Related papers: Confounder Identification-free Causal Visual Featu…

While numerous machine unlearning (MU) methods have recently been developed with promising results in erasing the influence of forgotten data, classes, or concepts, they are also highly vulnerable-for example, simple fine-tuning can…

Deep neural networks (DNNs) often struggle with out-of-distribution data, limiting their reliability in diverse realworld applications. To address this issue, domain generalization methods have been developed to learn domain-invariant…

Attention module does not always help deep models learn causal features that are robust in any confounding context, e.g., a foreground object feature is invariant to different backgrounds. This is because the confounders trick the attention…

Recent successes of deep learning-based recognition rely on maintaining the content related to the main-task label. However, how to explicitly dispel the noisy signals for better generalization in a controllable manner remains an open…

An important problem in causal inference is to break down the total effect of a treatment on an outcome into different causal pathways and to quantify the causal effect in each pathway. For instance, in causal fairness, the total effect of…

Neural networks are prone to catastrophic forgetting when trained incrementally on different tasks. Popular incremental learning methods mitigate such forgetting by retaining a subset of previously seen samples and replaying them during the…

Domain shift in histopathology, often caused by differences in acquisition processes or data sources, poses a major challenge to the generalization ability of deep learning models. Existing methods primarily rely on modeling statistical…

Multi-view unsupervised feature selection (MUFS) has recently received increasing attention for its promising ability in dimensionality reduction on multi-view unlabeled data. Existing MUFS methods typically select discriminative features…

Discriminative Correlation Filters (DCF) have demonstrated excellent performance for visual object tracking. The key to their success is the ability to efficiently exploit available negative data by including all shifted versions of a…

We uncover an ever-overlooked deficiency in the prevailing Few-Shot Learning (FSL) methods: the pre-trained knowledge is indeed a confounder that limits the performance. This finding is rooted from our causal assumption: a Structural Causal…

Causal inference has become a powerful tool to handle the out-of-distribution (OOD) generalization problem, which aims to extract the invariant features. However, conventional methods apply causal learners from multiple data splits, which…

Personalized learner modeling using cognitive diagnosis (CD), which aims to model learners' cognitive states by diagnosing learner traits from behavioral data, is a fundamental yet significant task in many web learning services. Existing…

Multi-view clustering (MVC) aims to explore the common clustering structure across multiple views. Many existing MVC methods heavily rely on the assumption of view consistency, where alignments for corresponding samples across different…

The excellent generalization, contextual learning, and emergence abilities in the pre-trained large models (PLMs) handle specific tasks without direct training data, making them the better foundation models in the adversarial domain…

This paper introduces a novel perspective about error in machine learning and proposes inverse feature learning (IFL) as a representation learning approach that learns a set of high-level features based on the representation of error for…

We propose a general framework for causal Imitation Learning (IL) with hidden confounders, which subsumes several existing settings. Our framework accounts for two types of hidden confounders: (a) variables observed by the expert but not by…

Humans have a remarkable ability to quickly and effectively learn new concepts in a continuous manner without forgetting old knowledge. Though deep learning has made tremendous successes on various computer vision tasks, it faces challenges…

Multi-modal fusion has emerged as a promising paradigm for accurate 3D object detection. However, performance degrades substantially when deployed in target domains different from training. In this work, focusing on dual-branch…

Learning by integrating multiple heterogeneous data sources is a common requirement in many tasks. Collective Matrix Factorization (CMF) is a technique to learn shared latent representations from arbitrary collections of matrices. It can be…

Contrastive learning (CL)-based self-supervised learning models learn visual representations in a pairwise manner. Although the prevailing CL model has achieved great progress, in this paper, we uncover an ever-overlooked phenomenon: When…