InvGC: Robust Cross-Modal Retrieval by Inverse Graph Convolution

October 20, 2023 ยท Entered Twilight ยท ๐Ÿ› Conference on Empirical Methods in Natural Language Processing

๐Ÿ’ค TWILIGHT: Eternal Rest
Repo abandoned since publication

Repo contents: .gitignore, DBNorm, InvGC, LICENSE, README.md

Authors Xiangru Jian, Yimu Wang arXiv ID 2310.13276 Category cs.CV: Computer Vision Cross-listed cs.CL, cs.LG, cs.MM Citations 6 Venue Conference on Empirical Methods in Natural Language Processing Repository https://github.com/yimuwangcs/Better_Cross_Modal_Retrieval โญ 6 Last Checked 1 month ago
Abstract
Over recent decades, significant advancements in cross-modal retrieval are mainly driven by breakthroughs in visual and linguistic modeling. However, a recent study shows that multi-modal data representations tend to cluster within a limited convex cone (as representation degeneration problem), which hinders retrieval performance due to the inseparability of these representations. In our study, we first empirically validate the presence of the representation degeneration problem across multiple cross-modal benchmarks and methods. Next, to address it, we introduce a novel method, called InvGC, a post-processing technique inspired by graph convolution and average pooling. Specifically, InvGC defines the graph topology within the datasets and then applies graph convolution in a subtractive manner. This method effectively separates representations by increasing the distances between data points. To improve the efficiency and effectiveness of InvGC, we propose an advanced graph topology, LocalAdj, which only aims to increase the distances between each data point and its nearest neighbors. To understand why InvGC works, we present a detailed theoretical analysis, proving that the lower bound of recall will be improved after deploying InvGC. Extensive empirical results show that InvGC and InvGC w/LocalAdj significantly mitigate the representation degeneration problem, thereby enhancing retrieval performance. Our code is available at https://github.com/yimuwangcs/Better_Cross_Modal_Retrieval
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Computer Vision