Related papers: GETAM: Gradient-weighted Element-wise Transformer …
Compared to conventional semantic segmentation with pixel-level supervision, Weakly Supervised Semantic Segmentation (WSSS) with image-level labels poses the challenge that it always focuses on the most discriminative regions, resulting in…
Though image-level weakly supervised semantic segmentation (WSSS) has achieved great progress with Class Activation Maps (CAMs) as the cornerstone, the large supervision gap between classification and segmentation still hampers the model to…
Weakly Supervised Object Localization (WSOL), which aims to localize objects by only using image-level labels, has attracted much attention because of its low annotation cost in real applications. Current studies focus on the Class…
In this paper, we propose a weakly supervised semantic segmentation approach for food images which takes advantage of the zero-shot capabilities and promptability of the Segment Anything Model (SAM) along with the attention mechanisms of…
Seed area generation is usually the starting point of weakly supervised semantic segmentation (WSSS). Computing the Class Activation Map (CAM) from a multi-label classification network is the de facto paradigm for seed area generation, but…
We have witnessed remarkable progress in foundation models in vision tasks. Currently, several recent works have utilized the segmenting anything model (SAM) to boost the segmentation performance in medical images, where most of them focus…
Semantic segmentation is a challenging task in the absence of densely labelled data. Only relying on class activation maps (CAM) with image-level labels provides deficient segmentation supervision. Prior works thus consider pre-trained…
In this work, we focus on the task of weakly supervised affordance grounding, where a model is trained to identify affordance regions on objects using human-object interaction images and egocentric object images without dense labels.…
CNN visualization and interpretation methods, like class-activation maps (CAMs), are typically used to highlight the image regions linked to class predictions. These models allow to simultaneously classify images and extract class-dependent…
Magnetic resonance imaging (MRI) is a commonly used technique for brain tumor segmentation, which is critical for evaluating patients and planning treatment. To make the labeling process less laborious and dependent on expertise,…
The collection of a high number of pixel-based labeled training samples for tree species identification is time consuming and costly in operational forestry applications. To address this problem, in this paper we investigate the…
While class activation map (CAM) generated by image classification network has been widely used for weakly supervised object localization (WSOL) and semantic segmentation (WSSS), such classifiers usually focus on discriminative object…
Despite their success, Segment Anything Models (SAMs) experience significant performance drops on severely degraded, low-quality images, limiting their effectiveness in real-world scenarios. To address this, we propose GleSAM, which…
Online segmentation of laser-induced damage on large-aperture optics in high-power laser facilities is challenged by complicated damage morphology, uneven illumination and stray light interference. Fully supervised semantic segmentation…
Learning semantic segmentation models under image-level supervision is far more challenging than under fully supervised setting. Without knowing the exact pixel-label correspondence, most weakly-supervised methods rely on external models to…
We present a two-stage learning framework for weakly supervised object localization (WSOL). While most previous efforts rely on high-level feature based CAMs (Class Activation Maps), this paper proposes to localize objects using the…
Unlike fully supervised semantic segmentation, weakly supervised semantic segmentation (WSSS) relies on weaker forms of supervision to perform dense prediction tasks. Among the various types of weak supervision, WSSS with image level…
Class activation map (CAM) helps to formulate saliency maps that aid in interpreting the deep neural network's prediction. Gradient-based methods are generally faster than other branches of vision interpretability and independent of human…
Compared with expensive pixel-wise annotations, image-level labels make it possible to learn semantic segmentation in a weakly-supervised manner. Within this pipeline, the class activation map (CAM) is obtained and further processed to…
Semantic Segmentation (SS) of LiDAR point clouds is essential for many applications, such as urban planning and autonomous driving. While much progress has been made in interpreting SS predictions for images, interpreting point cloud SS…