Search Results for author:
Found 10 papers, 5 papers with code
MaskConver: Revisiting Pure Convolution Model for Panoptic Segmentation
With ResNet50 backbone, our MaskConver achieves 53. 6% PQ on the COCO panoptic val set, outperforming the modern convolution-based model, Panoptic FCN, by 9. 3% as well as transformer-based models such as Mask2Former (+1. 7% PQ) and kMaX-DeepLab (+0. 6% PQ).
Ranked #8 on
Panoptic Segmentation
on COCO test-dev
MARS: A Motif-based Autoregressive Model for Retrosynthesis Prediction
In this paper, we propose a novel end-to-end graph generation model for retrosynthesis prediction, which sequentially identifies the reaction center, generates the synthons, and adds motifs to the synthons to generate reactants.
RetroComposer: Composing Templates for Template-Based Retrosynthesis Prediction
To overcome this limitation, we propose an innovative retrosynthesis prediction framework that can compose novel templates beyond training templates.
Ranked #8 on
Single-step retrosynthesis
on USPTO-50k
Bridging the Gap Between Object Detection and User Intent via Query-Modulation
When interacting with objects through cameras, or pictures, users often have a specific intent.
Hierarchical Graph Capsule Network
Graph Neural Networks (GNNs) draw their strength from explicitly modeling the topological information of structured data.
RetroXpert: Decompose Retrosynthesis Prediction like a Chemist
Retrosynthesis is the process of recursively decomposing target molecules into available building blocks.
Label-Driven Reconstruction for Domain Adaptation in Semantic Segmentation
Unsupervised domain adaptation enables to alleviate the need for pixel-wise annotation in the semantic segmentation.
Ranked #26 on
Domain Adaptation
on SYNTHIA-to-Cityscapes
Context-Aware Domain Adaptation in Semantic Segmentation
To achieve this goal, we design two cross-domain attention modules to adapt context dependencies from both spatial and channel views.
Ranked #27 on
Domain Adaptation
on SYNTHIA-to-Cityscapes
Re-balancing Variational Autoencoder Loss for Molecule Sequence Generation
We investigate the posterior collapse problem of current RNN-based VAEs for molecule sequence generation.
Weakly Supervised Deep Learning for Thoracic Disease Classification and Localization on Chest X-rays
Chest X-rays is one of the most commonly available and affordable radiological examinations in clinical practice.
