Contrastive positive sample propagation along the audio-visual event line
Visual and audio signals often coexist in natural environments, forming audio-visual events
(AVEs). Given a video, we aim to localize video segments containing an AVE and identify its …
(AVEs). Given a video, we aim to localize video segments containing an AVE and identify its …
Bridging the gap between classification and localization for weakly supervised object localization
Weakly supervised object localization aims to find a target object region in a given image
with only weak supervision, such as image-level labels. Most existing methods use a class …
with only weak supervision, such as image-level labels. Most existing methods use a class …
Weakly supervised object localization as domain adaption
Weakly supervised object localization (WSOL) focuses on localizing objects only with the
supervision of image-level classification masks. Most previous WSOL methods follow the …
supervision of image-level classification masks. Most previous WSOL methods follow the …
Deep weakly-supervised learning methods for classification and localization in histology images: a survey
Using deep learning models to diagnose cancer from histology data presents several
challenges. Cancer grading and localization of regions of interest (ROIs) in these images …
challenges. Cancer grading and localization of regions of interest (ROIs) in these images …
Bagging regional classification activation maps for weakly supervised object localization
Classification activation map (CAM), utilizing the classification structure to generate pixel-
wise localization maps, is a crucial mechanism for weakly supervised object localization …
wise localization maps, is a crucial mechanism for weakly supervised object localization …
F-cam: Full resolution class activation maps via guided parametric upscaling
Abstract Class Activation Mapping (CAM) methods have recently gained much attention for
weakly-supervised object localization (WSOL) tasks. They allow for CNN visualization and …
weakly-supervised object localization (WSOL) tasks. They allow for CNN visualization and …
Efficient classification of very large images with tiny objects
An increasing number of applications in computer vision, specially, in medical imaging and
remote sensing, become challenging when the goal is to classify very large images with tiny …
remote sensing, become challenging when the goal is to classify very large images with tiny …
DiPS: Discriminative pseudo-label sampling with self-supervised transformers for weakly supervised object localization
Self-supervised vision transformers (SSTs) have shown great potential to yield rich
localization maps that highlight different objects in an image. However, these maps remain …
localization maps that highlight different objects in an image. However, these maps remain …
Anti-adversarially manipulated attributions for weakly supervised semantic segmentation and object localization
Obtaining accurate pixel-level localization from class labels is a crucial process in weakly
supervised semantic segmentation and object localization. Attribution maps from a trained …
supervised semantic segmentation and object localization. Attribution maps from a trained …
On label granularity and object localization
Weakly supervised object localization (WSOL) aims to learn representations that encode
object location using only image-level category labels. However, many objects can be …
object location using only image-level category labels. However, many objects can be …