Related papers: RaSP: Relation-aware Semantic Prior for Weakly Sup…
Autonomous robotic systems applied to new domains require an abundance of expensive, pixel-level dense labels to train robust semantic segmentation models under full supervision. This study proposes a model-agnostic Depth Edge Alignment…
A major obstacle in instance segmentation is that existing methods often need many per-pixel labels in order to be effective. These labels require large human effort and for certain applications, such labels are not readily available. To…
We address the problem of learning new classes for semantic segmentation models from few examples, which is challenging because of the following two reasons. Firstly, it is difficult to learn from limited novel data to capture the…
After learning a new object category from image-level annotations (with no object bounding boxes), humans are remarkably good at precisely localizing those objects. However, building good object localizers (i.e., detectors) currently…
Visual grounding, which aims to build a correspondence between visual objects and their language entities, plays a key role in cross-modal scene understanding. One promising and scalable strategy for learning visual grounding is to utilize…
Pre-trained vision-language models learn massive data to model unified representations of images and natural languages, which can be widely applied to downstream machine learning tasks. In addition to zero-shot inference, in order to better…
Deep learning generates state-of-the-art semantic segmentation provided that a large number of images together with pixel-wise annotations are available. To alleviate the expensive data collection process, we propose a semi-supervised…
Semantic segmentation has been a long standing challenging task in computer vision. It aims at assigning a label to each image pixel and needs significant number of pixellevel annotated data, which is often unavailable. To address this…
Weakly supervised nuclei segmentation is a critical problem for pathological image analysis and greatly benefits the community due to the significant reduction of labeling cost. Adopting point annotations, previous methods mostly rely on…
Despite their effectiveness in a wide range of tasks, deep architectures suffer from some important limitations. In particular, they are vulnerable to catastrophic forgetting, i.e. they perform poorly when they are required to update their…
3D weakly supervised semantic segmentation (3D WSSS) aims to achieve semantic segmentation by leveraging sparse or low-cost annotated data, significantly reducing reliance on dense point-wise annotations. Previous works mainly employ class…
Semantic segmentation has been continuously investigated in the last ten years, and majority of the established technologies are based on supervised models. In recent years, image-level weakly supervised semantic segmentation (WSSS),…
Human learning benefits from multi-modal inputs that often appear as rich semantics (e.g., description of an object's attributes while learning about it). This enables us to learn generalizable concepts from very limited visual examples.…
This work proposes a hybrid unsupervised and supervised learning method to pre-train models applied in Earth observation downstream tasks when only a handful of labels denoting very general semantic concepts are available. We combine a…
Instance segmentation methods require large datasets with expensive and thus limited instance-level mask labels. Partially supervised instance segmentation aims to improve mask prediction with limited mask labels by utilizing the more…
In spite of remarkable success of the convolutional neural networks on semantic segmentation, they suffer from catastrophic forgetting: a significant performance drop for the already learned classes when new classes are added on the data,…
In semantic segmentation, training data down-sampling is commonly performed due to limited resources, the need to adapt image size to the model input, or improve data augmentation. This down-sampling typically employs different strategies…
Recently proposed methods for weakly-supervised semantic segmentation have achieved impressive performance in predicting pixel classes despite being trained with only image labels which lack positional information. Because image annotations…
For the semantic segmentation of images, state-of-the-art deep neural networks (DNNs) achieve high segmentation accuracy if that task is restricted to a closed set of classes. However, as of now DNNs have limited ability to operate in an…
We propose a weakly-supervised approach for conditional image generation of complex scenes where a user has fine control over objects appearing in the scene. We exploit sparse semantic maps to control object shapes and classes, as well as…