Related papers: EM-Paste: EM-guided Cut-Paste with DALL-E Augmenta…

Accurate segmentation of polyps and skin lesions is essential for diagnosing colorectal and skin cancers. While various segmentation methods for polyps and skin lesions using fully supervised deep learning techniques have been developed,…

Current methods for 3D semantic segmentation propose training models with limited annotations to address the difficulty of annotating large, irregular, and unordered 3D point cloud data. They usually focus on the 3D domain only, without…

Visual grounding localizes regions (boxes or segments) in the image corresponding to given referring expressions. In this work we address image segmentation from referring expressions, a problem that has so far only been addressed in a…

Weakly supervised learning has emerged as an appealing alternative to alleviate the need for large labeled datasets in semantic segmentation. Most current approaches exploit class activation maps (CAMs), which can be generated from…

An instance with a bad mask might make a composite image that uses it look fake. This encourages us to learn segmentation by generating realistic composite images. To achieve this, we propose a novel framework that exploits a new proposed…

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…

While standard Empirical Risk Minimization (ERM) training is proven effective for image classification on in-distribution data, it fails to perform well on out-of-distribution samples. One of the main sources of distribution shift for image…

We propose PARSE, a novel semi-supervised architecture for learning strong EEG representations for emotion recognition. To reduce the potential distribution mismatch between the large amounts of unlabeled data and the limited amount of…

Detecting unseen anomalies in unstructured environments presents a critical challenge for industrial and agricultural applications such as material recycling and weeding. Existing perception systems frequently fail to satisfy the strict…

Weakly supervised semantic segmentation (WSSS) has gained significant popularity since it relies only on weak labels such as image level annotations rather than pixel level annotations required by supervised semantic segmentation (SSS)…

We propose a weakly-supervised approach that takes image-sentence pairs as input and learns to visually ground (i.e., localize) arbitrary linguistic phrases, in the form of spatial attention masks. Specifically, the model is trained with…

We consider the generic problem of detecting low-level structures in images, which includes segmenting the manipulated parts, identifying out-of-focus pixels, separating shadow regions, and detecting concealed objects. Whereas each such…

Decomposition of the evidence lower bound (ELBO) objective of VAE used for density estimation revealed the deficiency of VAE for representation learning and suggested ways to improve the model. In this paper, we investigate whether we can…

Referring video object segmentation (RVOS) aims to segment the target instance in a video, referred by a text expression. Conventional approaches are mostly supervised learning, requiring expensive pixel-level mask annotations. To tackle…

Pixel-level annotations are expensive and time consuming to obtain. Hence, weak supervision using only image tags could have a significant impact in semantic segmentation. Recently, CNN-based methods have proposed to fine-tune pre-trained…

We present a new flavor of Variational Autoencoder (VAE) that interpolates seamlessly between unsupervised, semi-supervised and fully supervised learning domains. We show that unlabeled datapoints not only boost unsupervised tasks, but also…

Deep learning methods show promising results for overlapping cervical cell instance segmentation. However, in order to train a model with good generalization ability, voluminous pixel-level annotations are demanded which is quite expensive…

By estimating 3D shape and instances from a single view, we can capture information about an environment quickly, without the need for comprehensive scanning and multi-view fusion. Solving this task for composite scenes (such as object…

Recently, there has been a panoptic segmentation task combining semantic and instance segmentation, in which the goal is to classify each pixel with the corresponding instance ID. In this work, we propose a solution to tackle the panoptic…

In general, sufficient data is essential for the better performance and generalization of deep-learning models. However, lots of limitations(cost, resources, etc.) of data collection leads to lack of enough data in most of the areas. In…