81 citations · 173 across the 19 of their papers we have counts for
9 papers · 1 filter
From Misclassifications to Outliers: Joint Reliability Assessment in Classification
Yang Li, Youyang Sha, Yinzhi Wang +4
Building reliable classifiers is a fundamental challenge for deploying machine learning in real-world applications. A reliable system should not only detect out-of-distribution (OO…
EditVal: Benchmarking Diffusion Based Text-Guided Image Editing Methods
Samyadeep Basu, Mehrdad Saberi, Shweta Bhardwaj +5
A plethora of text-guided image editing methods have recently been developed by leveraging the impressive capabilities of large-scale diffusion-based generative models such as Imag…
Distilling Knowledge from Text-to-Image Generative Models Improves Visio-Linguistic Reasoning in CLIP
Samyadeep Basu, Shell Xu Hu, Maziar Sanjabi +2
Image-text contrastive models like CLIP have wide applications in zero-shot classification, image-text retrieval, and transfer learning. However, they often struggle on composition…
Strong Baselines for Parameter Efficient Few-Shot Fine-tuning
Samyadeep Basu, Daniela Massiceti, Shell Xu Hu +1
Few-shot classification (FSC) entails learning novel classes given only a few examples per class after a pre-training (or meta-training) phase on a set of base classes. Recent work…
TokenCut: Segmenting Objects in Images and Videos with Self-supervised Transformer and Normalized Cut
Yangtao Wang, Xi Shen, Yuan Yuan +5
In this paper, we describe a graph-based algorithm that uses the features obtained by a self-supervised transformer to detect and segment salient objects in images and videos. With…
Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference
Shell Xu Hu, Da Li, Jan Stühmer +2
Few-shot learning (FSL) is an important and topical problem in computer vision that has motivated extensive research into numerous methods spanning from sophisticated meta-learning…
Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut
Yangtao Wang, Xi Shen, Shell Hu +3
Transformers trained with self-supervised learning using self-distillation loss (DINO) have been shown to produce attention maps that highlight salient foreground objects. In this…
Boosting Co-teaching with Compression Regularization for Label Noise
Yingyi Chen, Xi Shen, Shell Xu Hu +1
In this paper, we study the problem of learning image classification models in the presence of label noise. We revisit a simple compression regularization named Nested Dropout. We…
Variational Information Distillation for Knowledge Transfer
Sungsoo Ahn, Shell Xu Hu, Andreas Damianou +2
Transferring knowledge from a teacher neural network pretrained on the same or a similar task to a student neural network can significantly improve the performance of the student n…