相关论文: MOSAIC: Masked Objective with Selective Adaptation…

While some powerful neural network architectures (e.g., Transformer, Graph Neural Networks) have achieved improved performance in sequential recommendation with high-order item dependency modeling, they may suffer from poor representation…

Multi-source unsupervised domain adaptation~(MSDA) aims at adapting models trained on multiple labeled source domains to an unlabeled target domain. In this paper, we propose a novel multi-source domain adaptation framework based on…

Large-scale deep learning models for physical AI applications depend on diverse training data collection efforts. These models and correspondingly, the training data, must address different evaluation criteria necessary for the models to be…

Vision-Language Models (VLMs) are powerful but remain vulnerable to multimodal jailbreak attacks. Existing attacks mainly rely on either explicit visual prompt attacks or gradient-based adversarial optimization. While the former is easier…

A general-purpose robot should be able to master a wide range of tasks and quickly learn a novel one by leveraging past experiences. One-shot imitation learning (OSIL) approaches this goal by training an agent with (pairs of) expert…

The problem of representative selection amounts to sampling few informative exemplars from large datasets. This paper presents MOSAIC, a novel representative selection approach from high-dimensional data that may exhibit non-linear…

The network trained for domain adaptation is prone to bias toward the easy-to-transfer classes. Since the ground truth label on the target domain is unavailable during training, the bias problem leads to skewed predictions, forgetting to…

Foundational vision models, such as the Segment Anything Model (SAM), have achieved significant breakthroughs through extensive pre-training on large-scale visual datasets. Despite their general success, these models may fall short in…

Reviews are central to how travelers evaluate products on online marketplaces, yet existing summarization research often emphasizes end-to-end quality while overlooking benchmark reliability and the practical utility of granular insights.…

As a pioneering work, PointContrast conducts unsupervised 3D representation learning via leveraging contrastive learning over raw RGB-D frames and proves its effectiveness on various downstream tasks. However, the trend of large-scale…

Medical image segmentation, or computing voxelwise semantic masks, is a fundamental yet challenging task to compute a voxel-level semantic mask. To increase the ability of encoder-decoder neural networks to perform this task across large…

Semantic segmentation of crops and weeds is crucial for site-specific farm management; however, most existing methods depend on labor intensive pixel-level annotations. A further challenge arises when models trained on one field (source…

Continual domain shift poses a significant challenge in real-world applications, particularly in situations where labeled data is not available for new domains. The challenge of acquiring knowledge in this problem setting is referred to as…

Recent advancements in machine learning (ML), natural language processing (NLP), and foundational models have shown promise for real-life applications in critical, albeit compute-constrainted fields like healthcare. In such areas, combining…

Partially-supervised instance segmentation is a task which requests segmenting objects from novel unseen categories via learning on limited seen categories with annotated masks thus eliminating demands of heavy annotation burden. The key to…

Agentic AI aims to create systems that set their own goals, adapt proactively to change, and refine behavior through continuous experience. Recent advances suggest that, when facing multiple and unforeseen tasks, agents could benefit from…

The task of open-set domain generalization (OSDG) involves recognizing novel classes within unseen domains, which becomes more challenging with multiple modalities as input. Existing works have only addressed unimodal OSDG within the…

As a successful approach to self-supervised learning, contrastive learning aims to learn invariant information shared among distortions of the input sample. While contrastive learning has yielded continuous advancements in sampling strategy…

This study introduces an efficacious approach, Masked Collaborative Contrast (MCC), to highlight semantic regions in weakly supervised semantic segmentation. MCC adroitly draws inspiration from masked image modeling and contrastive learning…

We propose a visual-linguistic representation learning approach within a self-supervised learning framework by introducing a new operation, loss, and data augmentation strategy. First, we generate diverse features for the image-text…