Walking the Web of Concept-Class Relationships in Incrementally Trained Interpretable Models

• URL: http://arxiv.org/abs/2502.20393v1
• Date: Thu, 27 Feb 2025 18:59:29 GMT
• Title: Walking the Web of Concept-Class Relationships in Incrementally Trained Interpretable Models
• Authors: Susmit Agrawal, Deepika Vemuri, Sri Siddarth Chakaravarthy P, Vineeth N. Balasubramanian,
• Abstract summary: We show that concepts and classes form a complex web of relationships, which is susceptible to degradation and needs to be preserved and augmented across experiences.<n>We propose a novel method - MuCIL - that uses multimodal concepts to perform classification without increasing the number of trainable parameters across experiences.
• Score: 25.84386438333865
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Concept-based methods have emerged as a promising direction to develop interpretable neural networks in standard supervised settings. However, most works that study them in incremental settings assume either a static concept set across all experiences or assume that each experience relies on a distinct set of concepts. In this work, we study concept-based models in a more realistic, dynamic setting where new classes may rely on older concepts in addition to introducing new concepts themselves. We show that concepts and classes form a complex web of relationships, which is susceptible to degradation and needs to be preserved and augmented across experiences. We introduce new metrics to show that existing concept-based models cannot preserve these relationships even when trained using methods to prevent catastrophic forgetting, since they cannot handle forgetting at concept, class, and concept-class relationship levels simultaneously. To address these issues, we propose a novel method - MuCIL - that uses multimodal concepts to perform classification without increasing the number of trainable parameters across experiences. The multimodal concepts are aligned to concepts provided in natural language, making them interpretable by design. Through extensive experimentation, we show that our approach obtains state-of-the-art classification performance compared to other concept-based models, achieving over 2$\times$ the classification performance in some cases. We also study the ability of our model to perform interventions on concepts, and show that it can localize visual concepts in input images, providing post-hoc interpretations.

Related papers

• OmniPrism: Learning Disentangled Visual Concept for Image Generation [57.21097864811521]
  Creative visual concept generation often draws inspiration from specific concepts in a reference image to produce relevant outcomes.<n>We propose OmniPrism, a visual concept disentangling approach for creative image generation.<n>Our method learns disentangled concept representations guided by natural language and trains a diffusion model to incorporate these concepts.
  arXiv  Detail & Related papers  (2024-12-16T18:59:52Z)
• Scaling Concept With Text-Guided Diffusion Models [53.80799139331966]
  Instead of replacing a concept, can we enhance or suppress the concept itself? We introduce ScalingConcept, a simple yet effective method to scale decomposed concepts up or down in real input without introducing new elements. More importantly, ScalingConcept enables a variety of novel zero-shot applications across image and audio domains.
  arXiv  Detail & Related papers  (2024-10-31T17:09:55Z)
• How to Continually Adapt Text-to-Image Diffusion Models for Flexible Customization? [91.49559116493414]
  We propose a novel Concept-Incremental text-to-image Diffusion Model (CIDM) It can resolve catastrophic forgetting and concept neglect to learn new customization tasks in a concept-incremental manner. Experiments validate that our CIDM surpasses existing custom diffusion models.
  arXiv  Detail & Related papers  (2024-10-23T06:47:29Z)
• ConceptExpress: Harnessing Diffusion Models for Single-image Unsupervised Concept Extraction [20.43411883845885]
  We introduce a novel task named Unsupervised Concept Extraction (UCE) that considers an unsupervised setting without any human knowledge of the concepts. Given an image that contains multiple concepts, the task aims to extract and recreate individual concepts solely relying on the existing knowledge from pretrained diffusion models. We present ConceptExpress that tackles UCE by unleashing the inherent capabilities of pretrained diffusion models in two aspects.
  arXiv  Detail & Related papers  (2024-07-09T17:50:28Z)
• Restyling Unsupervised Concept Based Interpretable Networks with Generative Models [14.604305230535026]
  We propose a novel method that relies on mapping the concept features to the latent space of a pretrained generative model. We quantitatively ascertain the efficacy of our method in terms of accuracy of the interpretable prediction network, fidelity of reconstruction, as well as faithfulness and consistency of learnt concepts.
  arXiv  Detail & Related papers  (2024-07-01T14:39:41Z)
• Improving Concept Alignment in Vision-Language Concept Bottleneck Models [9.228586820098723]
  Concept Bottleneck Models (CBM) map images to human-interpretable concepts before making class predictions. Recent approaches automate CBM construction by prompting Large Language Models (LLMs) to generate text concepts. It is desired to build CBMs with concepts defined by human experts rather than LLM-generated ones.
  arXiv  Detail & Related papers  (2024-05-03T03:02:00Z)
• Improving Intervention Efficacy via Concept Realignment in Concept Bottleneck Models [57.86303579812877]
  Concept Bottleneck Models (CBMs) ground image classification on human-understandable concepts to allow for interpretable model decisions. Existing approaches often require numerous human interventions per image to achieve strong performances. We introduce a trainable concept realignment intervention module, which leverages concept relations to realign concept assignments post-intervention.
  arXiv  Detail & Related papers  (2024-05-02T17:59:01Z)
• A Self-explaining Neural Architecture for Generalizable Concept Learning [29.932706137805713]
  We show that present SOTA concept learning approaches suffer from two major problems - lack of concept fidelity and limited concept interoperability. We propose a novel self-explaining architecture for concept learning across domains. We demonstrate the efficacy of our proposed approach over current SOTA concept learning approaches on four widely used real-world datasets.
  arXiv  Detail & Related papers  (2024-05-01T06:50:18Z)
• Separable Multi-Concept Erasure from Diffusion Models [52.51972530398691]
  We propose a Separable Multi-concept Eraser (SepME) to eliminate unsafe concepts from large-scale diffusion models. The latter separates optimizable model weights, making each weight increment correspond to a specific concept erasure. Extensive experiments indicate the efficacy of our approach in eliminating concepts, preserving model performance, and offering flexibility in the erasure or recovery of various concepts.
  arXiv  Detail & Related papers  (2024-02-03T11:10:57Z)
• Advancing Ante-Hoc Explainable Models through Generative Adversarial Networks [24.45212348373868]
  This paper presents a novel concept learning framework for enhancing model interpretability and performance in visual classification tasks. Our approach appends an unsupervised explanation generator to the primary classifier network and makes use of adversarial training. This work presents a significant step towards building inherently interpretable deep vision models with task-aligned concept representations.
  arXiv  Detail & Related papers  (2024-01-09T16:16:16Z)
• Concept Distillation: Leveraging Human-Centered Explanations for Model Improvement [3.026365073195727]
  Concept Activation Vectors (CAVs) estimate a model's sensitivity and possible biases to a given concept. We extend CAVs from post-hoc analysis to ante-hoc training in order to reduce model bias through fine-tuning. We show applications of concept-sensitive training to debias several classification problems.
  arXiv  Detail & Related papers  (2023-11-26T14:00:14Z)
• Separating Skills and Concepts for Novel Visual Question Answering [66.46070380927372]
  Generalization to out-of-distribution data has been a problem for Visual Question Answering (VQA) models. "Skills" are visual tasks, such as counting or attribute recognition, and are applied to "concepts" mentioned in the question. We present a novel method for learning to compose skills and concepts that separates these two factors implicitly within a model.
  arXiv  Detail & Related papers  (2021-07-19T18:55:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.