Furthermore, prior work's Typographic attacks against CLIP randomly sample a misleading class from a predefined set of categories.
Our results show that LLMs can, indeed, achieve good image classification performance when adapted this way.
To address this, we generate layer weights by learning to compose sets of SuperWeights, which represent a group of trainable parameters.
We call the resulting method ERM++, and show it significantly improves the performance of DG on five multi-source datasets by over 5% compared to standard ERM, and beats state-of-the-art despite being less computationally expensive.
1 code implementation • 26 Mar 2023 • Dina Bashkirova, Samarth Mishra, Diala Lteif, Piotr Teterwak, Donghyun Kim, Fadi Alladkani, James Akl, Berk Calli, Sarah Adel Bargal, Kate Saenko, Daehan Kim, Minseok Seo, YoungJin Jeon, Dong-Geol Choi, Shahaf Ettedgui, Raja Giryes, Shady Abu-Hussein, Binhui Xie, Shuang Li
To test the abilities of computer vision models on this task, we present the VisDA 2022 Challenge on Domain Adaptation for Industrial Waste Sorting.
We propose to use Relative Gradient Norm (RGN) as a way to measure the vulnerability of a backbone to feature distortion, and show that high RGN is indeed correlated with lower OOD performance.
We improve on these methods with MixtureEnsembles, which learns to factorize ensemble members with shared parameters by constructing each layer with a linear combination of templates.
Unsupervised domain adaptation (UDA) methods can dramatically improve generalization on unlabeled target domains.
Progress in machine learning is typically measured by training and testing a model on the same distribution of data, i. e., the same domain.
Existing methods struggle to extrapolate images with salient objects in the foreground or are limited to very specific objects such as humans, but tend to work well on indoor/outdoor scenes.
We use our reconstruction model as a tool for exploring the nature of representations, including: the influence of model architecture and training objectives (specifically robust losses), the forms of invariance that networks achieve, representational differences between correctly and incorrectly classified images, and the effects of manipulating logits and images.
Contrastive learning applied to self-supervised representation learning has seen a resurgence in recent years, leading to state of the art performance in the unsupervised training of deep image models.
Ranked #2 on Class Incremental Learning on cifar100
Image extension models have broad applications in image editing, computational photography and computer graphics.
Ranked #2 on Uncropping on Places2 val