Related papers: Boosting Unsupervised Video Instance Segmentation …
Unsupervised image segmentation is a critical task in computer vision. It enables dense scene understanding without human annotations, which is especially valuable in domains where labelled data is scarce. However, existing methods often…
There has been abundant work in unsupervised domain adaptation for semantic segmentation (DAS) seeking to adapt a model trained on images from a labeled source domain to an unlabeled target domain. While the vast majority of prior work has…
Weakly supervised point cloud semantic segmentation methods that require 1\% or fewer labels, hoping to realize almost the same performance as fully supervised approaches, which recently, have attracted extensive research attention. A…
Given the vast amounts of video available online, and recent breakthroughs in object detection with static images, object detection in video offers a promising new frontier. However, motion blur and compression artifacts cause substantial…
Unsupervised video object segmentation (VOS), also known as video salient object detection, aims to detect the most prominent object in a video at the pixel level. Recently, two-stream approaches that leverage both RGB images and optical…
How can unlabeled video augment visual learning? Existing methods perform "slow" feature analysis, encouraging the representations of temporally close frames to exhibit only small differences. While this standard approach captures the fact…
Despite significant progress in semi-supervised learning for image object detection, several key issues are yet to be addressed for video object detection: (1) Achieving good performance for supervised video object detection greatly depends…
The divergence between labeled training data and unlabeled testing data is a significant challenge for recent deep learning models. Unsupervised domain adaptation (UDA) attempts to solve such a problem. Recent works show that self-training…
Referring Image Segmentation (RIS) - the problem of identifying objects in images through natural language sentences - is a challenging task currently mostly solved through supervised learning. However, while collecting referred annotation…
Video Object Segmentation (VOS) has been targeted by various fully-supervised and self-supervised approaches. While fully-supervised methods demonstrate excellent results, self-supervised ones, which do not use pixel-level ground truth,…
Despite the availability of large datasets for tasks like image classification and image-text alignment, labeled data for more complex recognition tasks, such as detection and segmentation, is less abundant. In particular, for instance…
Enabling computational systems with the ability to localize actions in video-based content has manifold applications. Traditionally, such a problem is approached in a fully-supervised setting where video-clips with complete frame-by-frame…
Unsupervised learning from visual data is one of the most difficult challenges in computer vision, being a fundamental task for understanding how visual recognition works. From a practical point of view, learning from unsupervised visual…
Background: The quantitative analysis of microscope videos often requires instance segmentation and tracking of cellular and subcellular objects. The traditional method consists of two stages: (1) performing instance object segmentation of…
With the growing popularity of short-form video sharing platforms such as \em{Instagram} and \em{Vine}, there has been an increasing need for techniques that automatically extract highlights from video. Whereas prior works have approached…
Semi-supervised instance segmentation poses challenges due to limited labeled data, causing difficulties in accurately localizing distinct object instances. Current teacher-student frameworks still suffer from performance constraints due to…
Current state-of-the-art Video Object Segmentation (VOS) methods rely on dense per-object mask annotations both during training and testing. This requires time-consuming and costly video annotation mechanisms. We propose a novel Point-VOS…
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…
We present a novel data-efficient semi-supervised framework to improve the generalization of image captioning models. Constructing a large-scale labeled image captioning dataset is an expensive task in terms of labor, time, and cost. In…
Automatic surgical instrument segmentation of endoscopic images is a crucial building block of many computer-assistance applications for minimally invasive surgery. So far, state-of-the-art approaches completely rely on the availability of…