Related papers: Project-Probe-Aggregate: Efficient Fine-Tuning for…

Learning from a few examples is an important practical aspect of training classifiers. Various works have examined this aspect quite well. However, all existing approaches assume that the few examples provided are always correctly labeled.…

Adapting pre-trained foundation models for diverse downstream tasks is a core practice in artificial intelligence. However, the wide range of tasks and high computational costs make full fine-tuning impractical. To overcome this,…

Learning from a few examples is a challenging task for machine learning. While recent progress has been made for this problem, most of the existing methods ignore the compositionality in visual concept representation (e.g. objects are built…

Structured prediction requires models to generate ontology-constrained labels, grounded evidence, and valid structure under ambiguity, label skew, and heterogeneous group difficulty. We present a two-part framework for controllable…

Neural image classifiers can often learn to make predictions by overly relying on non-predictive features that are spuriously correlated with the class labels in the training data. This leads to poor performance in real-world atypical…

Image assessment aims to evaluate the quality and aesthetics of images and has been applied across various scenarios, such as natural and AIGC scenes. Existing methods mostly address these sub-tasks or scenes individually. While some works…

Test-time task adaptation in few-shot learning aims to adapt a pre-trained task-agnostic model for capturing taskspecific knowledge of the test task, rely only on few-labeled support samples. Previous approaches generally focus on…

Predictive performance of machine learning models trained with empirical risk minimization (ERM) can degrade considerably under distribution shifts. The presence of spurious correlations in training datasets leads ERM-trained models to…

Fine-tuning large foundation models is essential for building expert models tailored to specialized tasks and domains, but fully updating billions of parameters is computationally prohibitive. Reducing the number of trainable parameters…

A widely used algorithm for transfer learning is fine-tuning, where a pre-trained model is fine-tuned on a target task with a small amount of labeled data. When the capacity of the pre-trained model is significantly larger than the size of…

Pre-trained vision-language models learn massive data to model unified representations of images and natural languages, which can be widely applied to downstream machine learning tasks. In addition to zero-shot inference, in order to better…

Fine-tuning large pre-trained foundation models, such as the 175B GPT-3, has attracted more attention for downstream tasks recently. While parameter-efficient fine-tuning methods have been proposed and proven effective without retraining…

Parameter-efficient fine-tuning stands as the standard for efficiently fine-tuning large language and vision models on downstream tasks. Specifically, the efficiency of low-rank adaptation has facilitated the creation and sharing of…

Improper or erroneous labelling can pose a hindrance to reliable generalization for supervised learning. This can have negative consequences, especially for critical fields such as healthcare. We propose an effective new approach for…

As few-shot object detectors are often trained with abundant base samples and fine-tuned on few-shot novel examples,the learned models are usually biased to base classes and sensitive to the variance of novel examples. To address this…

Vision-Language Models such as CLIP exhibit strong zero-shot recognition capability by aligning images with textual concepts, yet they often underperform on multi-label recognition where multiple objects co-exist. A key bottleneck is that…

Domain Adaptation of Black-box Predictors (DABP) aims to learn a model on an unlabeled target domain supervised by a black-box predictor trained on a source domain. It does not require access to both the source-domain data and the predictor…

To enhance group robustness to spurious correlations, prior work often relies on auxiliary group annotations and assumes identical sets of groups across training and test domains. To overcome these limitations, we propose to leverage…

Despite its significant success, object detection in traffic and transportation scenarios requires time-consuming and laborious efforts in acquiring high-quality labeled data. Therefore, Unsupervised Domain Adaptation (UDA) for object…

This work proposes a robust Partial Domain Adaptation (PDA) framework that mitigates the negative transfer problem by incorporating a robust target-supervision strategy. It leverages ensemble learning and includes diverse, complementary…