skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Correct for Whom? Subjectivity and the Evaluation of Personalized Image Aesthetics Assessment Models
The problem of image aesthetic quality assessment is surprisingly difficult to define precisely. Most early work attempted to estimate the average aesthetic rating of a group of observers, while some recent work has shifted to an approach based on few-shot personalization. In this paper, we connect few-shot personalization, via Immanuel Kant's concept of disinterested judgment, to an argument from feminist aesthetics about the biased tendencies of objective standards for subjective pleasures. To empirically investigate this philosophical debate, we introduce PR-AADB, a relabeling of the existing AADB dataset with labels for pairs of images, and measure how well the existing groundtruth predicts our new pairwise labels. We find, consistent with the feminist critique, that both the existing groundtruth and few-shot personalized predictions represent some users' preferences significantly better than others, but that it is difficult to predict when and for whom the existing groundtruth will be correct. We thus advise against using benchmark datasets to evaluate models for personalized IAQA, and recommend caution when attempting to account for subjective difference using machine learning more generally.  more » « less
Award ID(s):
2112635
PAR ID:
10475043
Author(s) / Creator(s):
; ;
Publisher / Repository:
Proceedings of the AAAI Conference on Artificial Intelligence
Date Published:
Journal Name:
Proceedings of the AAAI Conference on Artificial Intelligence
Volume:
37
Issue:
10
ISSN:
2159-5399
Page Range / eLocation ID:
11818 to 11827
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; ; ; ; ; ; (, Advances in neural information processing systems)
    Weak supervision (WS) is a powerful method to build labeled datasets for training supervised models in the face of little-to-no labeled data. It replaces hand-labeling data with aggregating multiple noisy-but-cheap label estimates expressed by labeling functions (LFs). While it has been used successfully in many domains, weak supervision's application scope is limited by the difficulty of constructing labeling functions for domains with complex or high-dimensional features. To address this, a handful of methods have proposed automating the LF design process using a small set of ground truth labels. In this work, we introduce AutoWS-Bench-101: a framework for evaluating automated WS (AutoWS) techniques in challenging WS settings -- a set of diverse application domains on which it has been previously difficult or impossible to apply traditional WS techniques. While AutoWS is a promising direction toward expanding the application-scope of WS, the emergence of powerful methods such as zero-shot foundation models reveals the need to understand how AutoWS techniques compare or cooperate with modern zero-shot or few-shot learners. This informs the central question of AutoWS-Bench-101: given an initial set of 100 labels for each task, we ask whether a practitioner should use an AutoWS method to generate additional labels or use some simpler baseline, such as zero-shot predictions from a foundation model or supervised learning. We observe that in many settings, it is necessary for AutoWS methods to incorporate signal from foundation models if they are to outperform simple few-shot baselines, and AutoWS-Bench-101 promotes … 
    more » « less
  2. ; (, 2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA))
    In realistic speech enhancement settings for end-user devices, we often encounter only a few speakers and noise types that tend to reoccur in the specific acoustic environment. We propose a novel personalized speech enhancement method to adapt a compact denoising model to the test-time specificity. Our goal in this test-time adaptation is to utilize no clean speech target of the test speaker, thus fulfilling the requirement for zero-shot learning. To complement the lack of clean speech, we employ the knowledge distillation framework: we distill the more advanced denoising results from an overly large teacher model, and use them as the pseudo target to train the small student model. This zero-shot learning procedure circumvents the process of collecting users' clean speech, a process that users are reluctant to comply due to privacy concerns and technical difficulty of recording clean voice. Experiments on various test-time conditions show that the proposed personalization method can significantly improve the compact models' performance during the test time. Furthermore, since the personalized models outperform larger non-personalized baseline models, we claim that personalization achieves model compression with no loss of denoising performance. As expected, the student models underperform the state-of-the-art teacher models. 
    more » « less
  3. ; ; ; ; ; (, ACM Transactions on Applied Perception)
    Color composition (or color theme) is a key factor to determine how well a piece of art work or graphical design is perceived by humans. Despite a few color harmony models have been proposed, their results are often less satisfactory since they mostly neglect the variations of aesthetic cognition among individuals and treat the influence of all ratings equally as if they were all rated by the same anonymous user. To overcome this issue, in this article we propose a new color theme evaluation model by combining a back propagation neural network and a kernel probabilistic model to infer both the color theme rating and the user aesthetic preference. Our experiment results show that our model can predict more accurate and personalized color theme ratings than state of the art methods. Our work is also the first-of-its-kind effort to quantitatively evaluate the correlation between user aesthetic preferences and color harmonies of five-color themes, and study such a relation for users with different aesthetic cognition. 
    more » « less
  4. ; ; ; ; ; ; (, Curran Associates, Inc.)
    Personalization has emerged as a critical research area in modern intelligent systems, focusing on mining users' behavioral history and adapting to their preferences for delivering tailored experiences. Despite the remarkable few-shot capabilities exhibited by black-box large language models (LLMs), the inherent opacity of their model parameters presents significant challenges in aligning the generated output with individual expectations. Existing solutions have primarily focused on prompt design to incorporate user-specific profiles and behaviors; however, such approaches often struggle to generalize effectively due to their inability to capture shared knowledge among all users. To address these challenges, we propose HYDRA, a model factorization framework that captures both user-specific behavior patterns from historical data and shared general knowledge among all users to deliver personalized generation. In order to capture user-specific behavior patterns, we first train a reranker to prioritize the most useful information from top-retrieved relevant historical records. By combining the prioritized history with the corresponding query, we train an adapter to align the output with individual user-specific preferences, eliminating the reliance on access to inherent model parameters of black-box LLMs. Both the reranker and the adapter can be decomposed into a base model with multiple user-specific heads, resembling a hydra. The base model maintains shared knowledge across users, while the multiple personal heads capture user-specific preferences. Experimental results demonstrate that \method outperforms existing state-of-the-art prompt-based methods by an average relative improvement of 9.01% across five diverse personalization tasks in the LaMP benchmark. 
    more » « less
  5. ; ; ; ; (, International Conference on Learning Representations)
    Few-shot classification aims to learn a classifier to recognize unseen classes during training with limited labeled examples. While significant progress has been made, the growing complexity of network designs, meta-learning algorithms, and differences in implementation details make a fair comparison difficult. In this paper, we present 1) a consistent comparative analysis of several representative few-shot classification algorithms, with results showing that deeper backbones significantly reduce the gap across methods when domain differences are limited, 2) a slightly modified baseline method that surprisingly achieves competitive performance when compared with the state-of-the-art on both the mini-ImageNet and the CUB datasets, and 3) a new experimental setting for evaluating the cross-domain generalization ability for few-shot classification algorithms. Our results reveal that reducing intra-class variation is an important factor when the feature backbone is shallow, but not as critical when using deeper backbones. In a realistic, cross-domain evaluation setting, we show that a baseline method with a standard fine-tuning practice compares favorably against other state-of-the-art few-shot learning algorithms. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email