SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1712.01928 · 2017

Zero-Shot Visual Recognition using Semantics-Preserving Adversarial Embedding Networks

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We propose a novel framework called Semantics-Preserving Adversarial Embedding Network (SP-AEN) for zero-shot visual recognition (ZSL), where test images and their classes are both unseen during training. SP-AEN aims to tackle the inherent problem --- semantic loss --- in the prevailing family of embedding-based ZSL, where some semantics would be discarded during training if they are non-discriminative for training classes, but could become critical for recognizing test classes. Specifically, SP-AEN prevents the semantic loss by introducing an independent visual-to-semantic space embedder which disentangles the semantic space into two subspaces for the two arguably conflicting objectives: classification and reconstruction. Through adversarial learning of the two subspaces, SP-AEN can transfer the semantics from the reconstructive subspace to the discriminative one, accomplishing the improved zero-shot recognition of unseen classes. Comparing with prior works, SP-AEN can not only improve classification but also generate photo-realistic images, demonstrating the effectiveness of semantic preservation. On four popular benchmarks: CUB, AWA, SUN and aPY, SP-AEN considerably outperforms other state-of-the-art methods by an absolute performance difference of 12.2\%, 9.3\%, 4.0\%, and 3.6\% in terms of harmonic mean values

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1712.01928")
get_code_for_paper("1712.01928")
have("1712.01928")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1712.01928.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1712.01928.svg)](https://syntology.ai/paper/1712.01928)

Connect an agent — have() is free.