The reviewed record of science sign in
Pith

arxiv: 2309.17205 · v1 · pith:XU3U2RIE · submitted 2023-09-29 · cs.CV

Towards Complex-query Referring Image Segmentation: A Novel Benchmark

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:XU3U2RIErecord.jsonopen to challenge →

classification cs.CV
keywords complexexistingqueriesris-cqalgorithmsbeenbenchmarkblack
0
0 comments X
read the original abstract

Referring Image Understanding (RIS) has been extensively studied over the past decade, leading to the development of advanced algorithms. However, there has been a lack of research investigating how existing algorithms should be benchmarked with complex language queries, which include more informative descriptions of surrounding objects and backgrounds (\eg \textit{"the black car."} vs. \textit{"the black car is parking on the road and beside the bus."}). Given the significant improvement in the semantic understanding capability of large pre-trained models, it is crucial to take a step further in RIS by incorporating complex language that resembles real-world applications. To close this gap, building upon the existing RefCOCO and Visual Genome datasets, we propose a new RIS benchmark with complex queries, namely \textbf{RIS-CQ}. The RIS-CQ dataset is of high quality and large scale, which challenges the existing RIS with enriched, specific and informative queries, and enables a more realistic scenario of RIS research. Besides, we present a nichetargeting method to better task the RIS-CQ, called dual-modality graph alignment model (\textbf{\textsc{DuMoGa}}), which outperforms a series of RIS methods.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.