Related papers: Detector-Free Weakly Supervised Grounding by Separ…
Vision-language (VL) models often exhibit a limited understanding of complex expressions of visual objects (e.g., attributes, shapes, and their relations), given complex and diverse language queries. Traditional approaches attempt to…
This paper shows that text-only Language Models (LM) can learn to ground spatial relations like "left of" or "below" if they are provided with explicit location information of objects and they are properly trained to leverage those…
Image-text matching plays a critical role in bridging the vision and language, and great progress has been made by exploiting the global alignment between image and sentence, or local alignments between regions and words. However, how to…
Visual grounding (VG) aims to establish fine-grained alignment between vision and language. Ideally, it can be a testbed for vision-and-language models to evaluate their understanding of the images and texts and their reasoning abilities…
Semantic segmentation requires a holistic understanding of the physical world, as it assigns semantic labels to spatially continuous and structurally coherent objects rather than to isolated pixels. However, existing data-free knowledge…
Remote sensing visual grounding (RSVG) aims to localize objects in remote sensing imagery according to natural language expressions. Previous methods typically rely on sentence-level vision-language alignment, which struggles to exploit…
Weakly-Supervised Camouflaged Object Detection (WSCOD) has gained popularity for its promise to train models with weak labels to segment objects that visually blend into their surroundings. Recently, some methods using sparsely-annotated…
Background subtraction (BGS) aims to extract all moving objects in the video frames to obtain binary foreground segmentation masks. Deep learning has been widely used in this field. Compared with supervised-based BGS methods, unsupervised…
Weakly Supervised Semantic Segmentation (WSSS) addresses the challenge of training segmentation models using only image-level annotations. Existing WSSS methods struggle with precise object boundary localization and focus only on the most…
The requiring of large amounts of annotated training data has become a common constraint on various deep learning systems. In this paper, we propose a weakly supervised scene text detection method (WeText) that trains robust and accurate…
Scarcity of pixel-level labels is a significant challenge in practical scenarios. In specific domains like industrial smoke, acquiring such detailed annotations is particularly difficult and often requires expert knowledge. To alleviate…
Modern incremental learning for semantic segmentation methods usually learn new categories based on dense annotations. Although achieve promising results, pixel-by-pixel labeling is costly and time-consuming. Weakly incremental learning for…
Weakly supervised object localization (WSOL) strives to learn to localize objects with only image-level supervision. Due to the local receptive fields generated by convolution operations, previous CNN-based methods suffer from partial…
Visual grounding is a common vision task that involves grounding descriptive sentences to the corresponding regions of an image. Most existing methods use independent image-text encoding and apply complex hand-crafted modules or…
Fibrotic Lung Disease (FLD) is a severe condition marked by lung stiffening and scarring, leading to respiratory decline. High-resolution computed tomography (HRCT) is critical for diagnosing and monitoring FLD; however, fibrosis appears as…
Weakly-supervised segmentation (WSS) methods, reliant on image-level labels indicating object presence, lack explicit correspondence between labels and regions of interest (ROIs), posing a significant challenge. Despite this, WSS methods…
Automatic road extraction from satellite imagery using deep learning is a viable alternative to traditional manual mapping. Therefore it has received considerable attention recently. However, most of the existing methods are supervised and…
Urbanization, climate change, and agricultural stress are increasing the demand for precise and timely environmental monitoring. Land Surface Temperature (LST) is a key variable in this context and is retrieved from remote sensing…
Determining the intended sense of words in text - word sense disambiguation (WSD) - is a long standing problem in natural language processing. Recently, researchers have shown promising results using word vectors extracted from a neural…
Unsupervised semantic segmentation aims to discover groupings within and across images that capture object and view-invariance of a category without external supervision. Grouping naturally has levels of granularity, creating ambiguity in…