Discriminative Region-based Multi-Label Zero-Shot Learning
ICCV 2021

Paperswithcode Badges

overview

Our proposed approach achieves state-of-the-art for ZSL and GZSL tasks (as seen from the above badges). Please do consider adding recent ZSL or GZSL results to the same.

Video

Abstract

Multi-label zero-shot learning (ZSL) is a more realistic counter-part of standard single-label ZSL since several objects can co-exist in a natural image. However, the occurrence of multiple objects complicates the reasoning and requires region-specific processing of visual features to preserve their contextual cues. We note that the best existing multi-label ZSL method takes a shared approach towards attending to region features with a common set of attention maps for all the classes. Such shared maps lead to diffused attention, which does not discriminatively focus on relevant locations when the number of classes are large. Moreover, mapping spatially-pooled visual features to the class semantics leads to inter-class feature entanglement, thus hampering the classification. Here, we propose an alternate approach towards region-based discriminability- preserving multi-label zero-shot classification. Our approach maintains the spatial resolution to preserve region-level characteristics and utilizes a bi-level attention module (BiAM) to enrich the features by incorporating both region and scene context information.

overview

Attention Visualization

Below you will find qualitative results with attention maps for (generalized) zero-shot classification. For each image, class-specific maps for the ground truth unseen classes are shown with the corresponding labels on top.


overview
overview

Citation