Diffusiondet: Diffusion model for object detection

S Chen, P Sun, Y Song, P Luo - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
We propose DiffusionDet, a new framework that formulates object detection as a denoising
diffusion process from noisy boxes to object boxes. During the training stage, object boxes …

Resnet strikes back: An improved training procedure in timm

R Wightman, H Touvron, H Jégou - ar** and tissue domain segmentation for scalable spatial omics data analysis
V Singhal, N Chou, J Lee, Y Yue, J Liu, WK Chock… - Nature Genetics, 2024 - nature.com
Spatial omics data are clustered to define both cell types and tissue domains. We present
Building Aggregates with a Neighborhood Kernel and Spatial Yardstick (BANKSY), an …

Multimodal fake news detection through data augmentation-based contrastive learning

J Hua, X Cui, X Li, K Tang, P Zhu - Applied Soft Computing, 2023 - Elsevier
During the information exploding era, news can be created or edited purposely for
promoting the spreading of social influence. However, unverified or fabricated news can …

IDSN: A one-stage interpretable and differentiable STFT domain adaptation network for traction motor of high-speed trains cross-machine diagnosis

C He, H Shi, J Li - Mechanical Systems and Signal Processing, 2023 - Elsevier
A surge of transfer fault diagnosis techniques has been proposed to guarantee the safe
operation of traction motor systems. However, existing efforts highly depend on the …

The worst of both worlds: A comparative analysis of errors in learning from data in psychology and machine learning

J Hullman, S Kapoor, P Nanayakkara… - Proceedings of the …, 2022 - dl.acm.org
Arguments that machine learning (ML) is facing a reproducibility and replication crisis
suggest that some published claims in research cannot be taken at face value. Concerns …

Evidence of questionable research practices in clinical prediction models

N White, R Parsons, G Collins, A Barnett - BMC medicine, 2023 - Springer
Background Clinical prediction models are widely used in health and medical research. The
area under the receiver operating characteristic curve (AUC) is a frequently used estimate to …

Augmenting convolutional networks with attention-based aggregation

H Touvron, M Cord, A El-Nouby, P Bojanowski… - arxiv preprint arxiv …, 2021 - arxiv.org
We show how to augment any convolutional network with an attention-based global map to
achieve non-local reasoning. We replace the final average pooling by an attention-based …

Learned queries for efficient local attention

M Arar, A Shamir, AH Bermano - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
Abstract Vision Transformers (ViT) serve as powerful vision models. Unlike convolutional
neural networks, which dominated vision research in previous years, vision transformers …

If at First You Don't Succeed, Try, Try Again: Faithful Diffusion-based Text-to-Image Generation by Selection

S Karthik, K Roth, M Mancini, Z Akata - arxiv preprint arxiv:2305.13308, 2023 - arxiv.org
Despite their impressive capabilities, diffusion-based text-to-image (T2I) models can lack
faithfulness to the text prompt, where generated images may not contain all the mentioned …