Transformer-based visual segmentation: A survey
Visual segmentation seeks to partition images, video frames, or point clouds into multiple
segments or groups. This technique has numerous real-world applications, such as …
segments or groups. This technique has numerous real-world applications, such as …
Da-detr: Domain adaptive detection transformer with information fusion
The recent detection transformer (DETR) simplifies the object detection pipeline by removing
hand-crafted designs and hyperparameters as employed in conventional two-stage object …
hand-crafted designs and hyperparameters as employed in conventional two-stage object …
Position-aware structure learning for graph topology-imbalance by relieving under-reaching and over-squashing
Topology-imbalance is a graph-specific imbalance problem caused by the uneven topology
positions of labeled nodes, which significantly damages the performance of GNNs. What …
positions of labeled nodes, which significantly damages the performance of GNNs. What …
Exploring sparse visual prompt for cross-domain semantic segmentation
Visual Domain Prompts (VDP) have shown promising potential in addressing visual cross-
domain problems. Existing methods adopt VDP in classification domain adaptation (DA) …
domain problems. Existing methods adopt VDP in classification domain adaptation (DA) …
Lightweight Deep Learning for Resource-Constrained Environments: A Survey
Over the past decade, the dominance of deep learning has prevailed across various
domains of artificial intelligence, including natural language processing, computer vision …
domains of artificial intelligence, including natural language processing, computer vision …
Hyperbolic geometric graph representation learning for hierarchy-imbalance node classification
Learning unbiased node representations for imbalanced samples in the graph has become
a more remarkable and important topic. For the graph, a significant challenge is that the …
a more remarkable and important topic. For the graph, a significant challenge is that the …
Masked retraining teacher-student framework for domain adaptive object detection
Abstract Domain adaptive Object Detection (DAOD) leverages a labeled domain (source) to
learn an object detector generalizing to a novel domain without annotation (target). Recent …
learn an object detector generalizing to a novel domain without annotation (target). Recent …
DA-DETR: Domain Adaptive Detection Transformer with Information Fusion
The recent detection transformer (DETR) simplifies the object detection pipeline by removing
hand-crafted designs and hyperparameters as employed in conventional two-stage object …
hand-crafted designs and hyperparameters as employed in conventional two-stage object …
[HTML][HTML] Colorectal cancer lymph node metastasis prediction with weakly supervised transformer-based multi-instance learning
Lymph node metastasis examined by the resected lymph nodes is considered one of the
most important prognostic factors for colorectal cancer (CRC). However, it requires careful …
most important prognostic factors for colorectal cancer (CRC). However, it requires careful …
GPA-3D: Geometry-aware Prototype Alignment for Unsupervised Domain Adaptive 3D Object Detection from Point Clouds
Z Li, J Guo, T Cao, L Bingbing… - Proceedings of the …, 2023 - openaccess.thecvf.com
LiDAR-based 3D detection has made great progress in recent years. However, the
performance of 3D detectors is considerably limited when deployed in unseen …
performance of 3D detectors is considerably limited when deployed in unseen …