Related papers: Separate and Conquer: Decoupling Co-occurrence via…

The absence of large scale datasets with pixel-level supervisions is a significant obstacle for the training of deep convolutional networks for scene text segmentation. For this reason, synthetic data generation is normally employed to…

Semi-weakly supervised semantic segmentation (SWSSS) aims to train a model to identify objects in images based on a small number of images with pixel-level labels, and many more images with only image-level labels. Most existing SWSSS…

We present a self-supervised learning (SSL) method suitable for semi-global tasks such as object detection and semantic segmentation. We enforce local consistency between self-learned features, representing corresponding image locations of…

Generating precise class-aware pseudo ground-truths, a.k.a, class activation maps (CAMs), is essential for weakly-supervised semantic segmentation. The original CAM method usually produces incomplete and inaccurate localization maps. To…

Weakly supervised semantic segmentation is a challenging task as it only takes image-level information as supervision for training but produces pixel-level predictions for testing. To address such a challenging task, most recent…

Weakly supervised image segmentation (WSSS) from image tags remains challenging due to its under-constraint nature. Most mainstream work focus on the extraction of class activation map (CAM) and imposing various additional regularization.…

Weakly Supervised Object Detection (WSOD) is a task that detects objects in an image using a model trained only on image-level annotations. Current state-of-the-art models benefit from self-supervised instance-level supervision, but since…

Weakly-supervised image segmentation (WSIS) is a critical task in computer vision that relies on image-level class labels. Multi-stage training procedures have been widely used in existing WSIS approaches to obtain high-quality pseudo-masks…

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…

Although existing semantic segmentation approaches achieve impressive results, they still struggle to update their models incrementally as new categories are uncovered. Furthermore, pixel-by-pixel annotations are expensive and…

It has been widely known that CAM (Class Activation Map) usually only activates discriminative object regions and falsely includes lots of object-related backgrounds. As only a fixed set of image-level object labels are available to the…

Surface cracks are a common sight on public infrastructure nowadays. Recent work has been addressing this problem by supporting structural maintenance measures using machine learning methods. Those methods are used to segment surface cracks…

Unsupervised semantic segmentation aims to discover and localize semantically meaningful categories within image corpora without any form of annotation. To solve this task, algorithms must produce features for every pixel that are both…

Visual concept discovery has long been deemed important to improve interpretability of neural networks, because a bank of semantically meaningful concepts would provide us with a starting point for building machine learning models that…

Providing pixel-level supervisions for scene text segmentation is inherently difficult and costly, so that only few small datasets are available for this task. To face the scarcity of training data, previous approaches based on…

Weakly-Supervised Camouflaged Object Detection (WSCOD) aims to locate and segment objects that are visually concealed within their surrounding scenes, relying solely on sparse supervision such as scribble annotations. Despite recent…

Weakly supervised image segmentation trained with image-level labels usually suffers from inaccurate coverage of object areas during the generation of the pseudo groundtruth. This is because the object activation maps are trained with the…

Self-supervised Object Segmentation (SOS) aims to segment objects without any annotations. Under conditions of multi-camera inputs, the structural, textural and geometrical consistency among each view can be leveraged to achieve…

The costly process of obtaining semantic segmentation labels has driven research towards weakly supervised semantic segmentation (WSSS) methods, using only image-level, point, or box labels. The lack of dense scene representation requires…

We propose a weakly-supervised framework for the semantic segmentation of circular-scan synthetic-aperture-sonar (CSAS) imagery. The first part of our framework is trained in a supervised manner, on image-level labels, to uncover a set of…