Understanding Self-Supervised Features for Learning Unsupervised Instance Segmentation

2023-11-24 · Paul Engstler, Luke Melas-Kyriazi, Christian Rupprecht, Iro Laina

Self-supervised learning (SSL) can be used to solve complex visual tasks without human labels. Self-supervised representations encode useful semantic information about images, and as a result, they have already been used for tasks such as unsupervised semantic segmentation. In this paper, we investigate self-supervised representations for instance segmentation without any manual annotations. We find that the features of different SSL methods vary in their level of instance-awareness. In particular, DINO features, which are known to be excellent semantic descriptors, lack behind MAE features in their sensitivity for separating instances.

📄 PDF Abstract BibTeX arXiv:2311.14665

Code (0)

등록된 구현이 없습니다.

Tasks

Instance Segmentation Segmentation Self-Supervised Learning Semantic SegmentationSensitivityUnsupervised Instance Segmentation Unsupervised Semantic Segmentation

Methods 이 논문이 사용한 방법론

Attention 설명 없음

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Multi-Head Attention 설명 없음

Residual Connection 설명 없음

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Vision Transformer The Vision Transformer, or ViT, is a model for image classification that employs a Transformer-like architecture over…

UnScene3D: Unsupervised 3D Instance Segmentation for Indoor Scenes

2023-03-25 · CVPR 2024 1 · David Rozenberszki, Or Litany, Angela Dai

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 UnS…

3D Instance Segmentation Instance Segmentation Segmentation Semantic Segmentation

Unsupervised Salient Instance Detection

2024-01-01 · CVPR 2024 1 · Xin Tian, Ke Xu, Rynson Lau

The significant amount of manual efforts in annotating pixel-level labels has triggered the advancement of unsupervised saliency learning. However without supervision signals state-of-the-art methods can only infer r…

ProMerge: Prompt and Merge for Unsupervised Instance Segmentation

2024-09-27 · Dylan Li, Gyungin Shin

Unsupervised instance segmentation aims to segment distinct object instances in an image without relying on human-labeled data. This field has recently seen significant advancements, partly due to the strong local corres…

Instance Segmentation Semantic Segmentation Unsupervised Instance Segmentation

FreePoint: Unsupervised Point Cloud Instance Segmentation

2023-05-11 · CVPR 2024 1 · Zhikai Zhang, Jian Ding, Li Jiang, Dengxin Dai 외

Instance segmentation of point clouds is a crucial task in 3D field with numerous applications that involve localizing and segmenting objects in a scene. However, achieving satisfactory results requires a large number of…

Instance Segmentation Segmentation Semantic Segmentation Unsupervised Pre-training

Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion

2025-07-08 · Aleksandar Jevtić, Christoph Reich, Felix Wimbauer, Oliver Hahn 외

Semantic scene completion (SSC) aims to infer both the 3D geometry and semantics of a scene from single images. In contrast to prior work on SSC that heavily relies on expensive ground-truth annotations, we approach SSC …

3D geometry Domain Generalization Representation Learning Scene Understanding