paper-with-me

Papers

PerceptionCLIP: Visual Classification by Inferring and Conditioning on Contexts

2023-08-02 · Bang An, Sicheng Zhu, Michael-Andrei Panaitescu-Liess, Chaithanya Kumar Mummadi, Furong Huang

Vision-language models like CLIP are widely used in zero-shot image classification due to their ability to understand various visual concepts and natural language descriptions. However, how to fully leverage CLIP's unprecedented human-like understanding capabilities to achieve better performance is still an open question. This paper draws inspiration from the human visual perception process: when classifying an object, humans first infer contextual attributes (e.g., background and orientation) which help separate the foreground object from the background, and then classify the object based on this information. Inspired by it, we observe that providing CLIP with contextual attributes improves zero-shot image classification and mitigates reliance on spurious features. We also observe that CLIP itself can reasonably infer the attributes from an image. With these observations, we propose a training-free, two-step zero-shot classification method PerceptionCLIP. Given an image, it first infers contextual attributes (e.g., background) and then performs object classification conditioning on them. Our experiments show that PerceptionCLIP achieves better generalization, group robustness, and interoperability. Our code is available at https://github.com/umd-huang-lab/perceptionCLIP

📄 PDF Abstract BibTeX arXiv:2308.01313

Code (1)

umd-huang-lab/perceptionclip 공식 구현 pytorch

Tasks

Classificationimage-classificationImage ClassificationLanguage ModellingObjectzero-shot-classificationZero-Shot Image ClassificationZero-Shot Learning

Methods 이 논문이 사용한 방법론

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

Inferring Discourse Relations from PDTB-style Discourse Labels for Argumentative Revision Classification

2016-12-01 · COLING 2016 12 · Fan Zhang, Diane Litman, Katherine Forbes Riley

Penn Discourse Treebank (PDTB)-style annotation focuses on labeling local discourse relations between text spans and typically ignores larger discourse contexts. In this paper we propose two approaches to infer discourse…

ClassificationGeneral Classification

GRIFT: A graphical model for inferring visual classification features from human data

2007-12-01 · NeurIPS 2007 12 · Michael Ross, Andrew Cohen

This paper describes a new model for human visual classification that enables the recovery of image features that explain human subjects' performance on different visual classification tasks. Unlike previous methods, thi…

ClassificationGeneral Classification

Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders

2019-10-25 · Andy T. Liu, Shu-wen Yang, Po-Han Chi, Po-chun Hsu 외

We present Mockingjay as a new speech representation learning approach, where bidirectional Transformer encoders are pre-trained on a large amount of unlabeled speech. Previous speech representation methods learn through…

General ClassificationRepresentation LearningSentiment AnalysisSentiment Classification+2

Visualizing Classification Structure of Large-Scale Classifiers

2020-07-12 · Bilal Alsallakh, Zhixin Yan, Shabnam Ghaffarzadegan, Zeng Dai 외

We propose a measure to compute class similarity in large-scale classification based on prediction scores. Such measure has not been formally pro-posed in the literature. We show how visualizing the class similarity matr…

ClassificationGeneral Classification

Inferring Concept Hierarchies from Text Corpora via Hyperbolic Embeddings

2019-02-03 · ACL 2019 7 · Matt Le, Stephen Roller, Laetitia Papaxanthos, Douwe Kiela 외

We consider the task of inferring is-a relationships from large text corpora. For this purpose, we propose a new method combining hyperbolic embeddings and Hearst patterns. This approach allows us to set appropriate cons…