paper-with-me

Papers

Tailoring Visual Object Representations to Human Requirements: A Case Study with a Recycling Robot

2022-12-14 · Conference On Robot Learning (CoRL) 2022 12 · Debasmita Ghose, Michal Adam Lewkowicz, Kaleb Gezahegn, Julian Lee, Timothy Adamson, Marynel Vazquez, Brian Scassellati

Robots are well-suited to alleviate the burden of repetitive and tedious manipulation tasks. In many applications, though, a robot may be asked to interact with a wide variety of objects, making it hard or even impossible to pre-program visual object classifiers suitable for the task of interest. In this work, we study the problem of learning a classifier for visual objects based on a few examples provided by humans. We frame this problem from the perspective of learning a suitable visual object representation that allows us to distinguish the desired object category from others. Our proposed approach integrates human supervision into the representation learning process by combining contrastive learning with an additional loss function that brings the representations of human examples close to each other in the latent space. Our experiments show that our proposed method performs better than self-supervised and fully supervised learning methods in offline evaluations and can also be used in real-time by a robot in a simplified recycling domain, where recycling streams contain a variety of objects.

📄 PDF Abstract BibTeX

Code (1)

ScazLab/HumanSupContrastiveClustering pytorch

Tasks

Contrastive LearningObjectRepresentation Learning

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Tailoring: encoding inductive biases by optimizing unsupervised objectives at prediction time

2020-09-22 · NeurIPS 2021 12 · Ferran Alet, Maria Bauza, Kenji Kawaguchi, Nurullah Giray Kuru 외

From CNNs to attention mechanisms, encoding inductive biases into neural networks has been a fruitful source of improvement in machine learning. Adding auxiliary losses to the main objective function is a general way of …

Inductive BiasMeta-LearningTransductive Learning

Towards a Framework for Visual Intelligence in Service Robotics: Epistemic Requirements and Gap Analysis

2020-03-13 · Agnese Chiatti, Enrico Motta, Enrico Daga

A key capability required by service robots operating in real-world, dynamic environments is that of Visual Intelligence, i.e., the ability to use their vision system, reasoning components and background knowledge to mak…

Object Recognition

ClothHMR: 3D Mesh Recovery of Humans in Diverse Clothing from Single Image

2025-12-19 · Yunqi Gao, Leyuan Liu, Yuhan Li, Changxin Gao 외 arxiv

With 3D data rapidly emerging as an important form of multimedia information, 3D human mesh recovery technology has also advanced accordingly. However, current methods mainly focus on handling humans wearing tight clothi…

Human Mesh Recovery

Instruction-Driven Fusion of Infrared-Visible Images: Tailoring for Diverse Downstream Tasks

2024-11-14 · Zengyi Yang, Yafei Zhang, Huafeng Li, Yu Liu

The primary value of infrared and visible image fusion technology lies in applying the fusion results to downstream tasks. However, existing methods face challenges such as increased training complexity and significantly…

Infrared And Visible Image Fusionobject-detectionObject DetectionSalient Object Detection+2

Text-to-Sticker: Style Tailoring Latent Diffusion Models for Human Expression

2023-11-17 · Animesh Sinha, Bo Sun, Anmol Kalia, Arantxa Casanova 외

We introduce Style Tailoring, a recipe to finetune Latent Diffusion Models (LDMs) in a distinct domain with high visual quality, prompt alignment and scene diversity. We choose sticker image generation as the target doma…

DiversityImage GenerationPrompt Engineering