English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Recognition of remote sensing (RS) or aerial images is currently of greatinterest, and advancements in deep learning algorithms added flavor to it inrecent years. Occlusion, intra-class variance, lighting, etc., might arisewhile training neural networks using unimodal RS visual input. Even thoughjoint training of audio-visual modalities improves classification performancein a low-data regime, it has yet to be thoroughly investigated in the RSdomain. Here, we aim to solve a novel problem where both the audio and visualmodalities are present during the meta-training of a few-shot learning (FSL)classifier; however, one of the modalities might be missing during themeta-testing stage. This problem formulation is pertinent in the RS domain,given the difficulties in data acquisition or sensor malfunctioning. Tomitigate, we propose a novel few-shot generative framework, HallucinatedAudio-Visual Embeddings-Network (HAVE-Net), to meta-train cross-modal featuresfrom limited unimodal data. Precisely, these hallucinated features aremeta-learned from base classes and used for few-shot classification on novelclasses during the inference phase. The experimental results on the benchmarkADVANCE and AudioSetZSL datasets show that our hallucinated modalityaugmentation strategy for few-shot classification outperforms the classifierperformance trained with the real multimodal information at least by 0.8-2%.

HAVE-Net: Hallucinated Audio-Visual Embeddings for Few-Shot Classification with Unimodal Cues