Concept Visualization: Explaining the CLIP Multi-modal Embedding Using WordNet
Advances in multi-modal embeddings, and in particular CLIP, have recently driven several breakthroughs in Computer Vision (CV). CLIP has shown impressive performance on a variety of tasks, yet, its inherently opaque architecture may hinder the application of models employing CLIP as backbone, especially in fields where trust and model explainability are imperative, such as in the medical domain. Current explanation methodologies for CV models rely on Saliency Maps computed through gradient analysis or input perturbation. However, these Saliency Maps can only be computed to explain classes relevant to the end task, often smaller in scope than the backbone training classes. In the context of models implementing CLIP as their vision backbone, a substantial portion of the information embedded within the learned representations is thus left unexplained. In this work, we propose Concept Visualization (ConVis), a novel saliency methodology that explains the CLIP embedding of an image by exploiting the multi-modal nature of the embeddings. ConVis makes use of lexical information from WordNet to compute task-agnostic Saliency Maps for any concept, not limited to concepts the end model was trained on. We validate our use of WordNet via an out of distribution detection experiment, and test ConVis on an object localization benchmark, showing that Concept Visualizations correctly identify and localize the image's semantic content. Additionally, we perform a user study demonstrating that our methodology can give users insight on the model's functioning.
Code (1)
Tasks
Object LocalizationOut-of-Distribution DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
How can embedding models bind concepts?
Humans easily determine which color belongs to which shape in multi-object scenes, an ability known as concept binding. Vision-language embedding models such as CLIP struggle with binding: they recognize individual conce…
Cross-Modal RetrievalExplaining CLIP Zero-shot Predictions Through Concepts
Large-scale vision-language models such as CLIP have achieved remarkable success in zero-shot image recognition, yet their predictions remain largely opaque to human understanding. In contrast, Concept Bottleneck Models …
CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP
CLIP yielded impressive results on zero-shot transfer learning tasks and is considered as a foundation model like BERT or GPT3. CLIP vision models that have a rich representation are pre-trained using the InfoNCE objecti…
Contrastive LearningSelf-Supervised LearningTransfer LearningHow Well Do Deep Learning Models Capture Human Concepts? The Case of the Typicality Effect
How well do representations learned by ML models align with those of humans? Here, we consider concept representations learned by deep learning models and evaluate whether they show a fundamental behavioral signature of …
Language ModelingLanguage ModellingWhen does CLIP generalize better than unimodal models? When judging human-centric concepts
CLIP, a vision-language network trained with a multimodal contrastive learning objective on a large dataset of images and captions, has demonstrated impressive zero-shot ability in various tasks. However, recent work sho…
ClassificationContrastive LearningGenre classificationSentiment Analysis+1