Hybrid Knowledge Routed Modules for Large-scale Object Detection

10/30/2018
by   Chenhan Jiang, et al.
0

The dominant object detection approaches treat the recognition of each region separately and overlook crucial semantic correlations between objects in one scene. This paradigm leads to substantial performance drop when facing heavy long-tail problems, where very few samples are available for rare classes and plenty of confusing categories exists. We exploit diverse human commonsense knowledge for reasoning over large-scale object categories and reaching semantic coherency within one image. Particularly, we present Hybrid Knowledge Routed Modules (HKRM) that incorporates the reasoning routed by two kinds of knowledge forms: an explicit knowledge module for structured constraints that are summarized with linguistic knowledge (e.g. shared attributes, relationships) about concepts; and an implicit knowledge module that depicts some implicit constraints (e.g. common spatial layouts). By functioning over a region-to-region graph, both modules can be individualized and adapted to coordinate with visual patterns in each image, guided by specific knowledge forms. HKRM are light-weight, general-purpose and extensible by easily incorporating multiple knowledge to endow any detection networks the ability of global semantic reasoning. Experiments on large-scale object detection benchmarks show HKRM obtains around 34.5 categories) and 30.4 found in https://github.com/chanyn/HKRM.

READ FULL TEXT
research
02/18/2020

Universal-RCNN: Universal Object Detector via Transferable Graph R-CNN

The dominant object detection approaches treat each dataset separately a...
research
06/04/2019

Relational Reasoning using Prior Knowledge for Visual Captioning

Exploiting relationships among objects has achieved remarkable progress ...
research
09/10/2020

RVL-BERT: Visual Relationship Detection with Visual-Linguistic Knowledge from Pre-trained Representations

Visual relationship detection aims to reason over relationships among sa...
research
03/29/2018

Iterative Visual Reasoning Beyond Convolutions

We present a novel framework for iterative visual reasoning. Our framewo...
research
03/02/2021

Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detection

Few-shot object detection is an imperative and long-lasting problem due ...
research
10/25/2019

Heterogeneous Graph Learning for Visual Commonsense Reasoning

Visual commonsense reasoning task aims at leading the research field int...
research
08/07/2020

Polysemy Deciphering Network for Robust Human-Object Interaction Detection

Human-Object Interaction (HOI) detection is important to human-centric s...

Please sign up or login with your details

Forgot password? Click here to reset