Human vision, thought, and planning involve parsing and representing objects and scenes using structured representations based on part-whole hierarchies. Computer vision and machine learning researchers have recently sought to emulate this capability using neural networks, but a generative model formulation has been lacking. Generative models that leverage compositionality, recursion, and part-whole hierarchies are thought to underlie human concept learning and the ability to construct and represent flexible mental concepts. We introduce Recursive Neural Programs (RNPs), a neural generative model that addresses the part-whole hierarchy learning problem by modeling images as hierarchical trees of probabilistic sensory-motor programs. These programs recursively reuse learned sensory-motor primitives to model an image within different spatial reference frames, enabling hierarchical composition of objects from parts and implementing a grammar for images. We show that RNPs can learn part-whole hierarchies for a variety of image datasets, allowing rich compositionality and intuitive parts-based explanations of objects. Our model also suggests a cognitive framework for understanding how human brains can potentially learn and represent concepts in terms of recursively defined primitives and their relations with each other.
This content will become publicly available on March 25, 2025
ConceptBed: Evaluating Concept Learning Abilities of Text-to-Image Diffusion Models
The ability to understand visual concepts and replicate and compose these concepts from images is a central goal for computer vision. Recent advances in text-to-image (T2I) models have lead to high definition and realistic image quality generation by learning from large databases of images and their descriptions. However, the evaluation of T2I models has focused on photorealism and limited qualitative measures of visual understanding. To quantify the ability of T2I models in learning and synthesizing novel visual concepts (a.k.a. personalized T2I), we introduce ConceptBed, a large-scale dataset that consists of 284 unique visual concepts, and 33K composite text prompts. Along with the dataset, we propose an evaluation metric, Concept Confidence Deviation (CCD), that uses the confidence of oracle concept classifiers to measure the alignment between concepts generated by T2I generators and concepts contained in target images. We evaluate visual concepts that are either objects, attributes, or styles, and also evaluate four dimensions of compositionality: counting, attributes, relations, and actions. Our human study shows that CCD is highly correlated with human understanding of concepts. Our results point to a trade-off between learning the concepts and preserving the compositionality which existing approaches struggle to overcome. The data, code, and interactive demo is available at: https://conceptbed.github.io/
more » « less- Award ID(s):
- 1750082
- PAR ID:
- 10537863
- Publisher / Repository:
- AAAI
- Date Published:
- Journal Name:
- Proceedings of the AAAI Conference on Artificial Intelligence
- Volume:
- 38
- Issue:
- 13
- ISSN:
- 2159-5399
- Page Range / eLocation ID:
- 14554 to 14562
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
Abbott, Derek (Ed.)more » « less
Abstract -
The popularization of Text-to-Image (T2I) diffusion mod- els enables the generation of high-quality images from text descriptions. However, generating diverse customized im- ages with reference visual attributes remains challenging. This work focuses on personalizing T2I diffusion models at a more abstract concept or category level, adapting com- monalities from a set of reference images while creating new instances with sufficient variations. We introduce a solution that allows a pretrained T2I diffusion model to learn a set of soft prompts, enabling the generation of novel images by sampling prompts from the learned distri- bution. These prompts offer text-guided editing capabilities and additional flexibility in controlling variation and mix- ing between multiple distributions. We also show the adapt- ability of the learned prompt distribution to other tasks, such as text-to-3D. Finally we demonstrate effectiveness of our approach through quantitative analysis including auto- matic evaluation and human assessment.more » « less
-
Aliannejadi, M ; Faggioli, G ; Ferro, N ; Vlachos, M. (Ed.)This work discusses the participation of CS_Morgan in the Concept Detection and Caption Prediction tasks of the ImageCLEFmedical 2023 Caption benchmark evaluation campaign. The goal of this task is to automatically identify relevant concepts and their locations in images, as well as generate coherent captions for the images. The dataset used for this task is a subset of the extended Radiology Objects in Context (ROCO) dataset. The implementation approach employed by us involved the use of pre-trained Convolutional Neural Networks (CNNs), Vision Transformer (ViT), and Text-to-Text Transfer Transformer (T5) architectures. These models were leveraged to handle the different aspects of the tasks, such as concept detection and caption generation. In the Concept Detection task, the objective was to classify multiple concepts associated with each image. We utilized several deep learning architectures with ‘sigmoid’ activation to enable multilabel classification using the Keras framework. We submitted a total of five (5) runs for this task, and the best run achieved an F1 score of 0.4834, indicating its effectiveness in detecting relevant concepts in the images. For the Caption Prediction task, we successfully submitted eight (8) runs. Our approach involved combining the ViT and T5 models to generate captions for the images. For the caption prediction task, the ranking is based on the BERTScore, and our best run achieved a score of 0.5819 based on generating captions using the fine-tuned T5 model from keywords generated using the pretrained ViT as the encoder.more » « less
-
Biomedical images are crucial for diagnosing and planning treatments, as well as advancing scientific understanding of various ailments. To effectively highlight regions of interest (RoIs) and convey medical concepts, annotation markers like arrows, letters, or symbols are employed. However, annotating these images with appropriate medical labels poses a significant challenge. In this study, we propose a framework that leverages multimodal input features, including text/label features and visual features, to facilitate accurate annotation of biomedical images with multiple labels. Our approach integrates state-of-the-art models such as ResNet50 and Vision Transformers (ViT) to extract informative features from the images. Additionally, we employ Generative Pre-trained Distilled-GPT2 (Transformer based Natural Language Processing architecture) to extract textual features, leveraging their natural language understanding capabilities. This combination of image and text modalities allows for a more comprehensive representation of the biomedical data, leading to improved annotation accuracy. By combining the features extracted from both image and text modalities, we trained a simplified Convolutional Neural Network (CNN) based multi-classifier to learn the image-text relations and predict multi-labels for multi-modal radiology images. We used ImageCLEFmedical 2022 and 2023 datasets to demonstrate the effectiveness of our framework. This dataset likely contains a diverse range of biomedical images, enabling the evaluation of the framework’s performance under realistic conditions. We have achieved promising results with the F1 score of 0.508. Our proposed framework exhibits potential performance in annotating biomedical images with multiple labels, contributing to improved image understanding and analysis in the medical image processing domain.more » « less
-
While machine learning approaches to visual emotion recognition o er great promise, current methods consider training and testing models on small scale datasets covering limited visual emotion concepts. Our analysis identi es an important but long overlooked issue of existing visual emotion benchmarks in the form of dataset biases. We design a series of tests to show and measure how such dataset biases obstruct learning a generalizable emotion recognition model. Based on our analysis, we propose a webly supervised approach by leveraging a large quantity of stock image data. Our approach uses a simple yet e ective curriculum guided training strategy for learning discriminative emotion features. We discover that the models learned using our large scale stock image dataset exhibit signi cantly better generalization ability than the existing datasets without the manual collection of even a single label. Moreover, visual representation learned using our approach holds a lot of promise across a variety of tasks on di erent image and video datasets.more » « less
