Related papers: VideoCutLER: Surprisingly Simple Unsupervised Vide…
Instance segmentation with neural networks is an essential task in environment perception. In many works, it has been observed that neural networks can predict false positive instances with high confidence values and true positives with low…
We present a semi-supervised approach that localizes multiple unknown object instances in long videos. We start with a handful of labeled boxes and iteratively learn and label hundreds of thousands of object instances. We propose criteria…
We propose Cut-Once-and-LEaRn (COLER), a simple approach for unsupervised instance segmentation and object detection. COLER first uses our developed CutOnce to generate coarse pseudo labels, then enables the detector to learn from these…
Recent video foundation models such as SAM2 excel at prompted video segmentation by treating masks as a general-purpose primitive. However, many real-world settings require unprompted segmentation that aims to detect and track all objects…
Instance segmentation is a challenging task aiming at classifying and segmenting all object instances of specific classes. While two-stage box-based methods achieve top performances in the image domain, they cannot easily extend their…
Video instance segmentation (VIS) is a critical task with diverse applications, including autonomous driving and video editing. Existing methods often underperform on complex and long videos in real world, primarily due to two factors.…
Most existing video tasks related to "human" focus on the segmentation of salient humans, ignoring the unspecified others in the video. Few studies have focused on segmenting and tracking all humans in a complex video, including pedestrians…
We introduce CellSegmenter, a structured deep generative model and an amortized inference framework for unsupervised representation learning and instance segmentation tasks. The proposed inference algorithm is convolutional and…
Instance segmentation is a fundamental skill for many robotic applications. We propose a self-supervised method that uses grasp interactions to collect segmentation supervision for an instance segmentation model. When a robot grasps an…
Modeling temporal visual context across frames is critical for video instance segmentation (VIS) and other video understanding tasks. In this paper, we propose a fast online VIS model named CrossVIS. For temporal information modeling in…
Segmentation of objects in a video is challenging due to the nuances such as motion blurring, parallax, occlusions, changes in illumination, etc. Instead of addressing these nuances separately, we focus on building a generalizable solution…
We propose a method for unsupervised video object segmentation by transferring the knowledge encapsulated in image-based instance embedding networks. The instance embedding network produces an embedding vector for each pixel that enables…
We propose a realistic scenario for the unsupervised video learning where neither task boundaries nor labels are provided when learning a succession of tasks. We also provide a non-parametric learning solution for the under-explored problem…
We propose a novel algorithm for weakly supervised semantic segmentation based on image-level class labels only. In weakly supervised setting, it is commonly observed that trained model overly focuses on discriminative parts rather than the…
Video instance segmentation is a challenging task that serves as the cornerstone of numerous downstream applications, including video editing and autonomous driving. In this report, we present further improvements to the SOTA VIS method,…
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…
In this paper, we propose Contextual Guided Segmentation (CGS) framework for video instance segmentation in three passes. In the first pass, i.e., preview segmentation, we propose Instance Re-Identification Flow to estimate main properties…
Labeling objects with pixel-wise segmentation requires a huge amount of human labor compared to bounding boxes. Most existing methods for weakly supervised instance segmentation focus on designing heuristic losses with priors from bounding…
We present an approach to semi-supervised video object segmentation, in the context of the DAVIS 2017 challenge. Our approach combines category-based object detection, category-independent object appearance segmentation and temporal object…
3D instance segmentation is fundamental to geometric understanding of the world around us. Existing methods for instance segmentation of 3D scenes rely on supervision from expensive, manual 3D annotations. We propose UnScene3D, the first…