In this paper, we consider the problem of open-vocabulary semantic segmentation (OVS),
which aims to segment objects of arbitrary classes instead of pre-defined, closed-set …

Weakly supervised object localization (WSOL) remains challenging when learning object
localization models from image category labels. Conventional methods that discriminatively …

Fusing infrared and visible images can provide more texture details for subsequent object
detection task. Conversely, detection task furnishes object semantic information to improve …

Weakly supervised dense object localization (WSDOL) relies generally on Class Activation
Mapping (CAM), which exploits the correlation between the class weights of the image …

Humans excel at acquiring knowledge through observation. For example, we can learn to
use new tools by watching demonstrations. This skill is fundamental for intelligent systems to …

This paper proposes a novel transformer-based framework to generate accurate class-
specific object localization maps for weakly supervised semantic segmentation (WSSS) …

Weakly supervised object localization and semantic segmentation aim to localize objects
using only image-level labels. Recently, a new paradigm has emerged by generating a …

In today's digital age, Convolutional Neural Networks (CNNs), a subset of Deep Learning
(DL), are widely used for various computer vision tasks such as image classification, object …

The aim of weakly supervised object co-localization is to locate different objects of the same
superclass in a dataset. Recent methods achieve impressive co-localization performance by …

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 …