Related papers: LoFi: Location-Aware Fine-Grained Representation L…
Large Vision Language Models (LVLMs) have made remarkable progress, enabling sophisticated vision-language interaction and dialogue applications. However, existing benchmarks primarily focus on reasoning tasks, often neglecting fine-grained…
Parameter-efficient fine-tuning (PEFT) has become a practical route for adapting large language models to downstream tasks, with LoRA-style methods being particularly attractive because they are inexpensive to train and easy to deploy. Most…
Given a language expression, referring remote sensing image segmentation (RRSIS) aims to identify ground objects and assign pixel-wise labels within the imagery. The one of key challenges for this task is to capture discriminative…
Contrastive learning has been proved to be a promising technique for image-level representation learning from unlabeled data. Many existing works have demonstrated improved results by applying contrastive learning in classification and…
Motivation: Traditional image attribution methods struggle to satisfactorily explain predictions of neural networks. Prediction explanation is important, especially in medical imaging, for avoiding the unintended consequences of deploying…
Large Vision Language Models (LVLMs) have achieved remarkable success in a range of downstream tasks that require multimodal interaction, but their capabilities come with substantial computational and memory overhead, which hinders…
Language model pre-training based on large corpora has achieved tremendous success in terms of constructing enriched contextual representations and has led to significant performance gains on a diverse range of Natural Language…
Recently, multi-modal vision-language foundation models have gained significant attention in the medical field. While these models offer great opportunities, they still face crucial challenges, such as the requirement for fine-grained…
Vision-language models (VLMs) have recently shown remarkable zero-shot performance in medical image understanding, yet their grounding ability, the extent to which textual concepts align with visual evidence, remains underexplored. In the…
Semantic part localization can facilitate fine-grained categorization by explicitly isolating subtle appearance differences associated with specific object parts. Methods for pose-normalized representations have been proposed, but generally…
Large Vision-Language Models (LVLMs) have demonstrated proficiency in tackling a variety of visual-language tasks. However, current LVLMs suffer from misalignment between text and image modalities which causes three kinds of hallucination…
Recently, multimodal deep learning, which integrates histopathology slides and molecular biomarkers, has achieved a promising performance in glioma grading. Despite great progress, due to the intra-modality complexity and inter-modality…
Recent advancements in multimodal large language models (MLLMs) have shown promising results, yet existing approaches struggle to effectively handle both temporal and spatial localization simultaneously. This challenge stems from two key…
With the fast growing demand of location-based services in indoor environments, indoor positioning based on fingerprinting has attracted a lot of interest due to its high accuracy. In this paper, we present a novel deep learning based…
Open-vocabulary 6D object pose estimation empowers robots to manipulate arbitrary unseen objects guided solely by natural language. However, a critical limitation of existing approaches is their reliance on unconstrained global matching…
Fine-grained visual categorization is a classification task for distinguishing categories with high intra-class and small inter-class variance. While global approaches aim at using the whole image for performing the classification,…
Deformable image registration (DIR) remains a fundamental yet challenging problem in medical image analysis, largely due to the prohibitively high-dimensional deformation space of dense displacement fields and the scarcity of voxel-level…
Few-shot fine-grained recognition (FS-FGR) aims to recognize novel fine-grained categories with the help of limited available samples. Undoubtedly, this task inherits the main challenges from both few-shot learning and fine-grained…
Pose variation and subtle differences in appearance are key challenges to fine-grained classification. While deep networks have markedly improved general recognition, many approaches to fine-grained recognition rely on anchoring networks to…
Identifying subordinate-level categories from images is a longstanding task in computer vision and is referred to as fine-grained visual recognition (FGVR). It has tremendous significance in real-world applications since an average…