paper-with-me

Papers

HindSight: A Graph-Based Vision Model Architecture For Representing Part-Whole Hierarchies

2021-04-08 · Muhammad AbdurRafae

This paper presents a model architecture for encoding the representations of part-whole hierarchies in images in form of a graph. The idea is to divide the image into patches of different levels and then treat all of these patches as nodes for a fully connected graph. A dynamic feature extraction module is used to extract feature representations from these patches in each graph iteration. This enables us to learn a rich graph representation of the image that encompasses the inherent part-whole hierarchical information. Utilizing proper self-supervised training techniques, such a model can be trained as a general purpose vision encoder model which can then be used for various vision related downstream tasks (e.g., Image Classification, Object Detection, Image Captioning, etc.).

📄 PDF Abstract BibTeX arXiv:2104.03722

Code (0)

등록된 구현이 없습니다.

Tasks

Image Captioningimage-classificationImage Classificationobject-detectionObject Detection

Similar Papers 제목 키워드 기반

TurnSight: Turn-Level Hindsight Self-Distillation for Tool-Integrated Reasoning

2026-08-04 · Changle Qu, Sunhao Dai, Hengyi Cai, Yuqi Zhou 외 hf

Tool-Integrated Reasoning (TIR) enables LLMs to solve complex tasks through iterative tool interactions. However, existing reinforcement learning methods often rely on trajectory-level supervision, limiting fine-grained …

Reinforcement Learning

Visual Hindsight Self-Imitation Learning for Interactive Navigation

2023-12-05 · Kibeom Kim, Kisung Shin, Min Whoo Lee, Moonhoen Lee 외

Interactive visual navigation tasks, which involve following instructions to reach and interact with specific targets, are challenging not only because successful experiences are very rare but also because the complex vi…

Imitation LearningVisual Navigation

GUMBEL-NERF: Representing Unseen Objects as Part-Compositional Neural Radiance Fields

2024-10-27 · Yusuke Sekikawa, Chingwei Hsu, Satoshi Ikehata, Rei Kawakami 외

We propose Gumbel-NeRF, a mixture-of-expert (MoE) neural radiance fields (NeRF) model with a hindsight expert selection mechanism for synthesizing novel views of unseen objects. Previous studies have shown that the MoE s…

NeRFNovel View Synthesis

Complex Robotic Manipulation via Graph-Based Hindsight Goal Generation

2020-07-27 · Zhenshan Bing, Matthias Brucker, Fabrice O. Morin, Kai Huang 외

Reinforcement learning algorithms such as hindsight experience replay (HER) and hindsight goal generation (HGG) have been able to solve challenging robotic manipulation tasks in multi-goal settings with sparse rewards. H…

Dynamical-VAE-based Hindsight to Learn the Causal Dynamics of Factored-POMDPs

2024-11-12 · Chao Han, Debabrota Basu, Michael Mangan, Eleni Vasilaki 외

Learning representations of underlying environmental dynamics from partial observations is a critical challenge in machine learning. In the context of Partially Observable Markov Decision Processes (POMDPs), state repres…