Related papers: Hierarchical Lov\'asz Embeddings for Proposal-free…

CLIP retrieval is typically framed as a pointwise similarity problem in a shared embedding space. While CLIP achieves strong global cross-modal alignment, many retrieval failures arise from local geometric inconsistencies: nearby items are…

Panoptic segmentation, which combines instance and semantic segmentation, has gained a lot of attention in autonomous vehicles, due to its comprehensive representation of the scene. This task can be applied for cameras and LiDAR sensors,…

Part-aware panoptic segmentation is a problem of computer vision that aims to provide a semantic understanding of the scene at multiple levels of granularity. More precisely, semantic areas, object instances, and semantic parts are…

Incremental few-shot semantic segmentation (IFSS) targets at incrementally expanding model's capacity to segment new class of images supervised by only a few samples. However, features learned on old classes could significantly drift,…

Panoptic segmentation is a complex full scene parsing task requiring simultaneous instance and semantic segmentation at high resolution. Current state-of-the-art approaches cannot run in real-time, and simplifying these architectures to…

By representing words with probability densities rather than point vectors, probabilistic word embeddings can capture rich and interpretable semantic information and uncertainty. The uncertainty information can be particularly meaningful in…

Zero-shot learning, which aims to recognize new categories that are not included in the training set, has gained popularity owing to its potential ability in the real-word applications. Zero-shot learning models rely on learning an…

This work proposed a novel learning objective to train a deep neural network to perform end-to-end image pixel clustering. We applied the approach to instance segmentation, which is at the intersection of image semantic segmentation and…

Understanding the scene in which an autonomous robot operates is critical for its competent functioning. Such scene comprehension necessitates recognizing instances of traffic participants along with general scene semantics which can be…

In the context of pose-invariant object recognition and retrieval, we demonstrate that it is possible to achieve significant improvements in performance if both the category-based and the object-identity-based embeddings are learned…

This paper introduces panoptica, a versatile and performance-optimized package designed for computing instance-wise segmentation quality metrics from 2D and 3D segmentation maps. panoptica addresses the limitations of existing metrics and…

Label hierarchies widely exist in many vision-related problems, ranging from explicit label hierarchies existed in image classification to latent label hierarchies existed in semantic segmentation. Nevertheless, state-of-the-art methods…

This paper introduces a novel approach for 3D semantic instance segmentation on point clouds. A 3D convolutional neural network called submanifold sparse convolutional network is used to generate semantic predictions and instance embeddings…

Slot attention has emerged as a powerful framework for unsupervised object-centric learning, decomposing visual scenes into a small set of compact vector representations called \emph{slots}, each capturing a distinct region or object.…

In this paper, the task of video panoptic segmentation is studied and two different methods to solve the task will be proposed. Video panoptic segmentation (VPS) is a recently introduced computer vision task that requires classifying and…

One-shot semantic image segmentation aims to segment the object regions for the novel class with only one annotated image. Recent works adopt the episodic training strategy to mimic the expected situation at testing time. However, these…

A new, machine learning-based approach for automatically generating 3D digital geometries of woven composite textiles is proposed to overcome the limitations of existing analytical descriptions and segmentation methods. In this approach,…

3D point cloud panoptic segmentation is the combined task to (i) assign each point to a semantic class and (ii) separate the points in each class into object instances. Recently there has been an increased interest in such comprehensive 3D…

User generated 3D shapes in online repositories contain rich information about surfaces, primitives, and their geometric relations, often arranged in a hierarchy. We present a framework for learning representations of 3D shapes that reflect…

Unsupervised feature learning often finds low-dimensional embeddings that capture the structure of complex data. For tasks for which prior expert topological knowledge is available, incorporating this into the learned representation may…