Search Results for author:
Found 14 papers, 8 papers with code
Whispering Experts: Neural Interventions for Toxicity Mitigation in Language Models
We also show that AurA is effective with models of different scale (from 1. 5B to 40B parameters), and its effectiveness in mitigating toxic language, while preserving common-sense zero-shot abilities, holds across all scales.
Interpreting CLIP: Insights on the Robustness to ImageNet Distribution Shifts
While for ImageNet distribution shifts it has been shown that such differences in robustness can be traced back predominantly to differences in training data, so far it is not known what that translates to in terms of what the model has learned.
The Role of Entropy and Reconstruction in Multi-View Self-Supervised Learning
We consider a different lower bound on the MI consisting of an entropy and a reconstruction term (ER), and analyze the main MVSSL families through its lens.
Challenging Common Assumptions about Catastrophic Forgetting
In this paper, we study the progressive knowledge accumulation (KA) in DNNs trained with gradient-based algorithms in long sequences of tasks with data re-occurrence.
Continual Learning with Foundation Models: An Empirical Study of Latent Replay
Motivated by this, we study the efficacy of pre-trained vision models as a foundation for downstream continual learning (CL) scenarios.
SSR: Semi-supervised Soft Rasterizer for single-view 2D to 3D Reconstruction
In order to obtain the viewpoints for these unlabeled images, we propose to use a Siamese network that takes two images as input and outputs whether they correspond to the same viewpoint.
Can Active Learning Preemptively Mitigate Fairness Issues?
We also explore the interaction of algorithmic fairness methods such as gradient reversal (GRAD) and BALD.
Synbols: Probing Learning Algorithms with Synthetic Datasets
Progress in the field of machine learning has been fueled by the introduction of benchmark datasets pushing the limits of existing algorithms.
Embedding Propagation: Smoother Manifold for Few-Shot Classification
Furthermore, we show that embedding propagation consistently improves the accuracy of the models in multiple semi-supervised learning scenarios by up to 16\% points.
Attend and Rectify: a Gated Attention Mechanism for Fine-Grained Recovery
We propose a novel attention mechanism to enhance Convolutional Neural Networks for fine-grained recognition.
Ranked #107 on
Image Classification
on CIFAR-100
(using extra training data)
Beyond One-hot Encoding: lower dimensional target embedding
Following this observation, we embed the targets into a low-dimensional space, drastically improving convergence speed while preserving accuracy.
Deep Inference of Personality Traits by Integrating Image and Word Use in Social Networks
Following this trend on visual-based social analysis, we present a novel methodology based on Deep Learning to build a combined image-and-text based personality trait model, trained with images posted together with words found highly correlated to specific personality traits.
A Painless Attention Mechanism for Convolutional Neural Networks
We propose a novel attention mechanism to enhance Convolutional Neural Networks for fine-grained recognition.
Regularizing CNNs with Locally Constrained Decorrelations
In this paper, we show that regularizing negatively correlated features is an obstacle for effective decorrelation and present OrthoReg, a novel regularization technique that locally enforces feature orthogonality.
