# Focus-Consistent Multi-Level Aggregation for Compositional Zero-Shot Learning

arXiv: https://arxiv.org/abs/2408.17083 · HTML: https://mlsanity.com/paper/2408.17083/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 34 of its 52 references that are in the map.
- First posted on arXiv 30 Aug 2024.

## Builds on (most cited first, 30 of 34)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Deeper, Broader and Artier Domain Generalization](https://mlsanity.com/paper/1710.03077/) (2017)
- [Generalizing to Unseen Domains: A Survey on Domain Generalization](https://mlsanity.com/paper/2103.03097/) (2021)
- [Understanding Neural Networks Through Deep Visualization](https://mlsanity.com/paper/1506.06579/) (2015)
- [Zero-Shot Learning -- The Good, the Bad and the Ugly](https://mlsanity.com/paper/1703.04394/) (2017)
- [An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild](https://mlsanity.com/paper/1605.04253/) (2016)
- [Task-Driven Modular Networks for Zero-Shot Compositional Learning](https://mlsanity.com/paper/1905.05908/) (2019)
- [Learning Graph Embeddings for Compositional Zero-shot Learning](https://mlsanity.com/paper/2102.01987/) (2021)
- [Open World Compositional Zero-Shot Learning](https://mlsanity.com/paper/2101.12609/) (2021)
- [Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection](https://mlsanity.com/paper/1708.02001/) (2017)
- [Symmetry and Group in Attribute-Object Compositions](https://mlsanity.com/paper/2004.00587/) (2020)
- [A causal view of compositional zero-shot recognition](https://mlsanity.com/paper/2006.14610/) (2020)
- [Multi-level Feature Learning for Contrastive Multi-view Clustering](https://mlsanity.com/paper/2106.11193/) (2021)
- [Disentangling Visual Embeddings for Attributes and Objects](https://mlsanity.com/paper/2205.08536/) (2022)
- [Siamese Contrastive Embedding Network for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2206.14475/) (2022)
- [Effective Aesthetics Prediction with Multi-level Spatially Pooled Features](https://mlsanity.com/paper/1904.01382/) (2019)
- [Shape or Texture: Understanding Discriminative Features in CNNs](https://mlsanity.com/paper/2101.11604/) (2021)
- [Learning Graph Embeddings for Open World Compositional Zero-Shot Learning](https://mlsanity.com/paper/2105.01017/) (2021)
- [Independent Prototype Propagation for Zero-Shot Compositionality](https://mlsanity.com/paper/2106.00305/) (2021)
- [KG-SP: Knowledge Guided Simple Primitives for Open World Compositional Zero-Shot Learning](https://mlsanity.com/paper/2205.06784/) (2022)
- [Attention Consistency on Visual Corruptions for Single-Source Domain Generalization](https://mlsanity.com/paper/2204.13091/) (2022)
- [Multi-Level Bottom-Top and Top-Bottom Feature Fusion for Crowd Counting](https://mlsanity.com/paper/1908.10937/) (2019)
- [Learning Conditional Attributes for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2305.17940/) (2023)
- [Enhancing Self-supervised Video Representation Learning via Multi-level Feature Optimization](https://mlsanity.com/paper/2108.02183/) (2021)
- [Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2303.15230/) (2023)

## Abstract (arXiv)

To transfer knowledge from seen attribute-object compositions to recognize unseen ones, recent compositional zero-shot learning (CZSL) methods mainly discuss the optimal classification branches to identify the elements, leading to the popularity of employing a three-branch architecture. However, these methods mix up the underlying relationship among the branches, in the aspect of consistency and diversity. Specifically, consistently providing the highest-level features for all three branches increases the difficulty in distinguishing classes that are superficially similar. Furthermore, a single branch may focus on suboptimal regions when spatial messages are not shared between the personalized branches. Recognizing these issues and endeavoring to address them, we propose a novel method called Focus-Consistent Multi-Level Aggregation (FOMA). Our method incorporates a Multi-Level Feature Aggregation (MFA) module to generate personalized features for each branch based on the image content. Additionally, a Focus-Consistent Constraint encourages a consistent focus on the informative regions, thereby implicitly exchanging spatial information between all branches. Extensive experiments on three benchmark datasets (UT-Zappos, C-GQA, and Clothing16K) demonstrate that our FOMA outperforms SOTA.