Related papers: S2D: Sparse-To-Dense Keymask Distillation for Unsu…

Modern one-stage video instance segmentation networks suffer from two limitations. First, convolutional features are neither aligned with anchor boxes nor with ground-truth bounding boxes, reducing the mask sensitivity to spatial location.…

Single-stage instance segmentation approaches have recently gained popularity due to their speed and simplicity, but are still lagging behind in accuracy, compared to two-stage methods. We propose a fast single-stage instance segmentation…

This paper addresses the task of unsupervised video multi-object segmentation. Current approaches follow a two-stage paradigm: 1) detect object proposals using pre-trained Mask R-CNN, and 2) conduct generic feature matching for temporal…

3D semantic scene understanding tasks have achieved great success with the emergence of deep learning, but often require a huge amount of manually annotated training data. To alleviate the annotation cost, we propose the first…

This paper introduces a unified framework for video action segmentation via sequence to sequence (seq2seq) translation in a fully and timestamp supervised setup. In contrast to current state-of-the-art frame-level prediction methods, we…

State-of-the-art transformer-based video instance segmentation (VIS) approaches typically utilize either single-scale spatio-temporal features or per-frame multi-scale features during the attention computations. We argue that such an…

Current 3D segmentation methods heavily rely on large-scale point-cloud datasets, which are notoriously laborious to annotate. Few attempts have been made to circumvent the need for dense per-point annotations. In this work, we look at…

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…

Contemporary Video Instance Segmentation (VIS) methods typically adhere to a pre-train then fine-tune regime, where a segmentation model trained on images is fine-tuned on videos. However, the lack of temporal knowledge in the pre-trained…

Instance segmentation is essential for applications such as automated monitoring of plant health, growth, and yield. However, extensive effort is required to create large-scale datasets with pixel-level annotations of each object instance…

Self-supervised image encoders such as DINO have recently gained significant interest for learning robust visual features without labels. However, most SSL methods train on static images and miss the temporal cues inherent in videos. We…

The performance of Video Instance Segmentation (VIS) methods has improved significantly with the advent of transformer networks. However, these networks often face challenges in training due to the high annotation cost. To address this,…

Producing quality segmentation masks for images is a fundamental problem in computer vision. Recent research has explored large-scale supervised training to enable zero-shot segmentation on virtually any image style and unsupervised…

Video instance segmentation requires detecting, segmenting, and tracking objects in videos, typically relying on costly video annotations. This paper introduces a method that eliminates video annotations by utilizing image datasets. The…

This paper tackles the problem of semi-supervised video object segmentation on resource-constrained devices, such as mobile phones. We formulate this problem as a distillation task, whereby we demonstrate that small space-time-memory…

Weakly supervised video object segmentation (WSVOS) enables the identification of segmentation maps without requiring an extensive training dataset of object masks, relying instead on coarse video labels indicating object presence. Current…

Although instance segmentation methods have improved considerably, the dominant paradigm is to rely on fully-annotated training images, which are tedious to obtain. To alleviate this reliance, and boost results, semi-supervised approaches…

To improve the efficiency of surgical trajectory segmentation for robot learning in robot-assisted minimally invasive surgery, this paper presents a fast unsupervised method using video and kinematic data, followed by a promoting procedure…

Panoptic and instance segmentation networks are often trained with specialized object detection modules, complex loss functions, and ad-hoc post-processing steps to manage the permutation-invariance of the instance masks. This work builds…

We consider the task of semi-supervised video object segmentation (VOS). Our approach mitigates shortcomings in previous VOS work by addressing detail preservation and temporal consistency using visual warping. In contrast to prior work…