mlsanityData to 7 Oct 2026

Weakly Supervised Recovery of Semantic Attributes

arXiv 2103.11888 ↗First posted 22 Mar 2021cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

We consider the problem of the extraction of semantic attributes, supervised only with classification labels. For example, when learning to classify images of birds into species, we would like to observe the emergence of features that zoologists use to classify birds. To tackle this problem, we propose training a neural network with discrete features in the last layer, which is followed by two heads: a multi-layered perceptron (MLP) and a decision tree. Since decision trees utilize simple binary decision stumps we expect those discrete features to obtain semantic meaning. We present a theoretical analysis as well as a practical method for learning in the intersection of two hypothesis classes. Our results on multiple benchmarks show an improved ability to extract a set of features that are highly correlated with the set of unseen attributes.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 58 of its 94 references that are in the map. First posted on arXiv 22 Mar 2021.

Builds on

58 of 94 references.

References · 58

  1. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  3. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  4. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  5. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  6. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  7. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  8. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  9. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,031
  10. 2017SmoothGrad: removing noise by adding noisecited by 1,097
  11. 2018A Survey Of Methods For Explaining Black Box Modelscited by 970
  12. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 929
38 more
  1. 2019Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descentcited by 732
  2. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 731
  3. 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkscited by 707
  4. 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 611
  5. 2016DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradientscited by 557
  6. 2017Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Uglycited by 536
  7. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  8. 2016Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activationscited by 413
  9. 2016Top-down Neural Attention by Excitation Backpropcited by 318
  10. 2018On the Robustness of Interpretability Methodscited by 310
  11. 2016Not Just a Black Box: Learning Important Features Through Propagating Activation Differencescited by 295
  12. 2017Learning to Discover Cross-Domain Relations with Generative Adversarial Networkscited by 278
  13. 2019Understanding Deep Networks via Extremal Perturbations and Smooth Maskscited by 257
  14. 2015Explaining NonLinear Classification Decisions with Deep Taylor Decompositioncited by 248
  15. 2017Real Time Image Saliency for Black Box Classifierscited by 246
  16. 2017Distilling a Neural Network Into a Soft Decision Treecited by 230
  17. 2019Full-Gradient Representation for Neural Network Visualizationcited by 189
  18. 2018Tell Me Where to Look: Guided Attention Inference Networkcited by 168
  19. 2019Quantization Networkscited by 151
  20. 2016Dual Learning for Machine Translationcited by 146
  21. 2018Recent Advances in Autoencoder-Based Representation Learningcited by 130
  22. 2017Interpreting Deep Visual Representations via Network Dissectioncited by 103
  23. 2018Learning to Navigate for Fine-grained Classificationcited by 103
  24. 2015Visualizing Deep Convolutional Neural Networks Using Natural Pre-Imagescited by 93
  25. 2020Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patchescited by 92
  26. 2020Learning Attentive Pairwise Interaction for Fine-Grained Classificationcited by 84
  27. 2019A critical analysis of self-supervision, or what we can learn from a single imagecited by 75
  28. 2020Interpretable and Accurate Fine-grained Recognition via Region Groupingcited by 75
  29. 2018Adaptive Neural Treescited by 64
  30. 2019See Better Before Looking Closer: Weakly Supervised Data Augmentation Network for Fine-Grained Visual Classificationcited by 56
  31. 2019Relative Attributing Propagation: Interpreting the Comparative Contributions of Individual Units in Deep Neural Networkscited by 49
  32. 2018Understanding Individual Decisions of CNNs via Contrastive Backpropagationcited by 40
  33. 2017Learning Independent Features with Adversarial Nets for Non-linear ICAcited by 33
  34. 2019Neural tangent kernels, transportation mappings, and universal approximationcited by 30
  35. 2019Explaining Convolutional Neural Networks using Softmax Gradient Layer-wise Relevance Propagationcited by 29
  36. 2013PANDA: Pose Aligned Networks for Deep Attribute Modelingcited by 23
  37. 2020Visualization of Supervised and Self-Supervised Neural Networks via Attribution Guided Factorizationcited by 23
  38. 2020Neural Methods for Point-wise Dependency Estimationcited by 22

50 most cited of 58 All 58 (JSON)

Built on by

Not cited yet.