Weakly Supervised Recovery of Semantic Attributes
arXiv:2103.11888
Abstract
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.
References in corpus (24)
- Axiomatic Attribution for Deep Networks
- Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
- DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients
- Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations
- Explaining NonLinear Classification Decisions with Deep Taylor Decomposition
- Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
- SmoothGrad: removing noise by adding noise
- Dual Learning for Machine Translation
- Not Just a Black Box: Learning Important Features Through Propagating Activation Differences
- Visualizing Deep Convolutional Neural Networks Using Natural Pre-Images
- Domain Adaptation: Learning Bounds and Algorithms
- Towards Robust Interpretability with Self-Explaining Neural Networks
- Recent Advances in Autoencoder-Based Representation Learning
- Distilling a Neural Network Into a Soft Decision Tree
- A critical analysis of self-supervision, or what we can learn from a single image
- See Better Before Looking Closer: Weakly Supervised Data Augmentation Network for Fine-Grained Visual Classification
- Full-Gradient Representation for Neural Network Visualization
- Learning Independent Features with Adversarial Nets for Non-linear ICA
- Adaptive Neural Trees
- Explaining Convolutional Neural Networks using Softmax Gradient Layer-wise Relevance Propagation
- The Role of Minimal Complexity Functions in Unsupervised Learning of Semantic Mappings
- Disentangling Influence: Using Disentangled Representations to Audit Model Predictions
- Visualization of Supervised and Self-Supervised Neural Networks via Attribution Guided Factorization
- Block Coordinate Descent Only Converge to Minimizers