Related papers: ReCo: Retrieve and Co-segment for Zero-shot Transf…
Segment Anything Model (SAM) exhibits remarkable zero-shot segmentation capability; however, its prohibitive computational costs make edge deployment challenging. Although post-training quantization (PTQ) offers a promising compression…
Semantic segmentation is an important and popular research area in computer vision that focuses on classifying pixels in an image based on their semantics. However, supervised deep learning requires large amounts of data to train models and…
Semantic segmentation is a crucial step in many Earth observation tasks. Large quantity of pixel-level annotation is required to train deep networks for semantic segmentation. Earth observation techniques are applied to varieties of…
Image clustering is an important and open-challenging task in computer vision. Although many methods have been proposed to solve the image clustering task, they only explore images and uncover clusters according to the image features, thus…
Image segmentation is usually addressed by training a model for a fixed set of object classes. Incorporating additional classes or more complex queries later is expensive as it requires re-training the model on a dataset that encompasses…
Existing semantic segmentation models heavily rely on dense pixel-wise annotations. To reduce the annotation pressure, we focus on a challenging task named zero-shot semantic segmentation, which aims to segment unseen objects with zero…
Deep neural networks have enabled major progresses in semantic segmentation. However, even the most advanced neural architectures suffer from important limitations. First, they are vulnerable to catastrophic forgetting, i.e. they perform…
Contrastive Language-Image Pre-training (CLIP) has emerged as a simple yet effective way to train large-scale vision-language models. CLIP demonstrates impressive zero-shot classification and retrieval on diverse downstream tasks. However,…
Recent years have witnessed the great progress of deep neural networks on semantic segmentation, particularly in medical imaging. Nevertheless, training high-performing models require large amounts of pixel-level ground truth masks, which…
Few-shot semantic segmentation aims to segment objects from previously unseen classes using only a limited number of labeled examples. In this paper, we introduce Label Anything, a novel transformer-based architecture designed for…
Semantic segmentation is a crucial task in computer vision, where each pixel in an image is classified into a category. However, traditional methods face significant challenges, including the need for pixel-level annotations and extensive…
Pretrained language models have improved zero-shot text classification by allowing the transfer of semantic knowledge from the training data in order to classify among specific label sets in downstream tasks. We propose a simple way to…
zero-shot learning is an essential part of computer vision. As a classical downstream task, zero-shot semantic segmentation has been studied because of its applicant value. One of the popular zero-shot semantic segmentation methods is based…
Contrastive image-text models such as CLIP form the building blocks of many state-of-the-art systems. While they excel at recognizing common generic concepts, they still struggle on fine-grained entities which are rare, or even absent from…
The ability to understand visual information from limited labeled data is an important aspect of machine learning. While image-level classification has been extensively studied in a semi-supervised setting, dense pixel-level classification…
Feature selection, an effective technique for dimensionality reduction, plays an important role in many machine learning systems. Supervised knowledge can significantly improve the performance. However, faced with the rapid growth of newly…
CLIP has enabled new and exciting joint vision-language applications, one of which is open-vocabulary segmentation, which can locate any segment given an arbitrary text query. In our research, we ask whether it is possible to discover…
Modern sensing systems generate large volumes of unlabeled multivariate time-series data. This abundance of unlabeled data makes self-supervised learning (SSL) a natural approach for learning transferable representations. However, most…
Small sample instance segmentation is a very challenging task, and many existing methods follow the training strategy of meta-learning which pre-train models on support set and fine-tune on query set. The pre-training phase, which is highly…
Domain adaptive semantic segmentation attempts to make satisfactory dense predictions on an unlabeled target domain by utilizing the supervised model trained on a labeled source domain. In this work, we propose Semantic-Guided Pixel…