94 citations · 104 across the 5 of their papers we have counts for
5 papers
USD: Unknown Sensitive Detector Empowered by Decoupled Objectness and Segment Anything Model
Yulin He, Wei Chen, Yusong Tan +1
Open World Object Detection (OWOD) is a novel and challenging computer vision task that enables object detection with the ability to detect unknown objects. Existing methods typica…
LNL+K: Enhancing Learning with Noisy Labels Through Noise Source Knowledge Integration
Siqi Wang, Bryan A. Plummer
Learning with noisy labels (LNL) aims to train a high-performing model using a noisy dataset. We observe that noise for a given class often comes from a limited set of categories,…
Cross-modal Contrastive Learning for Multimodal Fake News Detection
Longzheng Wang, Chuang Zhang, Hongbo Xu +3
Automatic detection of multimodal fake news has gained a widespread attention recently. Many existing approaches seek to fuse unimodal features to produce multimodal news represent…
An Effective Transformer-based Solution for RSNA Intracranial Hemorrhage Detection Competition
Fangxin Shang, Siqi Wang, Xiaorong Wang +1
We present an effective method for Intracranial Hemorrhage Detection (IHD) which exceeds the performance of the winner solution in RSNA-IHD competition (2019). Meanwhile, our model…
Anchoring to Exemplars for Training Mixture-of-Expert Cell Embeddings
Siqi Wang, Manyuan Lu, Nikita Moshkov +2
Analyzing the morphology of cells in microscopy images can provide insights into the mechanism of compounds or the function of genes. Addressing this task requires methods that can…