Log In Sign Up

TRACE: Transform Aggregate and Compose Visiolinguistic Representations for Image Search with Text Feedback

by   Surgan Jandial, et al.

The ability to efficiently search for images over an indexed database is the cornerstone for several user experiences. Incorporating user feedback, through multi-modal inputs provide flexible and interaction to serve fine-grained specificity in requirements. We specifically focus on text feedback, through descriptive natural language queries. Given a reference image and textual user feedback, our goal is to retrieve images that satisfy constraints specified by both of these input modalities. The task is challenging as it requires understanding the textual semantics from the text feedback and then applying these changes to the visual representation. To address these challenges, we propose a novel architecture TRACE which contains a hierarchical feature aggregation module to learn the composite visio-linguistic representations. TRACE achieves the SOTA performance on 3 benchmark datasets: FashionIQ, Shoes, and Birds-to-Words, with an average improvement of at least  5.7 respectively in R@K metric. Our extensive experiments and ablation studies show that TRACE consistently outperforms the existing techniques by significant margins both quantitatively and qualitatively.


page 4

page 8

page 9

page 10

page 14


Image Search with Text Feedback by Additive Attention Compositional Learning

Effective image retrieval with text feedback stands to impact a range of...

Multi-Modal Reasoning Graph for Scene-Text Based Fine-Grained Image Classification and Retrieval

Scene text instances found in natural images carry explicit semantic inf...

Modality-Agnostic Attention Fusion for visual search with text feedback

Image retrieval with natural language feedback offers the promise of cat...

Comprehensive Multi-Modal Interactions for Referring Image Segmentation

We investigate Referring Image Segmentation (RIS), which outputs a segme...

Learning Granularity-Unified Representations for Text-to-Image Person Re-identification

Text-to-image person re-identification (ReID) aims to search for pedestr...

ROSITA: Enhancing Vision-and-Language Semantic Alignments via Cross- and Intra-modal Knowledge Integration

Vision-and-language pretraining (VLP) aims to learn generic multimodal r...

Teaching Temporal Logics to Neural Networks

We show that a deep neural network can learn the semantics of linear-tim...