paper-with-me

Papers

Evaluating Language-biased image classification based on semantic compositionality

2021-09-29 · ICLR 2022 4 · Yoann Lemesle, Masataka Sawayama, Guillermo Valle-Perez, Maxime Adolphe, Hélène Sauzéon, Pierre-Yves Oudeyer

Humans show language-biased image recognition for a word-embedded image, known as picture-word interference. Such interference depends on hierarchical semantic categories and reflects that human language processing highly interacts with visual processing. Similar to humans, recent artificial models jointly trained on texts and images, e.g., OpenAI CLIP, show language-biased image classification. Exploring whether the bias leads to interferences similar to those observed in humans can contribute to understanding how much the model acquires hierarchical semantic representations from joint learning of language and vision. The present study introduces methodological tools from the cognitive science literature to assess the biases of artificial models. Specifically, we introduce a benchmark task to test whether words superimposed on images can distort the image classification across different category levels and, if it can, whether the perturbation is due to the shared semantic representation between language and vision. Our dataset is a set of word-embedded images and consists of a mixture of natural image datasets and hierarchical word labels with superordinate/basic category levels. Using this benchmark test, we evaluate the CLIP model. We show that presenting words distorts the image classification by the model across different category levels, but the effect does not depend on the semantic relationship between images and embedded words. This suggests that the semantic word representation in the CLIP visual processing is not shared with the image representation, although the word representation strongly dominates for word-embedded images.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Classificationimage-classificationImage Classification

Methods 이 논문이 사용한 방법론

Test 설명 없음
CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

Language-biased image classification: evaluation based on semantic representations

2022-01-26 · Yoann Lemesle, Masataka Sawayama, Guillermo Valle-Perez, Maxime Adolphe 외

Humans show language-biased image recognition for a word-embedded image, known as picture-word interference. Such interference depends on hierarchical semantic categories and reflects that human language processing highl…

Classificationimage-classificationImage Classification

FewVS: A Vision-Semantics Integration Framework for Few-Shot Image Classification

2024-10-28 · Proceedings of the 32nd ACM International Conference on Multimedia 2024 10 · Zhuoling Li, Yong Wang, Kaitong Li

Some recent methods address few-shot image classification by extracting semantic information from class names and devising mechanisms for aligning vision and semantics to integrate information from both modalities. Howev…

Few-Shot Image ClassificationFew-Shot Learningimage-classificationImage Classification

RBC: Rectifying the Biased Context in Continual Semantic Segmentation

2022-03-16 · Hanbin Zhao, Fengyu Yang, Xinghe Fu, Xi Li

Recent years have witnessed a great development of Convolutional Neural Networks in semantic segmentation, where all classes of training images are simultaneously available. In practice, new images are usually made avail…

Continual Semantic SegmentationSegmentationSemantic Segmentation

Egoshots, an ego-vision life-logging dataset and semantic fidelity metric to evaluate diversity in image captioning models

2020-03-26 · Pranav Agarwal, Alejandro Betancourt, Vana Panagiotou, Natalia Díaz-Rodríguez

Image captioning models have been able to generate grammatically correct and human understandable sentences. However most of the captions convey limited information as the model used is trained on datasets that do not ca…

DiversityImage CaptioningObject Recognition

Approximated Doubly Robust Search Relevance Estimation

2022-08-16 · Lixin Zou, Changying Hao, Hengyi Cai, Suqi Cheng 외

Extracting query-document relevance from the sparse, biased clickthrough log is among the most fundamental tasks in the web search system. Prior art mainly learns a relevance judgment model with semantic features of the …

counterfactual