabilities of robotic manipulation. However, VLM-based systems often suffer from a lack of robustness, leading to unpredictable errors, particularly in scenarios…

During the last years, deep learning trackers achieved stimulating results while bringing interesting ideas to solve the tracking problem. This progress is mainly due to the use of learned deep features obtained by training deep…

Image classification serves as the cornerstone of computer vision, traditionally achieved through discriminative models based on deep neural networks. Recent advancements have introduced classification methods derived from generative…

At the pinnacle of computational imaging is the co-optimization of camera and algorithm. This, however, is not the only form of computational imaging. In problems such as imaging through adverse weather, the bigger challenge is how to…

Counterfactual explanations (CFE) for deep image classifiers aim to reveal how minimal input changes lead to different model decisions, providing critical insights for model interpretation and improvement. However, existing CFE methods…

Edge classification, a crucial task for graph applications, remains relatively under-explored compared to link prediction. Current methods often overlook the potential causal influences of node features on edge features, leading to a loss…

Trajectory prediction is critical for autonomous driving vehicles. Most existing methods tend to model the correlation between history trajectory (input) and future trajectory (output). Since correlation is just a superficial description of…

In this study, we introduce Convolutional Transformer Neural Collaborative Filtering (CTNCF), a novel approach aimed at enhancing recommendation systems by effectively capturing high-order structural information in user-item interactions.…

Despite significant advances in clustering methods in recent years, the outcome of clustering of a natural image dataset is still unsatisfactory due to two important drawbacks. Firstly, clustering of images needs a good feature…

Federated learning has emerged as a promising approach for training machine learning models on decentralized data sources while preserving data privacy. However, challenges such as communication bottlenecks, heterogeneity of client devices,…

Classifier-free guidance (CFG) is a fundamental tool in modern diffusion models for text-guided generation. Although effective, CFG has notable drawbacks. For instance, DDIM with CFG lacks invertibility, complicating image editing;…

In the contemporary of deep learning, where models often grapple with the challenge of simultaneously achieving robustness against adversarial attacks and strong generalization capabilities, this study introduces an innovative Local Feature…