Stem-OB: Generalizable Visual Imitation Learning with Stem-Like Convergent Observation through Diffusion Inversion

• URL: http://arxiv.org/abs/2411.04919v1
• Date: Thu, 07 Nov 2024 17:56:16 GMT
• Title: Stem-OB: Generalizable Visual Imitation Learning with Stem-Like Convergent Observation through Diffusion Inversion
• Authors: Kaizhe Hu, Zihang Rui, Yao He, Yuyao Liu, Pu Hua, Huazhe Xu,
• Abstract summary: We propose Stem-OB that utilizes pretrained image diffusion models to suppress low-level visual differences. This image inversion process is akin to transforming the observation into a shared representation. Our method is a simple yet highly effective plug-and-play solution.
• Score: 18.990678061962825
• License:
• Abstract: Visual imitation learning methods demonstrate strong performance, yet they lack generalization when faced with visual input perturbations, including variations in lighting and textures, impeding their real-world application. We propose Stem-OB that utilizes pretrained image diffusion models to suppress low-level visual differences while maintaining high-level scene structures. This image inversion process is akin to transforming the observation into a shared representation, from which other observations stem, with extraneous details removed. Stem-OB contrasts with data-augmentation approaches as it is robust to various unspecified appearance changes without the need for additional training. Our method is a simple yet highly effective plug-and-play solution. Empirical results confirm the effectiveness of our approach in simulated tasks and show an exceptionally significant improvement in real-world applications, with an average increase of 22.2% in success rates compared to the best baseline. See https://hukz18.github.io/Stem-Ob/ for more info.

Related papers

• Don't Judge by the Look: Towards Motion Coherent Video Representation [56.09346222721583]
  Motion Coherent Augmentation (MCA) is a data augmentation method for video understanding. MCA introduces appearance variation in videos and implicitly encourages the model to prioritize motion patterns, rather than static appearances.
  arXiv  Detail & Related papers  (2024-03-14T15:53:04Z)
• Visual Imitation Learning with Calibrated Contrastive Representation [44.63125396964309]
  Adversarial Imitation Learning (AIL) allows the agent to reproduce expert behavior with low-dimensional states and actions. This paper proposes a simple and effective solution by incorporating contrastive representative learning into visual AIL framework.
  arXiv  Detail & Related papers  (2024-01-21T04:18:30Z)
• Harnessing Diffusion Models for Visual Perception with Meta Prompts [68.78938846041767]
  We propose a simple yet effective scheme to harness a diffusion model for visual perception tasks. We introduce learnable embeddings (meta prompts) to the pre-trained diffusion models to extract proper features for perception. Our approach achieves new performance records in depth estimation tasks on NYU depth V2 and KITTI, and in semantic segmentation task on CityScapes.
  arXiv  Detail & Related papers  (2023-12-22T14:40:55Z)
• Exploring Data Augmentations on Self-/Semi-/Fully- Supervised Pre-trained Models [24.376036129920948]
  We investigate how data augmentation affects performance of vision pre-trained models. We apply 4 types of data augmentations termed with Random Erasing, CutOut, CutMix and MixUp. We report their performance on vision tasks such as image classification, object detection, instance segmentation, and semantic segmentation.
  arXiv  Detail & Related papers  (2023-10-28T23:46:31Z)
• ExposureDiffusion: Learning to Expose for Low-light Image Enhancement [87.08496758469835]
  This work addresses the issue by seamlessly integrating a diffusion model with a physics-based exposure model. Our method obtains significantly improved performance and reduced inference time compared with vanilla diffusion models. The proposed framework can work with both real-paired datasets, SOTA noise models, and different backbone networks.
  arXiv  Detail & Related papers  (2023-07-15T04:48:35Z)
• Mix-up Self-Supervised Learning for Contrast-agnostic Applications [33.807005669824136]
  We present the first mix-up self-supervised learning framework for contrast-agnostic applications. We address the low variance across images based on cross-domain mix-up and build the pretext task based on image reconstruction and transparency prediction.
  arXiv  Detail & Related papers  (2022-04-02T16:58:36Z)
• Improving Transferability of Representations via Augmentation-Aware Self-Supervision [117.15012005163322]
  AugSelf is an auxiliary self-supervised loss that learns the difference of augmentation parameters between two randomly augmented samples. Our intuition is that AugSelf encourages to preserve augmentation-aware information in learned representations, which could be beneficial for their transferability. AugSelf can easily be incorporated into recent state-of-the-art representation learning methods with a negligible additional training cost.
  arXiv  Detail & Related papers  (2021-11-18T10:43:50Z)
• Dense Contrastive Visual-Linguistic Pretraining [53.61233531733243]
  Several multimodal representation learning approaches have been proposed that jointly represent image and text. These approaches achieve superior performance by capturing high-level semantic information from large-scale multimodal pretraining. We propose unbiased Dense Contrastive Visual-Linguistic Pretraining to replace the region regression and classification with cross-modality region contrastive learning.
  arXiv  Detail & Related papers  (2021-09-24T07:20:13Z)
• Demystifying Contrastive Self-Supervised Learning: Invariances, Augmentations and Dataset Biases [34.02639091680309]
  Recent gains in performance come from training instance classification models, treating each image and it's augmented versions as samples of a single class. We demonstrate that approaches like MOCO and PIRL learn occlusion-invariant representations. Second, we demonstrate that these approaches obtain further gains from access to a clean object-centric training dataset like Imagenet.
  arXiv  Detail & Related papers  (2020-07-28T00:11:31Z)
• Un-Mix: Rethinking Image Mixtures for Unsupervised Visual Representation Learning [108.999497144296]
  Recently advanced unsupervised learning approaches use the siamese-like framework to compare two "views" from the same image for learning representations. This work aims to involve the distance concept on label space in the unsupervised learning and let the model be aware of the soft degree of similarity between positive or negative pairs. Despite its conceptual simplicity, we show empirically that with the solution -- Unsupervised image mixtures (Un-Mix), we can learn subtler, more robust and generalized representations from the transformed input and corresponding new label space.
  arXiv  Detail & Related papers  (2020-03-11T17:59:04Z)

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.