LOCL: Learning Object-Attribute Composition using Localization
Not on the map. Why?
Abstract (arXiv)
This paper describes LOCL (Learning Object Attribute Composition using Localization) that generalizes composition zero shot learning to objects in cluttered and more realistic settings. The problem of unseen Object Attribute (OA) associations has been well studied in the field, however, the performance of existing methods is limited in challenging scenes. In this context, our key contribution is a modular approach to localizing objects and attributes of interest in a weakly supervised context that generalizes robustly to unseen configurations. Localization coupled with a composition classifier significantly outperforms state of the art (SOTA) methods, with an improvement of about 12% on currently available challenging datasets. Further, the modularity enables the use of localized feature extractor to be used with existing OA compositional learning methods to improve their overall performance.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 27 of its 37 references that are in the map. First posted on arXiv 7 Oct 2022.
Builds on
27 of 37 references.
References · 27
- 2017Attention Is All You Needcited by 59,932
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
- 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,646
- 2015Spatial Transformer Networkscited by 1,423
- 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,421
- 2019Contrastive Multiview Codingcited by 1,297
- 2019Task-Driven Modular Networks for Zero-Shot Compositional Learningcited by 121
- 2020VSGNet: Spatial Attention Network for Detecting Human Object Interactions Using Graph Convolutionscited by 115
- 2021Learning Graph Embeddings for Compositional Zero-shot Learningcited by 112
- 2021Open World Compositional Zero-Shot Learningcited by 100
15 more
- 2020Symmetry and Group in Attribute-Object Compositionscited by 89
- 2020A causal view of compositional zero-shot recognitioncited by 78
- 2021Learning Graph Embeddings for Open World Compositional Zero-Shot Learningcited by 49
- 2016Weakly Supervised Cascaded Convolutional Networkscited by 47
- 2016Semantic Jitter: Dense Supervision for Visual Comparisons via Synthetic Imagescited by 45
- 2021Independent Prototype Propagation for Zero-Shot Compositionalitycited by 42
- 2016ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localizationcited by 39
- 2022What to look at and where: Semantic and Spatial Refined Transformer for detecting human-object interactionscited by 35
- 2021Relation-aware Compositional Zero-shot Learning for Attribute-Object Pair Recognitioncited by 19
- 2021Zero-Shot Compositional Concept Learningcited by 16
- 2019Recognizing Part Attributes with Insufficient Datacited by 12
- 2020Multiple instance learning on deep features for weakly supervised object detection with extreme domain shiftscited by 10
- 2021GTNet:Guided Transformer Network for Detecting Human-Object Interactionscited by 8
- 2020StressNet: Detecting Stress in Thermal Videoscited by 6
- 2022Context-Driven Detection of Invertebrate Species in Deep-Sea Videocited by 6
Built on by
Citing papers per year: 2023: 3.
3 papers.