We're Not Using Videos Effectively: An Updated Domain Adaptive Video Segmentation Baseline

• URL: http://arxiv.org/abs/2402.00868v3
• Date: Tue, 27 Feb 2024 22:25:15 GMT
• Title: We're Not Using Videos Effectively: An Updated Domain Adaptive Video Segmentation Baseline
• Authors: Simar Kareer, Vivek Vijaykumar, Harsh Maheshwari, Prithvijit Chattopadhyay, Judy Hoffman, Viraj Prabhu
• Abstract summary: Video-DAS works have historically studied a distinct set of benchmarks from Image-DAS, with minimal cross-benchmarking. We find that even after carefully controlling for data and model architecture, state-of-the-art Image-DAS methods outperform Video-DAS methods on established Video-DAS benchmarks.
• Score: 19.098970392639476
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: There has been abundant work in unsupervised domain adaptation for semantic segmentation (DAS) seeking to adapt a model trained on images from a labeled source domain to an unlabeled target domain. While the vast majority of prior work has studied this as a frame-level Image-DAS problem, a few Video-DAS works have sought to additionally leverage the temporal signal present in adjacent frames. However, Video-DAS works have historically studied a distinct set of benchmarks from Image-DAS, with minimal cross-benchmarking. In this work, we address this gap. Surprisingly, we find that (1) even after carefully controlling for data and model architecture, state-of-the-art Image-DAS methods (HRDA and HRDA+MIC) outperform Video-DAS methods on established Video-DAS benchmarks (+14.5 mIoU on Viper$\rightarrow$CityscapesSeq, +19.0 mIoU on Synthia$\rightarrow$CityscapesSeq), and (2) naive combinations of Image-DAS and Video-DAS techniques only lead to marginal improvements across datasets. To avoid siloed progress between Image-DAS and Video-DAS, we open-source our codebase with support for a comprehensive set of Video-DAS and Image-DAS methods on a common benchmark. Code available at https://github.com/SimarKareer/UnifiedVideoDA

Related papers

• GIM: Learning Generalizable Image Matcher From Internet Videos [18.974842517202365]
  We propose GIM, a self-training framework for learning a single generalizable model based on any image matching architecture. We also propose ZEB, the first zero-shot evaluation benchmark for image matching.
  arXiv  Detail & Related papers  (2024-02-16T21:48:17Z)
• FusionFrames: Efficient Architectural Aspects for Text-to-Video Generation Pipeline [4.295130967329365]
  This paper presents a new two-stage latent diffusion text-to-video generation architecture based on the text-to-image diffusion model. The design of our model significantly reduces computational costs compared to other masked frame approaches. We evaluate different configurations of MoVQ-based video decoding scheme to improve consistency and achieve higher PSNR, SSIM, MSE, and LPIPS scores.
  arXiv  Detail & Related papers  (2023-11-22T00:26:15Z)
• Memory Efficient Temporal & Visual Graph Model for Unsupervised Video Domain Adaptation [50.158454960223274]
  Existing video domain adaption (DA) methods need to store all temporal combinations of video frames or pair the source and target videos. We propose a memory-efficient graph-based video DA approach.
  arXiv  Detail & Related papers  (2022-08-13T02:56:10Z)
• Unsupervised Domain Adaptation for Video Transformers in Action Recognition [76.31442702219461]
  We propose a simple and novel UDA approach for video action recognition. Our approach builds a robust source model that better generalises to target domain. We report results on two video action benchmarks recognition for UDA.
  arXiv  Detail & Related papers  (2022-07-26T12:17:39Z)
• VRAG: Region Attention Graphs for Content-Based Video Retrieval [85.54923500208041]
  Region Attention Graph Networks (VRAG) improves the state-of-the-art video-level methods. VRAG represents videos at a finer granularity via region-level features and encodes video-temporal dynamics through region-level relations. We show that the performance gap between video-level and frame-level methods can be reduced by segmenting videos into shots and using shot embeddings for video retrieval.
  arXiv  Detail & Related papers  (2022-05-18T16:50:45Z)
• Guess What Moves: Unsupervised Video and Image Segmentation by Anticipating Motion [92.80981308407098]
  We propose an approach that combines the strengths of motion-based and appearance-based segmentation. We propose to supervise an image segmentation network, tasking it with predicting regions that are likely to contain simple motion patterns. In the unsupervised video segmentation mode, the network is trained on a collection of unlabelled videos, using the learning process itself as an algorithm to segment these videos.
  arXiv  Detail & Related papers  (2022-05-16T17:55:34Z)
• CycDA: Unsupervised Cycle Domain Adaptation from Image to Video [26.30914383638721]
  Domain Cycle Adaptation (CycDA) is a cycle-based approach for unsupervised image-to-video domain adaptation. We evaluate our approach on benchmark datasets for image-to-video and for mixed-source domain adaptation.
  arXiv  Detail & Related papers  (2022-03-30T12:22:26Z)
• Box Supervised Video Segmentation Proposal Network [3.384080569028146]
  We propose a box-supervised video object segmentation proposal network, which takes advantage of intrinsic video properties. The proposed method outperforms the state-of-the-art self-supervised benchmark by 16.4% and 6.9%. We provide extensive tests and ablations on the datasets, demonstrating the robustness of our method.
  arXiv  Detail & Related papers  (2022-02-14T20:38:28Z)
• Object Propagation via Inter-Frame Attentions for Temporally Stable Video Instance Segmentation [51.68840525174265]
  Video instance segmentation aims to detect, segment, and track objects in a video. Current approaches extend image-level segmentation algorithms to the temporal domain. We propose a video instance segmentation method that alleviates the problem due to missing detections.
  arXiv  Detail & Related papers  (2021-11-15T04:15:57Z)
• Unsupervised Domain Adaptation for Video Semantic Segmentation [91.30558794056054]
  Unsupervised Domain Adaptation for semantic segmentation has gained immense popularity since it can transfer knowledge from simulation to real. In this work, we present a new video extension of this task, namely Unsupervised Domain Adaptation for Video Semantic approaches. We show that our proposals significantly outperform previous image-based UDA methods both on image-level (mIoU) and video-level (VPQ) evaluation metrics.
  arXiv  Detail & Related papers  (2021-07-23T07:18:20Z)
• Unified Image and Video Saliency Modeling [21.701431656717112]
  We ask: Can image and video saliency modeling be approached via a unified model? We propose four novel domain adaptation techniques and an improved formulation of learned Gaussian priors. We integrate these techniques into a simple and lightweight encoder-RNN-decoder-style network, UNISAL, and train it jointly with image and video saliency data. We evaluate our method on the video saliency datasets DHF1K, Hollywood-2 and UCF-Sports, and the image saliency datasets SALICON and MIT300.
  arXiv  Detail & Related papers  (2020-03-11T18:28:29Z)

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.