Understanding invariance via feedforward inversion of discriminatively trained classifiers

• URL: http://arxiv.org/abs/2103.07470v1
• Date: Mon, 15 Mar 2021 17:56:06 GMT
• Title: Understanding invariance via feedforward inversion of discriminatively trained classifiers
• Authors: Piotr Teterwak, Chiyuan Zhang, Dilip Krishnan, Michael C. Mozer
• Abstract summary: Past research has discovered that some extraneous visual detail remains in the output logits. We develop a feedforward inversion model that produces remarkably high fidelity reconstructions. Our approach is based on BigGAN, with conditioning on logits instead of one-hot class labels.
• Score: 30.23199531528357
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A discriminatively trained neural net classifier achieves optimal performance if all information about its input other than class membership has been discarded prior to the output layer. Surprisingly, past research has discovered that some extraneous visual detail remains in the output logits. This finding is based on inversion techniques that map deep embeddings back to images. Although the logit inversions seldom produce coherent, natural images or recognizable object classes, they do recover some visual detail. We explore this phenomenon further using a novel synthesis of methods, yielding a feedforward inversion model that produces remarkably high fidelity reconstructions, qualitatively superior to those of past efforts. When applied to an adversarially robust classifier model, the reconstructions contain sufficient local detail and global structure that they might be confused with the original image in a quick glance, and the object category can clearly be gleaned from the reconstruction. Our approach is based on BigGAN (Brock, 2019), with conditioning on logits instead of one-hot class labels. We use our reconstruction model as a tool for exploring the nature of representations, including: the influence of model architecture and training objectives (specifically robust losses), the forms of invariance that networks achieve, representational differences between correctly and incorrectly classified images, and the effects of manipulating logits and images. We believe that our method can inspire future investigations into the nature of information flow in a neural net and can provide diagnostics for improving discriminative models.

Related papers

• Reinforcing Pre-trained Models Using Counterfactual Images [54.26310919385808]
  This paper proposes a novel framework to reinforce classification models using language-guided generated counterfactual images. We identify model weaknesses by testing the model using the counterfactual image dataset. We employ the counterfactual images as an augmented dataset to fine-tune and reinforce the classification model.
  arXiv  Detail & Related papers  (2024-06-19T08:07:14Z)
• Data Attribution for Text-to-Image Models by Unlearning Synthesized Images [71.23012718682634]
  The goal of data attribution for text-to-image models is to identify the training images that most influence the generation of a new image. We propose a new approach that efficiently identifies highly-influential images.
  arXiv  Detail & Related papers  (2024-06-13T17:59:44Z)
• A Phase Transition in Diffusion Models Reveals the Hierarchical Nature of Data [55.748186000425996]
  Recent advancements show that diffusion models can generate high-quality images. We study this phenomenon in a hierarchical generative model of data. Our analysis characterises the relationship between time and scale in diffusion models.
  arXiv  Detail & Related papers  (2024-02-26T19:52:33Z)
• DiG-IN: Diffusion Guidance for Investigating Networks -- Uncovering Classifier Differences Neuron Visualisations and Visual Counterfactual Explanations [35.458709912618176]
  Deep learning has led to huge progress in complex image classification tasks like ImageNet, unexpected failure modes, e.g. via spurious features. For safety-critical tasks the black-box nature of their decisions is problematic, and explanations or at least methods which make decisions plausible are needed urgently. We address these problems by generating images that optimize a classifier-derived objective using a framework for guided image generation.
  arXiv  Detail & Related papers  (2023-11-29T17:35:29Z)
• Diffusion Models Beat GANs on Image Classification [37.70821298392606]
  Diffusion models have risen to prominence as a state-of-the-art method for image generation, denoising, inpainting, super-resolution, manipulation, etc. We present our findings that these embeddings are useful beyond the noise prediction task, as they contain discriminative information and can also be leveraged for classification. We find that with careful feature selection and pooling, diffusion models outperform comparable generative-discriminative methods for classification tasks.
  arXiv  Detail & Related papers  (2023-07-17T17:59:40Z)
• Reconstruction-guided attention improves the robustness and shape processing of neural networks [5.156484100374057]
  We build an iterative encoder-decoder network that generates an object reconstruction and uses it as top-down attentional feedback. Our model shows strong generalization performance against various image perturbations. Our study shows that modeling reconstruction-based feedback endows AI systems with a powerful attention mechanism.
  arXiv  Detail & Related papers  (2022-09-27T18:32:22Z)
• Learning Discriminative Shrinkage Deep Networks for Image Deconvolution [122.79108159874426]
  We propose an effective non-blind deconvolution approach by learning discriminative shrinkage functions to implicitly model these terms. Experimental results show that the proposed method performs favorably against the state-of-the-art ones in terms of efficiency and accuracy.
  arXiv  Detail & Related papers  (2021-11-27T12:12:57Z)
• Counterfactual Generative Networks [59.080843365828756]
  We propose to decompose the image generation process into independent causal mechanisms that we train without direct supervision. By exploiting appropriate inductive biases, these mechanisms disentangle object shape, object texture, and background. We show that the counterfactual images can improve out-of-distribution with a marginal drop in performance on the original classification task.
  arXiv  Detail & Related papers  (2021-01-15T10:23:12Z)
• Adversarially-Trained Deep Nets Transfer Better: Illustration on Image Classification [53.735029033681435]
  Transfer learning is a powerful methodology for adapting pre-trained deep neural networks on image recognition tasks to new domains. In this work, we demonstrate that adversarially-trained models transfer better than non-adversarially-trained models.
  arXiv  Detail & Related papers  (2020-07-11T22:48:42Z)

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.