Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery

• URL: http://arxiv.org/abs/2407.14499v2
• Date: Mon, 12 Aug 2024 14:50:01 GMT
• Title: Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery
• Authors: Sukrut Rao, Sweta Mahajan, Moritz Böhle, Bernt Schiele,
• Abstract summary: Concept Bottleneck Models (CBMs) have been proposed to address the 'black-box' problem of deep neural networks. We propose a novel CBM approach -- called Discover-then-Name-CBM (DN-CBM) -- that inverts the typical paradigm. Our concept extraction strategy is efficient, since it is agnostic to the downstream task, and uses concepts already known to the model.
• Score: 52.498055901649025
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Concept Bottleneck Models (CBMs) have recently been proposed to address the 'black-box' problem of deep neural networks, by first mapping images to a human-understandable concept space and then linearly combining concepts for classification. Such models typically require first coming up with a set of concepts relevant to the task and then aligning the representations of a feature extractor to map to these concepts. However, even with powerful foundational feature extractors like CLIP, there are no guarantees that the specified concepts are detectable. In this work, we leverage recent advances in mechanistic interpretability and propose a novel CBM approach -- called Discover-then-Name-CBM (DN-CBM) -- that inverts the typical paradigm: instead of pre-selecting concepts based on the downstream classification task, we use sparse autoencoders to first discover concepts learnt by the model, and then name them and train linear probes for classification. Our concept extraction strategy is efficient, since it is agnostic to the downstream task, and uses concepts already known to the model. We perform a comprehensive evaluation across multiple datasets and CLIP architectures and show that our method yields semantically meaningful concepts, assigns appropriate names to them that make them easy to interpret, and yields performant and interpretable CBMs. Code available at https://github.com/neuroexplicit-saar/discover-then-name.

Related papers

• Explain via Any Concept: Concept Bottleneck Model with Open Vocabulary Concepts [8.028021897214238]
  "OpenCBM" is the first CBM with concepts of open vocabularies. Our model significantly outperforms the previous state-of-the-art CBM by 9% in the classification accuracy on the benchmark dataset CUB-200-2011.
  arXiv  Detail & Related papers  (2024-08-05T06:42:00Z)
• LLM-assisted Concept Discovery: Automatically Identifying and Explaining Neuron Functions [15.381209058506078]
  Prior works have associated concepts with neurons based on examples of concepts or a pre-defined set of concepts. We propose to leverage multimodal large language models for automatic and open-ended concept discovery. We validate each concept by generating examples and counterexamples and evaluating the neuron's response on this new set of images.
  arXiv  Detail & Related papers  (2024-06-12T18:19:37Z)
• Understanding Multimodal Deep Neural Networks: A Concept Selection View [29.08342307127578]
  Concept-based models map the black-box visual representations extracted by deep neural networks onto a set of human-understandable concepts. We propose a two-stage Concept Selection Model (CSM) to mine core concepts without introducing any human priors. Our approach achieves comparable performance to end-to-end black-box models.
  arXiv  Detail & Related papers  (2024-04-13T11:06:49Z)
• Sparse Concept Bottleneck Models: Gumbel Tricks in Contrastive Learning [86.15009879251386]
  We propose a novel architecture and method of explainable classification with Concept Bottleneck Models (CBM) CBMs require an additional set of concepts to leverage. We show a significant increase in accuracy using sparse hidden layers in CLIP-based bottleneck models.
  arXiv  Detail & Related papers  (2024-04-04T09:43:43Z)
• Simple Mechanisms for Representing, Indexing and Manipulating Concepts [46.715152257557804]
  We will argue that learning a concept could be done by looking at its moment statistics matrix to generate a concrete representation or signature of that concept. When the concepts are intersected', signatures of the concepts can be used to find a common theme across a number of related intersected' concepts.
  arXiv  Detail & Related papers  (2023-10-18T17:54:29Z)
• A Recursive Bateson-Inspired Model for the Generation of Semantic Formal Concepts from Spatial Sensory Data [77.34726150561087]
  This paper presents a new symbolic-only method for the generation of hierarchical concept structures from complex sensory data. The approach is based on Bateson's notion of difference as the key to the genesis of an idea or a concept. The model is able to produce fairly rich yet human-readable conceptual representations without training.
  arXiv  Detail & Related papers  (2023-07-16T15:59:13Z)
• DetCLIP: Dictionary-Enriched Visual-Concept Paralleled Pre-training for Open-world Detection [118.36746273425354]
  This paper presents a paralleled visual-concept pre-training method for open-world detection by resorting to knowledge enrichment from a designed concept dictionary. By enriching the concepts with their descriptions, we explicitly build the relationships among various concepts to facilitate the open-domain learning. The proposed framework demonstrates strong zero-shot detection performances, e.g., on the LVIS dataset, our DetCLIP-T outperforms GLIP-T by 9.9% mAP and obtains a 13.5% improvement on rare categories.
  arXiv  Detail & Related papers  (2022-09-20T02:01:01Z)
• Automatic Concept Extraction for Concept Bottleneck-based Video Classification [58.11884357803544]
  We present an automatic Concept Discovery and Extraction module that rigorously composes a necessary and sufficient set of concept abstractions for concept-based video classification. Our method elicits inherent complex concept abstractions in natural language to generalize concept-bottleneck methods to complex tasks.
  arXiv  Detail & Related papers  (2022-06-21T06:22:35Z)
• SegDiscover: Visual Concept Discovery via Unsupervised Semantic Segmentation [29.809900593362844]
  SegDiscover is a novel framework that discovers semantically meaningful visual concepts from imagery datasets with complex scenes without supervision. Our method generates concept primitives from raw images, discovering concepts by clustering in the latent space of a self-supervised pretrained encoder, and concept refinement via neural network smoothing.
  arXiv  Detail & Related papers  (2022-04-22T20:44:42Z)
• Concept Bottleneck Model with Additional Unsupervised Concepts [0.5939410304994348]
  We propose a novel interpretable model based on the concept bottleneck model (CBM) CBM uses concept labels to train an intermediate layer as the additional visible layer. By seamlessly training these two types of concepts while reducing the amount of computation, we can obtain both supervised and unsupervised concepts simultaneously.
  arXiv  Detail & Related papers  (2022-02-03T08:30:51Z)

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.