Related papers: Frozen Vision Transformers for Dense Prediction on…

We demonstrate the feasibility of a fully automatic computer-aided diagnosis (CAD) tool, based on deep learning, that localizes and classifies proximal femur fractures on X-ray images according to the AO classification. The proposed…

Vision transformer has emerged as a new paradigm in computer vision, showing excellent performance while accompanied by expensive computational cost. Image token pruning is one of the main approaches for ViT compression, due to the facts…

Real-time single-stage object detectors based on deep learning still remain less accurate than more complex ones. The trade-off between model performance and computational speed is a major challenge. In this paper, we propose a new way to…

Generalization under manipulation and dataset shift remains a core challenge in forged media detection for AI-driven edge sensing systems. Frozen vision foundation models with linear probes are strong baselines, but most pipelines use…

We introduce Patch Refinement a two-stage model for accurate 3D object detection and localization from point cloud data. Patch Refinement is composed of two independently trained Voxelnet-based networks, a Region Proposal Network (RPN) and…

The encoding of the target in object tracking moves from the coarse bounding-box to fine-grained segmentation map recently. Revisiting de facto real-time approaches that are capable of predicting mask during tracking, we observed that they…

Infrared small target detection based on deep learning offers unique advantages in separating small targets from complex and dynamic backgrounds. However, the features of infrared small targets gradually weaken as the depth of convolutional…

Vision-based Transformer have shown huge application in the perception module of autonomous driving in terms of predicting accurate 3D bounding boxes, owing to their strong capability in modeling long-range dependencies between the visual…

We introduce dense vision transformers, an architecture that leverages vision transformers in place of convolutional networks as a backbone for dense prediction tasks. We assemble tokens from various stages of the vision transformer into…

During benchmarking, the state-of-the-art model for glacier calving front delineation achieves near-human performance. However, when applied in a real-world setting at a novel study site, its delineation accuracy is insufficient for calving…

The highest accuracy object detectors to date are based on a two-stage approach popularized by R-CNN, where a classifier is applied to a sparse set of candidate object locations. In contrast, one-stage detectors that are applied over a…

The ImageNet pre-training initialization is the de-facto standard for object detection. He et al. found it is possible to train detector from scratch(random initialization) while needing a longer training schedule with proper normalization…

We study a crucial yet often overlooked issue inherent to Vision Transformers (ViTs): feature maps of these models exhibit grid-like artifacts, which hurt the performance of ViTs in downstream dense prediction tasks such as semantic…

Consistent in-focus input imagery is an essential precondition for machine vision systems to perceive the dynamic environment. A defocus blur severely degrades the performance of vision systems. To tackle this problem, we propose a…

Recent advances in training vision-language models have demonstrated unprecedented robustness and transfer learning effectiveness; however, standard computer vision datasets are image-only, and therefore not well adapted to such training…

Deep learning models are transforming agricultural applications by enabling automated phenotyping, monitoring, and yield estimation. However, their effectiveness heavily depends on large amounts of annotated training data, which can be…

Vision Transformers trained only on image classification routinely transfer to tasks that demand spatial understanding, yet they receive no spatial supervision during pretraining. We ask where and how robustly such structure is encoded.…

Motivated by the remarkable achievements of DETR-based approaches on COCO object detection and segmentation benchmarks, recent endeavors have been directed towards elevating their performance through self-supervised pre-training of…

Shack Hartmann wavefront sensor is a two dimensional array of lenslets which is used to detect the incoming phase distorted wavefront through local tilt measurements made by recording the spot pattern near the focal plane. Wavefront…

State-of-the-art vessel segmentation methods typically require large-scale annotated datasets and suffer from severe performance degradation under domain shifts. In clinical practice, however, acquiring extensive annotations for every new…