Graph-guided Cross-composition Feature Disentanglement for Compositional Zero-shot Learning (2025.findings-acl)
Copied to clipboard
Yuxia Geng, Runkai Zhu, Jiaoyan Chen, Jintai Chen, Xiang Chen, Zhuo Chen, Shuofei Qiao, Yuxiang Wang, Xiaoliang Xu, Sheng-Jun Huang
| Challenge: | Disentanglement of visual features of primitives (i.e., attributes and objects) has shown exceptional results in Compositional Zero-shot Learning (CZSL). |
| Approach: | They propose a solution that takes multiple compositions as inputs and constrains disentangled primitive features to be general across compositions. |
| Outcome: | The proposed architecture significantly improves performance on three popular CZSL benchmarks and has been verified by solid ablation studies. |
Similar Papers
DMSD: Dual-Modal Semantic Disentanglement for Compositional Zero-Shot Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Compositional Zero-Shot Learning (CZSL) is a new research paradigm that learns sub-concepts from seen compositions and recognizes unseen novel combinations. |
| Approach: | They propose a Dual-Modal Semantic Disentanglement framework that integrates visual and textual information to achieve effective sub-concept disentangling. |
| Outcome: | The proposed framework achieves state-of-the-art performance on three benchmark datasets . it integrates a class-centroid bridge module to guide class centroids toward the textual space . |
Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing fine-tuning approaches for compositional understanding compromise performance in zero-shot multi-modal tasks. |
| Approach: | They propose a method to enhance compositional understanding in pre-trained vision and language models without sacrificing performance in zero-shot multi-modal tasks. |
| Outcome: | The proposed method achieves compositionality on par with state-of-the-art models and retains strong multi-modal capabilities. |
Disentangled Sequence to Sequence Learning for Compositional Generalization (2022.acl-long)
Copied to clipboard
| Challenge: | Existing models struggle to generalize to unseen compositions of seen components . a new approach allows for disentangled representations and better generalization . |
| Approach: | They propose an extension to sequence-to-sequence models which encourage disentanglement by re-encoding source input. |
| Outcome: | The proposed extension delivers better generalization and more disentangled representations . human expressions can be understood by combining known atomic components . |
Learning to Compose Representations of Different Encoder Layers towards Improving Compositional Generalization (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies show that sequence-to-sequence (seq2sequ) models struggle with compositional generalization (CG) a crucial property of human language learning is its compositional globalization (GC), the algebraic ability to understand and produce a potentially infinite number of novel combinations from known components. |
| Approach: | They propose a sequence-to-sequence (seq2sequ) extension which learns to compose representations of different encoder layers dynamically for different tasks. |
| Outcome: | The proposed model achieves competitive results on two comprehensive and realistic benchmarks, which empirically demonstrates the effectiveness of the proposed model. |
ComCLIP: Training-Free Compositional Image and Text Matching (2024.naacl-long)
Copied to clipboard
| Challenge: | erroneous semantics of individual entities are essentially confounders that cause the matching failure. |
| Approach: | They propose a training-free compositional CLIP model which disentangles input images into subjects, objects, and action subimages and composes CLIP’s vision encoder and text encoder to perform evolving matching over compositional text embedding and subimage embeddments. |
| Outcome: | The proposed model mitigates spurious correlations introduced by the pretrained CLIP models and dynamically evaluates the importance of each component. |
Real-World Compositional Generalization with Disentangled Sequence-to-Sequence Learning (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to compositional generalization have been designed with semantic parsing in mind. |
| Approach: | They propose a disentangled sequence-to-sequence model which encourages more disentanglement and improves its compute and memory efficiency. |
| Outcome: | The proposed model improves generalization performance across existing tasks and datasets and a new machine translation benchmark. |
Zero-Shot Dependency Parsing with Worst-Case Aware Automated Curriculum Learning (2022.acl-short)
Copied to clipboard
| Challenge: | Large multilingual pretrained language models such as mBERT and XLM-RoBERTa have been found to be effective for cross-lingual transfer of syntactic parsing models but only between related languages. |
| Approach: | They propose to use multi-task learning to dynamically optimize for parsing performance on outlier languages by using a multi-level learning approach. |
| Outcome: | The proposed method significantly outperforms uniform and size-proportional sampling in the zero-shot setting. |
Zero-shot Dependency Parsing with Pre-trained Multilingual Sentence Representations (D19-61)
Copied to clipboard
| Challenge: | Pretrained sentence representations have set the new state of the art in many language understanding tasks. |
| Approach: | They propose to use a multilingual corpus to train deep bidirectional sentence representations that are fully lexicalized to allow for the development of an unsupervised universal dependency parser. |
| Outcome: | The proposed approach outperforms the best CoNLL 2018 systems in all of the shared task’s six truly low-resource languages while using a single system. |
Cross-Modal Masked Compositional Concept Modeling for Enhancing Visio-Linguistic Compositionality (2026.acl-long)
Copied to clipboard
| Challenge: | a contrastive learning approach for vision-language models is needed to capture compositional information. |
| Approach: | They propose a framework that masks compositional concepts in one modality and reconstructs them conditioned on full contextual information from the other . |
| Outcome: | The proposed framework enhances compositionality in visual language models and improves their ability to capture syntactic structure and linguistic information. |
Refinement Matters: Textual Description Needs to be Refined for Zero-shot Learning (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Zero-Shot Learning (ZSL) is a new form of learning that uses textual description and attribute to transfer knowledge from seen to unseen classes. |
| Approach: | They propose a non-generative gating-based attribute refinement network for ZSL that uses a circle loss-guided attribute embedder to refine the attributes. |
| Outcome: | The proposed approach outperforms generative methods and most generative ones in all three scenarios. |