-
Rethinking Visual Relationships for High-level Image Understanding
Relationships, as the bond of isolated entities in images, reflect the i...
read it
-
Scene Graph Generation via Conditional Random Fields
Despite the great success object detection and segmentation models have ...
read it
-
Unbiased Scene Graph Generation from Biased Training
Today's scene graph generation (SGG) task is still far from practical, m...
read it
-
PCPL: Predicate-Correlation Perception Learning for Unbiased Scene Graph Generation
Today, scene graph generation(SGG) task is largely limited in realistic ...
read it
-
Learning to Compose Dynamic Tree Structures for Visual Contexts
We propose to compose dynamic tree structures that place the objects in ...
read it
-
Long-tail Visual Relationship Recognition with a Visiolinguistic Hubless Loss
Scaling up the vocabulary and complexity of current visual understanding...
read it
-
Knowledge-Embedded Routing Network for Scene Graph Generation
To understand a scene in depth not only involves locating/recognizing in...
read it
CogTree: Cognition Tree Loss for Unbiased Scene Graph Generation
Scene graphs are semantic abstraction of images that encourage visual understanding and reasoning. However, the performance of Scene Graph Generation (SGG) is unsatisfactory when faced with biased data in real-world scenarios. Conventional debiasing research mainly studies from the view of data representation, e.g. balancing data distribution or learning unbiased models and representations, ignoring the mechanism that how humans accomplish this task. Inspired by the role of the prefrontal cortex (PFC) in hierarchical reasoning, we analyze this problem from a novel cognition perspective: learning a hierarchical cognitive structure of the highly-biased relationships and navigating that hierarchy to locate the classes, making the tail classes receive more attention in a coarse-to-fine mode. To this end, we propose a novel Cognition Tree (CogTree) loss for unbiased SGG. We first build a cognitive structure CogTree to organize the relationships based on the prediction of a biased SGG model. The CogTree distinguishes remarkably different relationships at first and then focuses on a small portion of easily confused ones. Then, we propose a hierarchical loss specially for this cognitive structure, which supports coarse-to-fine distinction for the correct relationships while progressively eliminating the interference of irrelevant ones. The loss is model-independent and can be applied to various SGG models without extra supervision. The proposed CogTree loss consistently boosts the performance of several state-of-the-art models on the Visual Genome benchmark.
READ FULL TEXT
Comments
There are no comments yet.