Related papers: Dynamic Adapter with Semantics Disentangling for C…

Vision-language models such as CLIP have shown great impact on diverse downstream tasks for zero-shot or label-free predictions. However, when it comes to low-level vision such as image restoration their performance deteriorates…

Extracting image semantics effectively and assigning corresponding labels to multiple objects or attributes for natural images is challenging due to the complex scene contents and confusing label dependencies. Recent works have focused on…

Vision-Language Pre-training (VLP) models like CLIP have significantly advanced Remote Sensing Image-Text Retrieval (RSITR). However, existing methods predominantly rely on coarse-grained global alignment, which often overlooks the dense,…

Code-switching (CS) refers to the phenomenon that languages switch within a speech signal and leads to language confusion for automatic speech recognition (ASR). This paper aims to address language confusion for improving CS-ASR from two…

In this paper, we present a direct adaptation strategy (ADAS), which aims to directly adapt a single model to multiple target domains in a semantic segmentation task without pretrained domain-specific models. To do so, we design a…

It is hard to generate an image at target view well for previous cross-view image translation methods that directly adopt a simple encoder-decoder or U-Net structure, especially for drastically different views and severe deformation cases.…

The Contrastive Language-Audio Pretraining (CLAP) model has demonstrated excellent performance in general audio description-related tasks, such as audio retrieval. However, in the emerging field of emotional speaking style description…

Speech signals are inherently complex as they encompass both global acoustic characteristics and local semantic information. However, in the task of target speech extraction, certain elements of global and local semantic information in the…

Scene change detection (SCD) is crucial for urban monitoring and navigation but remains challenging in real-world environments due to lighting variations, seasonal shifts, viewpoint differences, and complex urban layouts. Existing methods…

Domain adaptive object detection (DAOD) aims to generalize detectors trained on an annotated source domain to an unlabelled target domain. However, existing methods focus on reducing the domain bias of the detection backbone by inferring a…

Cognitive Language Processing (CLP), situated at the intersection of Natural Language Processing (NLP) and cognitive science, plays a progressively pivotal role in the domains of artificial intelligence, cognitive intelligence, and brain…

Automated grading of diabetic retinopathy (DR) faces several critical challenges: subtle inter-grade visual distinctions in fine-grained lesion patterns, distributional discrepancies induced by heterogeneous imaging devices and acquisition…

Ambiguity poses persistent challenges in natural language understanding for large language models (LLMs). To better understand how lexical ambiguity can be resolved through the visual domain, we develop an interpretable Visual Word Sense…

This paper proposes a novel pixel-level distribution regularization scheme (DRSL) for self-supervised domain adaptation of semantic segmentation. In a typical setting, the classification loss forces the semantic segmentation model to…

Inspired by the dual-stream theory of the human visual system (HVS) - where the ventral stream is responsible for object recognition and detail analysis, while the dorsal stream focuses on spatial relationships and motion perception - an…

Recent advances in using retrieval components over external knowledge sources have shown impressive results for a variety of downstream tasks in natural language processing. Here, we explore the use of unstructured external knowledge…

Exploiting cross-lingual resources is an effective way to compensate for data scarcity of low resource languages. Recently, a novel multilingual model fusion technique has been proposed where a model is trained to learn cross-lingual…

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…

Current general-purpose large language models (LLMs) commonly exhibit knowledge hallucination and insufficient domain-specific adaptability in domain-specific tasks, limiting their effectiveness in specialized question answering scenarios.…

Large Vision-Language Models (LVLMs) use their vision encoders to translate images into representations for downstream reasoning, but the encoders often underperform in domain-specific visual tasks such as medical image diagnosis or…