SegDAC: Improving Visual Reinforcement Learning by Extracting Dynamic Objectc-Centric Representations from Pretrained Vision Models

• URL: http://arxiv.org/abs/2508.09325v2
• Date: Fri, 17 Oct 2025 22:15:14 GMT
• Title: SegDAC: Improving Visual Reinforcement Learning by Extracting Dynamic Objectc-Centric Representations from Pretrained Vision Models
• Authors: Alexandre Brown, Glen Berseth,
• Abstract summary: SegDAC is an Actor-Driven Actor-Critic method for visual reinforcement learning.<n>It learns which segments to focus on using online RL, without using human labels.<n>It achieves significantly better visual generalization, doubling prior performance on the hardest setting and matching or surpassing prior methods in sample efficiency.
• Score: 61.135869433338264
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Visual reinforcement learning (RL) is challenging due to the need to extract useful representations from high-dimensional inputs while learning effective control from sparse and noisy rewards. Although large perception models exist, integrating them effectively into RL for visual generalization and improved sample efficiency remains difficult. We propose SegDAC, a Segmentation-Driven Actor-Critic method. SegDAC uses Segment Anything (SAM) for object-centric decomposition and YOLO-World to ground the image segmentation process via text inputs. It includes a novel transformer-based architecture that supports a dynamic number of segments at each time step and effectively learns which segments to focus on using online RL, without using human labels. By evaluating SegDAC over a challenging visual generalization benchmark using Maniskill3, which covers diverse manipulation tasks under strong visual perturbations, we demonstrate that SegDAC achieves significantly better visual generalization, doubling prior performance on the hardest setting and matching or surpassing prior methods in sample efficiency across all evaluated tasks.

Related papers

• CRIA: A Cross-View Interaction and Instance-Adapted Pre-training Framework for Generalizable EEG Representations [52.251569042852815]
  CRIA is an adaptive framework that utilizes variable-length and variable-channel coding to achieve a unified representation of EEG data across different datasets.<n>The model employs a cross-attention mechanism to fuse temporal, spectral, and spatial features effectively.<n> Experimental results on the Temple University EEG corpus and the CHB-MIT dataset show that CRIA outperforms existing methods with the same pre-training conditions.
  arXiv  Detail & Related papers  (2025-06-19T06:31:08Z)
• Frequency-based Matcher for Long-tailed Semantic Segmentation [22.199174076366003]
  We focus on a relatively under-explored task setting, long-tailed semantic segmentation (LTSS) We propose a dual-metric evaluation system and construct the LTSS benchmark to demonstrate the performance of semantic segmentation methods and long-tailed solutions. We also propose a transformer-based algorithm to improve LTSS, frequency-based matcher, which solves the oversuppression problem by one-to-many matching.
  arXiv  Detail & Related papers  (2024-06-06T09:57:56Z)
• Semantic Equitable Clustering: A Simple and Effective Strategy for Clustering Vision Tokens [57.37893387775829]
  We introduce a fast and balanced clustering method, named Semantic Equitable Clustering (SEC)<n>SEC clusters tokens based on their global semantic relevance in an efficient, straightforward manner.<n>We propose a versatile vision backbone, SECViT, to serve as a vision language connector.
  arXiv  Detail & Related papers  (2024-05-22T04:49:00Z)
• Language-Driven Visual Consensus for Zero-Shot Semantic Segmentation [114.72734384299476]
  We propose a Language-Driven Visual Consensus (LDVC) approach, fostering improved alignment of semantic and visual information. We leverage class embeddings as anchors due to their discrete and abstract nature, steering vision features toward class embeddings. Our approach significantly boosts the capacity of segmentation models for unseen classes.
  arXiv  Detail & Related papers  (2024-03-13T11:23:55Z)
• MST: Adaptive Multi-Scale Tokens Guided Interactive Segmentation [8.46894039954642]
  We propose a novel multi-scale token adaptation algorithm for interactive segmentation. By performing top-k operations across multi-scale tokens, the computational complexity is greatly simplified. We also propose a token learning algorithm based on contrastive loss.
  arXiv  Detail & Related papers  (2024-01-09T07:59:42Z)
• Gramian Attention Heads are Strong yet Efficient Vision Learners [26.79263390835444]
  We introduce a novel architecture design that enhances expressiveness by incorporating multiple head classifiers (ie, classification heads) Our approach employs attention-based aggregation, utilizing pairwise feature similarity to enhance multiple lightweight heads with minimal resource overhead. Our models eventually surpass state-of-the-art CNNs and ViTs regarding the accuracy-grained trade-off on ImageNet-1K.
  arXiv  Detail & Related papers  (2023-10-25T09:08:58Z)
• SegMatch: A semi-supervised learning method for surgical instrument segmentation [11.72367272074871]
  We propose SegMatch, a semi-supervised learning method to reduce the need for expensive annotation for laparoscopic and robotic surgical images.<n>SegMatch builds on FixMatch, a widespread semi-supervised classification pipeline combining consistency regularization and pseudo-labelling.<n>Our results show that SegMatch outperforms fully-supervised approaches by incorporating unlabelled data.
  arXiv  Detail & Related papers  (2023-08-09T21:30:18Z)
• ALP: Action-Aware Embodied Learning for Perception [60.64801970249279]
  We introduce Action-Aware Embodied Learning for Perception (ALP) ALP incorporates action information into representation learning through a combination of optimizing a reinforcement learning policy and an inverse dynamics prediction objective. We show that ALP outperforms existing baselines in several downstream perception tasks.
  arXiv  Detail & Related papers  (2023-06-16T21:51:04Z)
• Robust Representation Learning by Clustering with Bisimulation Metrics for Visual Reinforcement Learning with Distractions [9.088460902782547]
  Clustering with Bisimulation Metrics (CBM) learns robust representations by grouping visual observations in the latent space. CBM alternates between two steps: (1) grouping observations by measuring their bisimulation distances to the learned prototypes; (2) learning a set of prototypes according to the current cluster assignments. Experiments demonstrate that CBM significantly improves the sample efficiency of popular visual RL algorithms.
  arXiv  Detail & Related papers  (2023-02-12T13:27:34Z)
• Multi-Task Self-Supervised Learning for Image Segmentation Task [0.0]
  The paper presents 1. Self-supervised techniques to boost semantic segmentation performance using multi-task learning with Depth prediction and Surface Normalization. 2. Performance evaluation of the different types of weighing techniques (UW, Nash-MTL) used for Multi-task learning.
  arXiv  Detail & Related papers  (2023-02-05T21:25:59Z)
• Multi-level Contrast Network for Wearables-based Joint Activity Segmentation and Recognition [10.828099015828693]
  Human activity recognition (HAR) with wearables is promising research that can be widely adopted in many smart healthcare applications. Most HAR algorithms are susceptible to the multi-class windows problem that is essential yet rarely exploited. We introduce the segmentation technology into HAR, yielding joint activity segmentation and recognition.
  arXiv  Detail & Related papers  (2022-08-16T05:39:02Z)
• Adversarial Feature Augmentation and Normalization for Visual Recognition [109.6834687220478]
  Recent advances in computer vision take advantage of adversarial data augmentation to ameliorate the generalization ability of classification models. Here, we present an effective and efficient alternative that advocates adversarial augmentation on intermediate feature embeddings. We validate the proposed approach across diverse visual recognition tasks with representative backbone networks.
  arXiv  Detail & Related papers  (2021-03-22T20:36:34Z)
• Visual Object Tracking by Segmentation with Graph Convolutional Network [7.729569666460712]
  We propose to utilize graph convolutional network (GCN) model for superpixel based object tracking. The proposed model provides a general end-to-end framework which integrates i) label linear prediction, and ii) structure-aware feature information of each superpixel together.
  arXiv  Detail & Related papers  (2020-09-05T12:43:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.