Search Results for author:
Found 22 papers, 9 papers with code
Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)
CLIP embeddings have demonstrated remarkable performance across a wide range of computer vision tasks.
Certifying LLM Safety against Adversarial Prompting
We defend against three attack modes: i) adversarial suffix, where an adversarial sequence is appended at the end of a harmful prompt; ii) adversarial insertion, where the adversarial sequence is inserted anywhere in the middle of the prompt; and iii) adversarial infusion, where adversarial tokens are inserted at arbitrary positions in the prompt, not necessarily as a contiguous block.
Discriminative Feature Attributions: Bridging Post Hoc Explainability and Inherent Interpretability
This strategy naturally combines the ease of use of post hoc explanations with the faithfulness of inherently interpretable models.
Efficient Estimation of Average-Case Robustness for Multi-Class Classification
These estimators linearize models in the local region around an input and analytically compute the robustness of the resulting linear models.
On Minimizing the Impact of Dataset Shifts on Actionable Explanations
To this end, we conduct rigorous theoretical analysis to demonstrate that model curvature, weight decay parameters while training, and the magnitude of the dataset shift are key factors that determine the extent of explanation (in)stability.
Consistent Explanations in the Face of Model Indeterminacy via Ensembling
This work addresses the challenge of providing consistent explanations for predictive models in the presence of model indeterminacy, which arises due to the existence of multiple (nearly) equally well-performing models for a given dataset and task.
Word-Level Explanations for Analyzing Bias in Text-to-Image Models
We introduce a method for computing scores for each word in the prompt; these scores represent its influence on biases in the model's output.
Which Models have Perceptually-Aligned Gradients? An Explanation via Off-Manifold Robustness
Quantifying the perceptual alignment of model gradients via their similarity with the gradients of generative models, we show that off-manifold robustness correlates well with perceptual alignment.
Efficiently Training Low-Curvature Neural Networks
To achieve this, we minimize a data-independent upper bound on the curvature of a neural network, which decomposes overall curvature in terms of curvatures and slopes of its constituent layers.
Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanations
By bringing diverse explanation methods into a common framework, this work (1) advances the conceptual understanding of these methods, revealing their shared local function approximation objective, properties, and relation to one another, and (2) guides the use of these methods in practice, providing a principled approach to choose among methods and paving the way for the creation of new ones.
Data-Efficient Structured Pruning via Submodular Optimization
Structured pruning is an effective approach for compressing large pre-trained neural networks without significantly affecting their performance.
Cyclical Pruning for Sparse Neural Networks
Current methods for pruning neural network weights iteratively apply magnitude-based pruning on the model weights and re-train the resulting model to recover lost accuracy.
Rethinking the Role of Gradient-Based Attribution Methods for Model Interpretability
This leads us to hypothesize that the highly structured and explanatory nature of input-gradients may be due to the alignment of this class-conditional model $p_{\theta}(x \mid y)$ with that of the ground truth data distribution $p_{\text{data}} (x \mid y)$.
Full-Gradient Representation for Neural Network Visualization
Our experiments reveal that our method explains model behaviour correctly, and more comprehensively than other methods in the literature.
Knowledge Transfer with Jacobian Matching
We then rely on this analysis to apply Jacobian matching to transfer learning by establishing equivalence of a recent transfer learning procedure to distillation.
Confidence estimation in Deep Neural networks via density modelling
State-of-the-art Deep Neural Networks can be easily fooled into providing incorrect high-confidence predictions for images with small amounts of adversarial noise.
Training Sparse Neural Networks
Deep neural networks with lots of parameters are typically used for large-scale computer vision tasks such as image classification.
Generalized Dropout
One set of methods in this family, called Dropout++, is a version of Dropout with trainable parameters.
Compensating for Large In-Plane Rotations in Natural Images
This is inspired by the neuro-scientific concept of mental rotation, which humans use to compare pairs of rotated objects.
A Taxonomy of Deep Convolutional Neural Nets for Computer Vision
With this new paradigm, every problem in computer vision is now being re-examined from a deep learning perspective.
Learning Neural Network Architectures using Backpropagation
In this work, we introduce the problem of architecture-learning, i. e; learning the architecture of a neural network along with weights.
Data-free parameter pruning for Deep Neural Networks
Our experiments in pruning the densely connected layers show that we can remove upto 85\% of the total parameters in an MNIST-trained network, and about 35\% for AlexNet without significantly affecting performance.
