English
Related papers

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

200 papers

Pretrained language models have improved zero-shot text classification by allowing the transfer of semantic knowledge from the training data in order to classify among specific label sets in downstream tasks. We propose a simple way to…

Computation and Language · Computer Science 2023-10-24 Lingyu Gao , Debanjan Ghosh , Kevin Gimpel

Low-shot image classification is a fundamental task in computer vision, and the emergence of large-scale vision-language models such as CLIP has greatly advanced the forefront of research in this field. However, most existing CLIP-based…

Computer Vision and Pattern Recognition · Computer Science 2024-04-02 Yibo Miao , Yu Lei , Feng Zhou , Zhijie Deng

We propose a novel taxonomy for bias evaluation of discriminative foundation models, such as Contrastive Language-Pretraining (CLIP), that are used for labeling tasks. We then systematically evaluate existing methods for mitigating bias in…

Computer Vision and Pattern Recognition · Computer Science 2023-10-19 Junaid Ali , Matthaeus Kleindessner , Florian Wenzel , Kailash Budhathoki , Volkan Cevher , Chris Russell

Deep learning models trained to optimize average accuracy often exhibit systematic failures on particular subpopulations. In real world settings, the subpopulations most affected by such disparities are frequently unlabeled or unknown,…

Machine Learning · Computer Science 2026-02-10 Abinitha Gourabathina , Hyewon Jeong , Teya Bergamaschi , Marzyeh Ghassemi , Collin Stultz

Multi-modality image fusion, particularly infrared and visible, plays a crucial role in integrating diverse modalities to enhance scene understanding. Although early research prioritized visual quality, preserving fine details and adapting…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Guanyao Wu , Haoyu Liu , Hongming Fu , Yichuan Peng , Jinyuan Liu , Xin Fan , Risheng Liu

Fine-grained entity typing aims to assign entity mentions in the free text with types arranged in a hierarchical structure. Traditional distant supervision based methods employ a structured data source as a weak supervision and do not need…

Computation and Language · Computer Science 2018-01-10 Denghui Zhang , Pengshan Cai , Yantao Jia , Manling Li , Yuanzhuo Wang , Xueqi Cheng

In computer vision, traditional ensemble learning methods exhibit either a low training efficiency or the limited performance to enhance the reliability of deep neural networks. In this paper, we propose a lightweight, loss-function-free,…

Computer Vision and Pattern Recognition · Computer Science 2024-08-09 Jiaqi Wu , Junbiao Pang , Qingming Huang

Existing text classification methods mainly focus on a fixed label set, whereas many real-world applications require extending to new fine-grained classes as the number of samples per label increases. To accommodate such requirements, we…

Computation and Language · Computer Science 2021-09-23 Dheeraj Mekala , Varun Gangal , Jingbo Shang

Class-level evaluation can conceal substantial performance disparities across subconcepts within the same class, causing models that perform well on average to fail on specific subpopulations. Prior work has shown that common evaluation…

Machine Learning · Computer Science 2026-04-30 Taylor Maxson , Roberto Corizzo , Yaning Wu , Nathalie Japkowicz , Colin Bellinger

Learning from feedback has been shown to enhance the alignment between text prompts and images in text-to-image diffusion models. However, due to the lack of focus in feedback content, especially regarding the object type and quantity,…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Xuexiang Niu , Jinping Tang , Lei Wang , Ge Zhu

Self-supervised pre-training, based on the pretext task of instance discrimination, has fueled the recent advance in label-efficient object detection. However, existing studies focus on pre-training only a feature extractor network to learn…

Computer Vision and Pattern Recognition · Computer Science 2024-02-16 Nanqing Dong , Linus Ericsson , Yongxin Yang , Ales Leonardis , Steven McDonagh

Weakly-supervised text classification trains a classifier using the label name of each target class as the only supervision, which largely reduces human annotation efforts. Most existing methods first use the label names as static…

Computation and Language · Computer Science 2023-10-23 Yunyi Zhang , Minhao Jiang , Yu Meng , Yu Zhang , Jiawei Han

Fine-tuning has proven to be highly effective in adapting pre-trained models to perform better on new desired tasks with minimal data samples. Among the most widely used approaches are reparameterization methods, which update a target…

Machine Learning · Computer Science 2025-10-27 Aymane El Firdoussi , El Mahdi Chayti , Mohamed El Amine Seddik , Martin Jaggi

Deep neural networks often exploit *spurious* features that are present in the majority of examples within a class during training. This leads to *poor worst-group test accuracy*, i.e., poor accuracy for minority groups that lack these…

Machine Learning · Computer Science 2025-04-18 Siddharth Joshi , Yu Yang , Yihao Xue , Wenhan Yang , Baharan Mirzasoleiman

Last-layer retraining methods have emerged as an efficient framework for correcting existing base models. Within this framework, several methods have been proposed to deal with correcting models for subgroup fairness with and without group…

Machine Learning · Computer Science 2024-06-17 Nathan Stromberg , Rohan Ayyagari , Sanmi Koyejo , Richard Nock , Lalitha Sankar

Training deep neural networks is challenging when large and annotated datasets are unavailable. Extensive manual annotation of data samples is time-consuming, expensive, and error-prone, notably when it needs to be done by experts. To…

Machine Learning · Computer Science 2021-09-08 Barbara C Benato , Alexandru C Telea , Alexandre X Falcão

In this paper, we present a semi-supervised fine-tuning approach designed to improve the performance of pre-trained foundation models on downstream tasks with limited labeled data. By leveraging content-style decomposition within an…

Computer Vision and Pattern Recognition · Computer Science 2024-10-07 Mariia Drozdova , Vitaliy Kinakh , Yury Belousov , Erica Lastufka , Slava Voloshynovskiy

This work addresses the challenge of achieving zero-shot adversarial robustness while preserving zero-shot generalization in large-scale foundation models, with a focus on the popular Contrastive Language-Image Pre-training (CLIP). Although…

Computer Vision and Pattern Recognition · Computer Science 2024-05-29 Fengji Ma , Li Liu , Hei Victor Cheng

This paper presents a novel method to improve the robustness of foundation models to group-based biases. We propose a simple yet effective method, called DoubleCCA, that leverages random sentences and Canonical Correlation Analysis (CCA) to…

Computation and Language · Computer Science 2024-11-26 Hong Liu , Yitong Lu

Few-shot image classifiers are designed to recognize and classify new data with minimal supervision and limited data but often show reliance on spurious correlations between classes and spurious attributes, known as spurious bias. Spurious…

Computer Vision and Pattern Recognition · Computer Science 2024-09-05 Guangtao Zheng , Wenqian Ye , Aidong Zhang