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

Hello Everyone!
We are back with another talk for the month of December!
What are we talking about this time?
Transfer/Low-shot/Semi/Unsupervised Learning, Recognition and classification
We are discussing the paper 'Discriminative Region-based Multi-Label Zero-Shot Learning ’ accepted at ICCV 2021 with Akshita Gupta on Saturday, Dec 11 2021, 7:00pm IST/ 8:30am EST.

Register here!
Read the paper!

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. The enriched region-level features are then mapped to the class semantics and only their class predictions are spatially pooled to obtain image- level predictions, thereby keeping the multi-class features disentangled. Our approach sets a new state of the art on two large-scale multi-label zero-shot benchmarks: NUS- WIDE and Open Images. On NUS-WIDE, our approach achieves an absolute gain of 6.9% mAP for ZSL, compared to the best published results.

Akshita Gupta is a Research Engineer at the Inception Institute of Artificial Intelligence. She serves as a reviewer for various vision conferences like CVPR and ICCV. She has worked as an Outreachy intern at Mozilla in 2018. She completed her Bachelor’s degree from DIT University and, during that time, she studied a semester at Indian Institute of Technology, Roorkee.

Till next time,
Happy Winters!
Keep reading papers and join us to discuss all your doubts!
Team CVT