paper-with-me

Papers

Critic Guided Segmentation of Rewarding Objects in First-Person Views

2021-07-20 · Andrew Melnik, Augustin Harter, Christian Limberg, Krishan Rana, Niko Suenderhauf, Helge Ritter

This work discusses a learning approach to mask rewarding objects in images using sparse reward signals from an imitation learning dataset. For that, we train an Hourglass network using only feedback from a critic model. The Hourglass network learns to produce a mask to decrease the critic's score of a high score image and increase the critic's score of a low score image by swapping the masked areas between these two images. We trained the model on an imitation learning dataset from the NeurIPS 2020 MineRL Competition Track, where our model learned to mask rewarding objects in a complex interactive 3D environment with a sparse reward signal. This approach was part of the 1st place winning solution in this competition. Video demonstration and code: https://rebrand.ly/critic-guided-segmentation

📄 PDF Abstract BibTeX arXiv:2107.09540

Code (1)

ndrwmlnk/critic-guided-segmentation-of-rewarding-objects-in-first-person-views pytorch

Tasks

Imitation Learning

Similar Papers 제목 키워드 기반

Critic-Guided Learning to Segment Rewarding Objects in First-Person Views

2021-03-09 · ICLR Workshop SSL-RL 2021 5 · Anonymous

We train a U-Net model to generate masks over reward-related objects in images. Our approach allows to train the U-Net model without explicit label information, but only using feedback from a critic model which learned t…

SegEarth-R2: Towards Comprehensive Language-guided Segmentation for Remote Sensing Images

2025-12-23 · Zepeng Xin, Kaiyu Li, Luodi Chen, Wanchen Li 외 arxiv

Effectively grounding complex language to pixels in remote sensing (RS) images is a critical challenge for applications like disaster response and environmental monitoring. Current models can parse simple, single-target …

Temporal Self-Rewarding Language Models: Decoupling Chosen-Rejected via Past-Future

2025-08-08 · Yidong Wang, Xin Wang, Cunxiang Wang, Junfeng Fang 외 arxiv

Self-Rewarding Language Models propose an architecture in which the Large Language Models(LLMs) both generates responses and evaluates its own outputs via LLM-as-a-Judge prompting, dynamically improving its generative ca…

Mathematical ReasoningCode Generation

Object-Guided Instance Segmentation With Auxiliary Feature Refinement for Biological Images

2021-06-14 · Jingru Yi, Pengxiang Wu, Hui Tang, Bo Liu 외

Instance segmentation is of great importance for many biological applications, such as study of neural cell interactions, plant phenotyping, and quantitatively measuring how cells react to drug treatment. In this paper, …

Instance SegmentationObjectPlant PhenotypingSegmentation+1

DR$^2$Seg: Decomposed Two-Stage Rollouts for Efficient Reasoning Segmentation in Multimodal Large Language Models

2026-01-15 · Yulin He, Wei Chen, Zhikang Jian, Tianhang Guo 외 arxiv

Reasoning segmentation is an emerging vision-language task that requires reasoning over intricate text queries to precisely segment objects. However, existing methods typically suffer from overthinking, generating verbos…

Multimodal ReasoningObject Localization