Concept Alignment
11 papers with code • 0 benchmarks • 0 datasets
Concept Alignment aims to align the learned representations or concepts within a model with the intended or target concepts. It involves adjusting the model's parameters or training process to ensure that the learned concepts accurately reflect the underlying patterns in the data.
Benchmarks
These leaderboards are used to track progress in Concept Alignment
Most implemented papers
Discovery of Natural Language Concepts in Individual Units of CNNs
Although deep convolutional networks have achieved improved performance in many natural language tasks, they have been treated as black boxes because they are difficult to interpret.
Concept Extraction Using Pointer-Generator Networks
Concept extraction is crucial for a number of downstream applications.
Joint covariate-alignment and concept-alignment: a framework for domain generalization
Particularly, our framework proposes to jointly minimize both the covariate-shift as well as the concept-shift between the seen domains for a better performance on the unseen domain.
CapEnrich: Enriching Caption Semantics for Web Images via Cross-modal Pre-trained Knowledge
Automatically generating textual descriptions for massive unlabeled images on the web can greatly benefit realistic web applications, e. g. multimodal retrieval and recommendation.
ConceptBed: Evaluating Concept Learning Abilities of Text-to-Image Diffusion Models
To quantify the ability of T2I models in learning and synthesizing novel visual concepts (a. k. a.
AltDiffusion: A Multilingual Text-to-Image Diffusion Model
Specifically, we first train a multilingual text encoder based on the knowledge distillation.
Expanding Scene Graph Boundaries: Fully Open-vocabulary Scene Graph Generation via Visual-Concept Alignment and Retention
For the more challenging settings of relation-involved open vocabulary SGG, the proposed approach integrates relation-aware pre-training utilizing image-caption data and retains visual-concept alignment through knowledge distillation.
MICA: Towards Explainable Skin Lesion Diagnosis via Multi-Level Image-Concept Alignment
Black-box deep learning approaches have showcased significant potential in the realm of medical image analysis.
Lumen: Unleashing Versatile Vision-Centric Capabilities of Large Multimodal Models
To address this issue, we propose a novel LMM architecture named Lumen, a Large multimodal model with versatile vision-centric capability enhancement.
Improving Concept Alignment in Vision-Language Concept Bottleneck Models
To address this issue, we propose a novel Contrastive Semi-Supervised (CSS) learning method that leverages a few labeled concept samples to activate truthful visual concepts and improve concept alignment in the CLIP model.