Related papers: Connect Later: Improving Fine-tuning for Robustnes…

Instruction tuning of language models has demonstrated the ability to enhance model generalization to unseen tasks via in-context learning using a few examples. However, typical supervised learning still requires a plethora of downstream…

The impressive performance of deep learning architectures is associated with a massive increase in model complexity. Millions of parameters need to be tuned, with training and inference time scaling accordingly, together with energy…

Unsupervised domain adaptation (UDA) methods intend to reduce the gap between source and target domains by using unlabeled target domain and labeled source domain data, however, in the medical domain, target domain data may not always be…

Finetuning image-text models such as CLIP achieves state-of-the-art accuracies on a variety of benchmarks. However, recent works like WiseFT (Wortsman et al., 2021) and LP-FT (Kumar et al., 2022) have shown that even subtle differences in…

Neural language models (LMs) are vulnerable to training data extraction attacks due to data memorization. This paper introduces a novel attack scenario wherein an attacker adversarially fine-tunes pre-trained LMs to amplify the exposure of…

The full potential of large pretrained models remains largely untapped in control domains like robotics. This is mainly because of the scarcity of data and the computational challenges associated with training or fine-tuning these large…

Few-shot slot tagging is an emerging research topic in the field of Natural Language Understanding (NLU). With sufficient annotated data from source domains, the key challenge is how to train and adapt the model to another target domain…

The waive of labels in the target domain makes Unsupervised Domain Adaptation (UDA) an attractive technique in many real-world applications, though it also brings great challenges as model adaptation becomes harder without labeled target…

Synthetically augmenting training datasets with diffusion models has become an effective strategy for improving the generalization of image classifiers. However, existing approaches typically increase dataset size by 10-30x and struggle to…

Recent deep learning methods for object detection rely on a large amount of bounding box annotations. Collecting these annotations is laborious and costly, yet supervised models do not generalize well when testing on images from a different…

There is growing evidence that pretrained language models improve task-specific fine-tuning not just for the languages seen in pretraining, but also for new languages and even non-linguistic data. What is the nature of this surprising…

We propose associative domain adaptation, a novel technique for end-to-end domain adaptation with neural networks, the task of inferring class labels for an unlabeled target domain based on the statistical properties of a labeled source…

We introduce LiDAR-UDA, a novel two-stage self-training-based Unsupervised Domain Adaptation (UDA) method for LiDAR segmentation. Existing self-training methods use a model trained on labeled source data to generate pseudo labels for target…

Post-training (via supervised fine-tuning) improves instruction-following, but often induces semantic mode collapse by biasing models toward low-entropy fine-tuning data at the expense of the high-entropy pretraining distribution.…

Test-time adaptation (TTA) aims to adapt a trained classifier using online unlabeled test data only, without any information related to the training procedure. Most existing TTA methods adapt the trained classifier using the classifier's…

Vision-language models (VLMs) such as CLIP exhibit strong Out-of-distribution (OOD) detection capabilities by aligning visual and textual representations. Recent CLIP-based test-time adaptation methods further improve detection performance…

Domain adaptation methods for 2D human pose estimation typically require continuous access to the source data during adaptation, which can be challenging due to privacy, memory, or computational constraints. To address this limitation, we…

Generalisation of deep neural networks becomes vulnerable when distribution shifts are encountered between train (source) and test (target) domain data. Few-shot domain adaptation mitigates this issue by adapting deep neural networks…

Learned image compression (LIC) has achieved state-of-the-art rate-distortion performance, deemed promising for next-generation image compression techniques. However, pre-trained LIC models usually suffer from significant performance…

We propose Regularized Learning under Label shifts (RLLS), a principled and a practical domain-adaptation algorithm to correct for shifts in the label distribution between a source and a target domain. We first estimate importance weights…