Related papers: Counterfactual Co-occurring Learning for Bias Miti…

Weakly supervised temporal action localization (WSTAL) aims to localize actions in untrimmed videos using video-level labels. Despite recent advances, existing approaches mainly follow a localization-by-classification pipeline, generally…

The backbone of traditional CNN classifier is generally considered as a feature extractor, followed by a linear layer which performs the classification. We propose a novel loss function, termed as CAM-loss, to constrain the embedded feature…

Quantifying and evaluating image complexity can be instrumental in enhancing the performance of various computer vision tasks. Supervised learning can effectively learn image complexity features from well-annotated datasets. However,…

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…

Self-Supervised Contrastive Learning has proven effective in deriving high-quality representations from unlabeled data. However, a major challenge that hinders both unimodal and multimodal contrastive learning is feature suppression, a…

Attribute bias in federated learning (FL) typically leads local models to optimize inconsistently due to the learning of non-causal associations, resulting degraded performance. Existing methods either use data augmentation for increasing…

Weakly supervised object localization aims to find a target object region in a given image with only weak supervision, such as image-level labels. Most existing methods use a class activation map (CAM) to generate a localization map;…

Learning visual representation of high quality is essential for image classification. Recently, a series of contrastive representation learning methods have achieved preeminent success. Particularly, SupCon outperformed the dominant methods…

Variational autoencoders (VAEs) and other generative methods have garnered growing interest not just for their generative properties but also for the ability to dis-entangle a low-dimensional latent variable space. However, few existing…

Understanding predictions made by deep neural networks is notoriously difficult, but also crucial to their dissemination. As all machine learning based methods, they are as good as their training data, and can also capture unwanted biases.…

Although large vision-language models (LVLMs) have demonstrated remarkable capabilities, they are prone to hallucinations in multi-image tasks. We attribute this issue to limitations in existing attention mechanisms and insufficient…

This paper considers contrastive training for cross-modal 0-shot transfer wherein a pre-trained model in one modality is used for representation learning in another domain using pairwise data. The learnt models in the latter domain can then…

Biases in machine learning pose significant challenges, particularly when models amplify disparities that affect disadvantaged groups. Traditional bias mitigation techniques often lead to a {\itshape leveling-down effect}, whereby improving…

Real-scene image super-resolution aims to restore real-world low-resolution images into their high-quality versions. A typical RealSR framework usually includes the optimization of multiple criteria which are designed for different image…

Personalized recommendation is widely used in the web applications, and graph contrastive learning (GCL) has gradually become a dominant approach in recommender systems, primarily due to its ability to extract self-supervised signals from…

We study the collaborative image retrieval problem at the wireless edge, where multiple edge devices capture images of the same object, which are then used jointly to retrieve similar images at the edge server over a shared multiple access…

Weakly supervised object localization (WSOL) focuses on localizing objects only with the supervision of image-level classification masks. Most previous WSOL methods follow the classification activation map (CAM) that localizes objects based…

Conditional contrastive learning frameworks consider the conditional sampling procedure that constructs positive or negative data pairs conditioned on specific variables. Fair contrastive learning constructs negative pairs, for example,…

Place recognition is an essential and challenging task in loop closing and global localization for robotics and autonomous driving applications. Benefiting from the recent advances in deep learning techniques, the performance of LiDAR place…

Modern self-supervised learning algorithms typically enforce persistency of instance representations across views. While being very effective on learning holistic image and video representations, such an objective becomes sub-optimal for…