CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks

• URL: http://arxiv.org/abs/2204.10965v5
• Date: Mon, 5 Jun 2023 17:49:40 GMT
• Title: CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks
• Authors: Tuomas Oikarinen, Tsui-Wei Weng
• Abstract summary: We propose CLIP-Dissect, a new technique to automatically describe the function of individual hidden neurons inside vision networks. We show that CLIP-Dissect provides more accurate descriptions than existing methods for last layer neurons. CLIP-Dissect is computationally efficient and can label all neurons from five layers of ResNet-50 in just 4 minutes.
• Score: 7.8858544147141085
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we propose CLIP-Dissect, a new technique to automatically describe the function of individual hidden neurons inside vision networks. CLIP-Dissect leverages recent advances in multimodal vision/language models to label internal neurons with open-ended concepts without the need for any labeled data or human examples. We show that CLIP-Dissect provides more accurate descriptions than existing methods for last layer neurons where the ground-truth is available as well as qualitatively good descriptions for hidden layer neurons. In addition, our method is very flexible: it is model agnostic, can easily handle new concepts and can be extended to take advantage of better multimodal models in the future. Finally CLIP-Dissect is computationally efficient and can label all neurons from five layers of ResNet-50 in just 4 minutes, which is more than 10 times faster than existing methods. Our code is available at https://github.com/Trustworthy-ML-Lab/CLIP-dissect. Finally, crowdsourced user study results are available at Appendix B to further support the effectiveness of our method.

Related papers

• Neuron-based Personality Trait Induction in Large Language Models [115.08894603023712]
  Large language models (LLMs) have become increasingly proficient at simulating various personality traits. We present a neuron-based approach for personality trait induction in LLMs.
  arXiv  Detail & Related papers  (2024-10-16T07:47:45Z)
• Interpreting Neurons in Deep Vision Networks with Language Models [9.369923839058634]
  We propose Describe-and-Dissect (DnD), a novel method to describe the roles of hidden neurons in vision networks. DnD is training-free, meaning we don't train any new models and can easily leverage more capable general purpose models. We present a use case providing critical insights into land cover prediction models for sustainability applications.
  arXiv  Detail & Related papers  (2024-03-20T17:33:02Z)
• Manipulating Feature Visualizations with Gradient Slingshots [54.31109240020007]
  We introduce a novel method for manipulating Feature Visualization (FV) without significantly impacting the model's decision-making process. We evaluate the effectiveness of our method on several neural network models and demonstrate its capabilities to hide the functionality of arbitrarily chosen neurons.
  arXiv  Detail & Related papers  (2024-01-11T18:57:17Z)
• DISCOVER: Making Vision Networks Interpretable via Competition and Dissection [11.028520416752325]
  This work contributes to post-hoc interpretability, and specifically Network Dissection. Our goal is to present a framework that makes it easier to discover the individual functionality of each neuron in a network trained on a vision task.
  arXiv  Detail & Related papers  (2023-10-07T21:57:23Z)
• NeuroCLIP: Neuromorphic Data Understanding by CLIP and SNN [16.104055742259128]
  We develop NeuroCLIP, which consists of 2D CLIP and two specially designed modules for neuromorphic data understanding. Various experiments on neuromorphic datasets including N-MNIST, CIFAR10-DVS, and ES-ImageNet demonstrate the effectiveness of NeuroCLIP.
  arXiv  Detail & Related papers  (2023-06-21T07:46:27Z)
• Noisy Heuristics NAS: A Network Morphism based Neural Architecture Search using Heuristics [11.726528038065764]
  We present a new Network Morphism based NAS called Noisy Heuristics NAS. We add new neurons randomly and prune away some to select only the best fitting neurons. Our method generalizes both on toy datasets and on real-world data sets such as MNIST, CIFAR-10, and CIFAR-100.
  arXiv  Detail & Related papers  (2022-07-10T13:58:21Z)
• Variable Bitrate Neural Fields [75.24672452527795]
  We present a dictionary method for compressing feature grids, reducing their memory consumption by up to 100x. We formulate the dictionary optimization as a vector-quantized auto-decoder problem which lets us learn end-to-end discrete neural representations in a space where no direct supervision is available.
  arXiv  Detail & Related papers  (2022-06-15T17:58:34Z)
• Natural Language Descriptions of Deep Visual Features [50.270035018478666]
  We introduce a procedure that automatically labels neurons with open-ended, compositional, natural language descriptions. We use MILAN for analysis, characterizing the distribution and importance of neurons selective for attribute, category, and relational information in vision models. We also use MILAN for auditing, surfacing neurons sensitive to protected categories like race and gender in models trained on datasets intended to obscure these features.
  arXiv  Detail & Related papers  (2022-01-26T18:48:02Z)
• Explainability Tools Enabling Deep Learning in Future In-Situ Real-Time Planetary Explorations [58.720142291102135]
  Deep learning (DL) has proven to be an effective machine learning and computer vision technique. Most of the Deep Neural Network (DNN) architectures are so complex that they are considered a 'black box' In this paper, we used integrated gradients to describe the attributions of each neuron to the output classes. It provides a set of explainability tools (ET) that opens the black box of a DNN so that the individual contribution of neurons to category classification can be ranked and visualized.
  arXiv  Detail & Related papers  (2022-01-15T07:10:00Z)
• Non-linear Neurons with Human-like Apical Dendrite Activations [81.18416067005538]
  We show that a standard neuron followed by our novel apical dendrite activation (ADA) can learn the XOR logical function with 100% accuracy. We conduct experiments on six benchmark data sets from computer vision, signal processing and natural language processing.
  arXiv  Detail & Related papers  (2020-02-02T21:09:39Z)

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.