Diffuse Attend and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusion

J Tian, L Aggarwal, A Colaco, Z Kira… - Proceedings of the …, 2024 - openaccess.thecvf.com
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 …

Bridging the gap to real-world object-centric learning

M Seitzer, M Horn, A Zadaianchuk, D Zietlow… - ar**_in_Contrastive_Vision-Language_Models_ICCV_2023_paper.pdf" data-clk="hl=ko&sa=T&oi=gga&ct=gga&cd=4&d=8007875619441193435&ei=QVuwZ6zQGNaIieoP4pXqgQk" data-clk-atid="27FNxnKwIW8J" target="_blank">[PDF] thecvf.com

Perceptual grou** in contrastive vision-language models

K Ranasinghe, B McKinzie, S Ravi… - Proceedings of the …, 2023 - openaccess.thecvf.com
Recent advances in zero-shot image recognition suggest that vision-language models learn
generic visual representations with a high degree of semantic information that may be …

Distilling self-supervised vision transformers for weakly-supervised few-shot classification & segmentation

D Kang, P Koniusz, M Cho… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
We address the task of weakly-supervised few-shot image classification and segmentation,
by leveraging a Vision Transformer (ViT) pretrained with self-supervision. Our proposed …

Time does tell: Self-supervised time-tuning of dense image representations

M Salehi, E Gavves, CGM Snoek… - Proceedings of the …, 2023 - openaccess.thecvf.com
Spatially dense self-supervised learning is a rapidly growing problem domain with
promising applications for unsupervised segmentation and pretraining for dense …

In defense of lazy visual grounding for open-vocabulary semantic segmentation

D Kang, M Cho - European Conference on Computer Vision, 2024 - Springer
Abstract We present Lazy Visual Grounding for open-vocabulary semantic segmentation,
which decouples unsupervised object mask discovery from object grounding. Plenty of the …

Rotating features for object discovery

S Löwe, P Lippe, F Locatello… - Advances in Neural …, 2023 - proceedings.neurips.cc
The binding problem in human cognition, concerning how the brain represents and
connects objects within a fixed network of neural connections, remains a subject of intense …

Autorecon: Automated 3d object discovery and reconstruction

Y Wang, X He, S Peng, H Lin… - Proceedings of the …, 2023 - openaccess.thecvf.com
A fully automated object reconstruction pipeline is crucial for digital content creation. While
the area of 3D reconstruction has witnessed profound developments, the removal of …