Alert button

"Image": models, code, and papers
Alert button

SciCap+: A Knowledge Augmented Dataset to Study the Challenges of Scientific Figure Captioning

Jun 06, 2023
Zhishen Yang, Raj Dabre, Hideki Tanaka, Naoaki Okazaki

Figure 1 for SciCap+: A Knowledge Augmented Dataset to Study the Challenges of Scientific Figure Captioning
Figure 2 for SciCap+: A Knowledge Augmented Dataset to Study the Challenges of Scientific Figure Captioning
Figure 3 for SciCap+: A Knowledge Augmented Dataset to Study the Challenges of Scientific Figure Captioning
Figure 4 for SciCap+: A Knowledge Augmented Dataset to Study the Challenges of Scientific Figure Captioning
Viaarxiv icon

What makes a good data augmentation for few-shot unsupervised image anomaly detection?

Apr 21, 2023
Lingrui Zhang, Shuheng Zhang, Guoyang Xie, Jiaqi Liu, Hua Yan, Jinbao Wang, Feng Zheng, Yaochu Jin

Figure 1 for What makes a good data augmentation for few-shot unsupervised image anomaly detection?
Figure 2 for What makes a good data augmentation for few-shot unsupervised image anomaly detection?
Figure 3 for What makes a good data augmentation for few-shot unsupervised image anomaly detection?
Figure 4 for What makes a good data augmentation for few-shot unsupervised image anomaly detection?
Viaarxiv icon

Ablating Concepts in Text-to-Image Diffusion Models

Mar 23, 2023
Nupur Kumari, Bingliang Zhang, Sheng-Yu Wang, Eli Shechtman, Richard Zhang, Jun-Yan Zhu

Figure 1 for Ablating Concepts in Text-to-Image Diffusion Models
Figure 2 for Ablating Concepts in Text-to-Image Diffusion Models
Figure 3 for Ablating Concepts in Text-to-Image Diffusion Models
Figure 4 for Ablating Concepts in Text-to-Image Diffusion Models
Viaarxiv icon

BugNIST -- A New Large Scale Volumetric 3D Image Dataset for Classification and Detection

Apr 04, 2023
Anders Bjorholm Dahl, Patrick Møller Jensen, Carsten Gundlach, Rebecca Engberg, Hans Martin Kjer, Vedrana Andersen Dahl

Figure 1 for BugNIST -- A New Large Scale Volumetric 3D Image Dataset for Classification and Detection
Figure 2 for BugNIST -- A New Large Scale Volumetric 3D Image Dataset for Classification and Detection
Figure 3 for BugNIST -- A New Large Scale Volumetric 3D Image Dataset for Classification and Detection
Figure 4 for BugNIST -- A New Large Scale Volumetric 3D Image Dataset for Classification and Detection
Viaarxiv icon

Disentangling the Link Between Image Statistics and Human Perception

Mar 17, 2023
Alexander Hepburn, Valero Laparra, Raul Santos-Rodriguez, Jesús Malo

Figure 1 for Disentangling the Link Between Image Statistics and Human Perception
Figure 2 for Disentangling the Link Between Image Statistics and Human Perception
Figure 3 for Disentangling the Link Between Image Statistics and Human Perception
Figure 4 for Disentangling the Link Between Image Statistics and Human Perception
Viaarxiv icon

Localized Region Contrast for Enhancing Self-Supervised Learning in Medical Image Segmentation

Apr 06, 2023
Xiangyi Yan, Junayed Naushad, Chenyu You, Hao Tang, Shanlin Sun, Kun Han, Haoyu Ma, James Duncan, Xiaohui Xie

Figure 1 for Localized Region Contrast for Enhancing Self-Supervised Learning in Medical Image Segmentation
Figure 2 for Localized Region Contrast for Enhancing Self-Supervised Learning in Medical Image Segmentation
Figure 3 for Localized Region Contrast for Enhancing Self-Supervised Learning in Medical Image Segmentation
Figure 4 for Localized Region Contrast for Enhancing Self-Supervised Learning in Medical Image Segmentation
Viaarxiv icon

Ambiguity in solving imaging inverse problems with deep learning based operators

May 31, 2023
Davide Evangelista, Elena Morotti, Elena Loli Piccolomini, James Nagy

Figure 1 for Ambiguity in solving imaging inverse problems with deep learning based operators
Figure 2 for Ambiguity in solving imaging inverse problems with deep learning based operators
Figure 3 for Ambiguity in solving imaging inverse problems with deep learning based operators
Figure 4 for Ambiguity in solving imaging inverse problems with deep learning based operators
Viaarxiv icon

RaSP: Relation-aware Semantic Prior for Weakly Supervised Incremental Segmentation

May 31, 2023
Subhankar Roy, Riccardo Volpi, Gabriela Csurka, Diane Larlus

Figure 1 for RaSP: Relation-aware Semantic Prior for Weakly Supervised Incremental Segmentation
Figure 2 for RaSP: Relation-aware Semantic Prior for Weakly Supervised Incremental Segmentation
Figure 3 for RaSP: Relation-aware Semantic Prior for Weakly Supervised Incremental Segmentation
Figure 4 for RaSP: Relation-aware Semantic Prior for Weakly Supervised Incremental Segmentation
Viaarxiv icon

Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models

Jun 01, 2023
Sivan Doveh, Assaf Arbelle, Sivan Harary, Roei Herzig, Donghyun Kim, Paola Cascante-bonilla, Amit Alfassy, Rameswar Panda, Raja Giryes, Rogerio Feris, Shimon Ullman, Leonid Karlinsky

Figure 1 for Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models
Figure 2 for Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models
Figure 3 for Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models
Figure 4 for Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models
Viaarxiv icon

PanFlowNet: A Flow-Based Deep Network for Pan-sharpening

May 16, 2023
Gang Yang, Xiangyong Cao, Wenzhe Xiao, Man Zhou, Aiping Liu, Xun chen, Deyu Meng

Figure 1 for PanFlowNet: A Flow-Based Deep Network for Pan-sharpening
Figure 2 for PanFlowNet: A Flow-Based Deep Network for Pan-sharpening
Figure 3 for PanFlowNet: A Flow-Based Deep Network for Pan-sharpening
Figure 4 for PanFlowNet: A Flow-Based Deep Network for Pan-sharpening
Viaarxiv icon