2024/06/11 by Brandon Trabucco, Trabucco, Brandon, Max Gurinas +5
Computer Science · Social Sciences · #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #Data Visualization and Analytics #FOS: Computer and information sciences #Geographic Information Systems Studies #Machine Learning (cs.LG)
paper · pdf · doi:10.48550/arxiv.2406.07506
openalex publication_date 2024/06/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Large multimodal models such as Stable Diffusion can generate, detect, and classify new visual concepts after fine-tuning just a single word embedding. Do models learn similar words for the same concepts (i.e. = orange + cat)? We conduct a large-scale analysis on three state-of-the-art models in text-to-image generation, open-set object detection, and zero-shot classification, and find that new word embeddings are model-specific and non-transferable. Across 4,800 new embeddings trained for 40 diverse visual concepts on four standard datasets, we find perturbations within an ε-ball to any prior embedding that generate, detect, and classify an arbitrary concept. When these new embeddings are spliced into new models, fine-tuning that targets the original model is lost. We show popular soft prompt-tuning approaches find these perturbative solutions when applied to visual concept learning tasks, and embeddings for visual concepts are not transferable. Code for reproducing our work is available at: https://visual-words.github.io.