paper-with-me

홈 › Papers

Deep Set Prediction Networks

2019-06-15 · NeurIPS 2019 12 · Yan Zhang, Jonathon Hare, Adam Prügel-Bennett

Current approaches for predicting sets from feature vectors ignore the unordered nature of sets and suffer from discontinuity issues as a result. We propose a general model for predicting sets that properly respects the structure of sets and avoids this problem. With a single feature vector as input, we show that our model is able to auto-encode point sets, predict the set of bounding boxes of objects in an image, and predict the set of attributes of these objects.

📄 PDF Abstract BibTeX arXiv:1906.06565

Code (1)

Cyanogenoid/dspn 공식 구현 pytorch

Tasks

Prediction

Similar Papers 제목 키워드 기반

Conformal e-prediction

2020-01-16 · Vladimir Vovk

This paper discusses a counterpart of conformal prediction for e-values, conformal e-prediction. Conformal e-prediction is conceptually simpler and had been developed in the 1990s as precursor of conformal prediction. Wh…

Conformal PredictionPrediction

Fuzzy Prediction Sets: Conformal Prediction with E-values

2025-09-16 · Nick W. Koning, Sam van Meer arxiv

Prediction sets offer a binary inclusion/exclusion for each element at the same fixed confidence level. We generalize to fuzzy prediction sets, which exclude elements at their own data-driven confidence level. Our key in…

Towards Human-AI Complementarity with Prediction Sets

2024-05-27 · Giovanni De Toni, Nastaran Okati, Suhas Thejaswi, Eleni Straitouri 외

Decision support systems based on prediction sets have proven to be effective at helping human experts solve classification tasks. Rather than providing single-label predictions, these systems provide sets of label predi…

Conformal PredictionPrediction

Electricity Price Prediction for Energy Storage System Arbitrage: A Decision-focused Approach

2023-04-30 · Linwei Sang, Yinliang Xu, Huan Long, Qinran Hu 외

Electricity price prediction plays a vital role in energy storage system (ESS) management. Current prediction models focus on reducing prediction errors but overlook their impact on downstream decision-making. So this pa…

Decision MakingManagementPrediction

Self-Calibrating Conformal Prediction

2024-02-11 · Lars van der Laan, Ahmed M. Alaa

In machine learning, model calibration and predictive inference are essential for producing reliable predictions and quantifying uncertainty to support decision-making. Recognizing the complementary roles of point and in…

Binary ClassificationConformal PredictionDecision MakingManagement+3