Seq-SG2SL: Inferring Semantic Layout from Scene Graph Through Sequence to Sequence Learning
This work addresses a specific bottleneck in text-to-image generation for computer vision applications, but it is incremental as it adapts existing seq-to-seq techniques to a new task.
The paper tackles the problem of generating semantic layouts from scene graphs, a key step in text-to-image synthesis, by proposing Seq-SG2SL, a sequence-to-sequence learning framework that improves over non-sequential methods on the Visual Genome dataset.
Generating semantic layout from scene graph is a crucial intermediate task connecting text to image. We present a conceptually simple, flexible and general framework using sequence to sequence (seq-to-seq) learning for this task. The framework, called Seq-SG2SL, derives sequence proxies for the two modality and a Transformer-based seq-to-seq model learns to transduce one into the other. A scene graph is decomposed into a sequence of semantic fragments (SF), one for each relationship. A semantic layout is represented as the consequence from a series of brick-action code segments (BACS), dictating the position and scale of each object bounding box in the layout. Viewing the two building blocks, SF and BACS, as corresponding terms in two different vocabularies, a seq-to-seq model is fittingly used to translate. A new metric, semantic layout evaluation understudy (SLEU), is devised to evaluate the task of semantic layout prediction inspired by BLEU. SLEU defines relationships within a layout as unigrams and looks at the spatial distribution for n-grams. Unlike the binary precision of BLEU, SLEU allows for some tolerances spatially through thresholding the Jaccard Index and is consequently more adapted to the task. Experimental results on the challenging Visual Genome dataset show improvement over a non-sequential approach based on graph convolution.