computer-vision-1

set matching

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in set-matching-1

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find set-matching-1 models and implementations

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

DETRs with Hybrid Matching

Hao He, Yuhui Yuan, Ding Jia, Xiao-pei Wu, Haojun Yu, Weihong Lin, Lei-huan Sun, Chao Zhang, Hanhua Hu•Mon Jul 25 2022

A simple yet effective method based on a hybrid matching scheme that combines the original one-to-one matching branch with an auxiliary one- to-many matching branch during training that shows that a wide range of representative DETR methods can be consistently improved across a widerange of visual tasks.

272

Content

0

Paper Graph

Exchangeable Deep Neural Networks for Set-to-Set Matching and Learning

Takuma Nakamura, Yuki Saito, Hirotaka Hachiya, K. Fukumizu•Wed Nov 18 2020

A novel deep learning architecture to address the abovementioned difficulties and also an efficient training framework for set-to-set matching is proposed and evaluated through experiments based on two industrial applications: fashion set recommendation and group re-identification.

16 0

Paper Graph

More Than Meets The Eye: Semi-supervised Learning Under Non-IID Data

Luis Oala, Saúl Calderón Ramírez•Mon Apr 19 2021

It is demonstrated that simple density based dissimilarity measures in the feature space of a generic classifier offer a promising and more reliable quantitative matching criterion to select unlabelled data before SSDL training.

5 0

Paper Graph

SHIFT15M: Fashion-specific dataset for set-to-set matching with several distribution shifts

Masanari Kimura, Takuma Nakamura, Yuki Saito•Sun Aug 29 2021

This paper proposes SHIFT15M, a dataset that can be used to properly evaluate set-to-set matching models in situations where the distribution of data changes between training and testing.

3 0

Paper Graph

DETRs with Collaborative Hybrid Assignments Training

Guanglu Song, Zhuofan Zong, Yu Liu•Mon Nov 21 2022

A novel collaborative hybrid assignments training scheme, namely Co - DETR, to learn more efficient and effective DETR-based detectors from versatile label assignment manners to enhance the encoder’s learning ability in end-to-end detectors.

535 0

Paper Graph

Learning-Based Efficient Graph Similarity Computation via Multi-Scale Convolutional Set Matching

Yunsheng Bai, Haoyang Ding, Ken Gu, Yizhou Sun•Sun Sep 09 2018

The model, Graph-Sim, achieves the state-of-the-art performance on four real-world graph datasets under six out of eight settings, compared to existing popular methods for approximate Graph Edit Distance (GED) and Maximum Common Subgraph (MCS) computation.

124 0

Paper Graph

Convolutional Set Matching for Graph Similarity

Wei Wang, Yunsheng Bai, Haoyang Ding, Yizhou Sun•Mon Oct 22 2018

This work introduces GSimCNN (Graph Similarity Computation via Convolutional Neural Networks) for predicting the similarity score between two graphs and demonstrates that the model achieves the state-of-the-art performance on graph similarity search.

39 0

Paper Graph

FreebaseQA: A New Factoid QA Data Set Matching Trivia-Style Question-Answer Pairs with Freebase

Dekun Wu, Kelvin Jiang, Hui Jiang•Fri May 31 2019

This data set, named FreebaseQA, is generated by matching trivia-type question-answer pairs with subject-predicate-object triples in Freebase to generate over 54K matches from about 28K unique questions with minimal cost.

93 0

Paper Graph

The CAT SET on the MAT: Cross Attention for Set Matching in Bipartite Hypergraphs

Govind Sharma, Swyam Prakash Singh, V. Devi, M. Murty•Fri Oct 29 2021

This work poses bipartite hyperedge link prediction as a set-matching (SETMAT) problem and proposes a novel neural network architecture called CATSETMAT for the same, which is compared with multiple techniques from the state-of-the-art.

2 0

Paper Graph

Adding a benchmark result helps the community track progress.