Related papers: Pseudo-Label Enhanced Prototypical Contrastive Lea…

Identifying influential nodes in complex networks is a fundamental task in network analysis with wide-ranging applications across domains. While deep learning has advanced node influence detection, existing supervised approaches remain…

Recent open-vocabulary detection methods aim to detect novel objects by distilling knowledge from vision-language models (VLMs) trained on a vast amount of image-text pairs. To improve the effectiveness of these methods, researchers have…

Intent classification (IC) plays an important role in task-oriented dialogue systems. However, IC models often generalize poorly when training without sufficient annotated examples for each user intent. We propose a novel pre-training…

Partial label learning (PLL) is an important problem that allows each training example to be labeled with a coarse candidate set, which well suits many real-world data annotation scenarios with label ambiguity. Despite the promise, the…

The clustering-based unsupervised relation discovery method has gradually become one of the important methods of open relation extraction (OpenRE). However, high-dimensional vectors can encode complex linguistic information which leads to…

Fine-tuning vision-language models (VLMs) with abundant unlabeled data recently has attracted increasing attention. Existing methods that resort to the pseudolabeling strategy would suffer from heavily incorrect hard pseudolabels when VLMs…

This work aims to adapt large-scale pre-trained vision-language models, such as contrastive language-image pretraining (CLIP), to enhance the performance of object reidentification (Re-ID) across various supervision settings. Although…

Despite the great progress of unsupervised domain adaptation (UDA) with the deep neural networks, current UDA models are opaque and cannot provide promising explanations, limiting their applications in the scenarios that require safe and…

Vision-language models (VLMs) such as CLIP exhibit strong Out-of-distribution (OOD) detection capabilities by aligning visual and textual representations. Recent CLIP-based test-time adaptation methods further improve detection performance…

Out-of-Domain (OOD) intent detection is important for practical dialog systems. To alleviate the issue of lacking OOD training samples, some works propose synthesizing pseudo OOD samples and directly assigning one-hot OOD labels to these…

Contrastive Language Image Pretraining (CLIP) has received widespread attention, since its learned representations can be transferred well to various downstream tasks. During the training process of the CLIP model, the InfoNCE objective…

Visual recognition is recently learned via either supervised learning on human-annotated image-label data or language-image contrastive learning with webly-crawled image-text pairs. While supervised learning may result in a more…

We focus on a relatively unexplored learning paradigm known as {\em Online Unsupervised Continual Learning} (O-UCL), where an agent receives a non-stationary, unlabeled data stream and progressively learns to identify an increasing number…

Accurately modeling users' evolving preferences from sequential interactions remains a central challenge in recommender systems. Recent studies emphasize the importance of capturing multiple latent intents underlying user behaviors.…

Significant advancements have been made in single label incremental learning (SLCIL),yet the more practical and challenging multi label class incremental learning (MLCIL) remains understudied. Recently,visual language models such as CLIP…

The success of deep learning heavily depends on the availability of large labeled training sets. However, it is hard to get large labeled datasets in medical image domain because of the strict privacy concern and costly labeling efforts.…

The representation learning problem in the oil & gas industry aims to construct a model that provides a representation based on logging data for a well interval. Previous attempts are mainly supervised and focus on similarity task, which…

Building the Natural Language Understanding (NLU) modules of task-oriented Spoken Dialogue Systems (SDS) involves a definition of intents and entities, collection of task-relevant data, annotating the data with intents and entities, and…

Partial-label learning (PLL) relies on a key assumption that the true label of each training example must be in the candidate label set. This restrictive assumption may be violated in complex real-world scenarios, and thus the true label of…

Intent learning, which aims to learn users' intents for user understanding and item recommendation, has become a hot research spot in recent years. However, existing methods suffer from complex and cumbersome alternating optimization,…