Related papers: Hybrid Global-Local Representation with Augmented …
Large language models (LLMs) have been effectively used for many computer vision tasks, including image classification. In this paper, we present a simple yet effective approach for zero-shot image classification using multimodal LLMs.…
Semi-supervised learning has received considerable attention for its potential to leverage abundant unlabeled data to enhance model robustness. Pseudo labeling is a widely used strategy in semi supervised learning. However, existing methods…
The semantic segmentation task aims at dense classification at the pixel-wise level. Deep models exhibited progress in tackling this task. However, one remaining problem with these approaches is the loss of spatial precision, often produced…
Generalized Referring Expression Segmentation (GRES) extends the scope of classic RES to refer to multiple objects in one expression or identify the empty targets absent in the image. GRES poses challenges in modeling the complex spatial…
We study few-shot semantic segmentation that aims to segment a target object from a query image when provided with a few annotated support images of the target class. Several recent methods resort to a feature masking (FM) technique to…
We address representation learning for large-scale instance-level image retrieval. Apart from backbone, training pipelines and loss functions, popular approaches have focused on different spatial pooling and attention mechanisms, which are…
This paper investigates a challenging problem of zero-shot learning in the multi-label scenario (MLZSL), wherein, the model is trained to recognize multiple unseen classes within a sample (e.g., an image) based on seen classes and auxiliary…
In vision-language pre-training (VLP), masked image modeling (MIM) has recently been introduced for fine-grained cross-modal alignment. However, in most existing methods, the reconstruction targets for MIM lack high-level semantics, and…
Recent self-supervised advances in medical computer vision exploit global and local anatomical self-similarity for pretraining prior to downstream tasks such as segmentation. However, current methods assume i.i.d. image acquisition, which…
Ultra High Resolution (UHR) remote sensing imagery (RSI) (e.g. 100,000 $\times$ 100,000 pixels or more) poses a significant challenge for current Remote Sensing Multimodal Large Language Models (RSMLLMs). If choose to resize the UHR image…
Visual grounding tasks, such as referring image segmentation (RIS) and referring expression comprehension (REC), aim to localize a target object based on a given textual description. The target object in an image can be described in…
Medical image segmentation remains challenging due to the vast diversity of anatomical structures, imaging modalities, and segmentation tasks. While deep learning has made significant advances, current approaches struggle to generalize as…
Cross-modal MRI segmentation is of great value for computer-aided medical diagnosis, enabling flexible data acquisition and model generalization. However, most existing methods have difficulty in handling local variations in domain shift…
Spatial transcriptomics (ST) enables mapping gene expression with spatial context but is severely affected by high sparsity and technical noise, which conceals true biological signals and hinders downstream analyses. To address these…
Unmanned Aerial Vehicle (UAV) Cross-View Geo-Localization (CVGL) presents significant challenges due to the view discrepancy between oblique UAV images and overhead satellite images. Existing methods heavily rely on the supervision of…
Referring Image Segmentation (RIS), which aims to segment specific objects based on natural language descriptions, plays an essential role in vision-language understanding. Despite its progress in remote sensing applications, RIS in…
Compared to facial expression recognition, expression synthesis requires a very high-dimensional mapping. This problem exacerbates with increasing image sizes and limits existing expression synthesis approaches to relatively small images.…
Visual Place Recognition (VPR) enables coarse localization by comparing query images to a reference database of geo-tagged images. Recent breakthroughs in deep learning architectures and training regimes have led to methods with improved…
Contrastive Language-Image Pre-training (CLIP) has demonstrated remarkable generalization ability and strong performance across a wide range of vision-language tasks. However, due to the lack of region-level supervision, CLIP exhibits…
Cross-view object geo-localization enables high-precision object localization through cross-view matching, with critical applications in autonomous driving, urban management, and disaster response. However, existing methods rely on…