EdgeTAM: On-Device Track Anything Model

• URL: http://arxiv.org/abs/2501.07256v1
• Date: Mon, 13 Jan 2025 12:11:07 GMT
• Title: EdgeTAM: On-Device Track Anything Model
• Authors: Chong Zhou, Chenchen Zhu, Yunyang Xiong, Saksham Suri, Fanyi Xiao, Lemeng Wu, Raghuraman Krishnamoorthi, Bo Dai, Chen Change Loy, Vikas Chandra, Bilge Soran,
• Abstract summary: Segment Anything Model (SAM) 2 further extends its capability from image to video inputs through a memory bank mechanism. We aim at making SAM 2 much more efficient so that it even runs on mobile devices while maintaining a comparable performance. We propose EdgeTAM, which leverages a novel 2D Spatial Perceiver to reduce the computational cost.
• Score: 65.10032957471824
• License:
• Abstract: On top of Segment Anything Model (SAM), SAM 2 further extends its capability from image to video inputs through a memory bank mechanism and obtains a remarkable performance compared with previous methods, making it a foundation model for video segmentation task. In this paper, we aim at making SAM 2 much more efficient so that it even runs on mobile devices while maintaining a comparable performance. Despite several works optimizing SAM for better efficiency, we find they are not sufficient for SAM 2 because they all focus on compressing the image encoder, while our benchmark shows that the newly introduced memory attention blocks are also the latency bottleneck. Given this observation, we propose EdgeTAM, which leverages a novel 2D Spatial Perceiver to reduce the computational cost. In particular, the proposed 2D Spatial Perceiver encodes the densely stored frame-level memories with a lightweight Transformer that contains a fixed set of learnable queries. Given that video segmentation is a dense prediction task, we find preserving the spatial structure of the memories is essential so that the queries are split into global-level and patch-level groups. We also propose a distillation pipeline that further improves the performance without inference overhead. As a result, EdgeTAM achieves 87.7, 70.0, 72.3, and 71.7 J&F on DAVIS 2017, MOSE, SA-V val, and SA-V test, while running at 16 FPS on iPhone 15 Pro Max.

Related papers

• Efficient Track Anything [32.0480507678127]
  Segment Anything Model 2 (SAM 2) has emerged as a powerful tool for video object segmentation and tracking anything. High complexity of multistage image encoder and memory module has limited its applications in real-world tasks. We propose EfficientTAMs, lightweight track anything models that produce high-quality results with low latency and model size.
  arXiv  Detail & Related papers  (2024-11-28T05:52:10Z)
• A Distractor-Aware Memory for Visual Object Tracking with SAM2 [11.864619292028278]
  Memory-based trackers are video object segmentation methods that form the target model by concatenating recently tracked frames into a memory buffer and localize the target by attending the current image to the buffered frames. SAM2.1++ outperforms SAM2.1 and related SAM memory extensions on seven benchmarks and sets a solid new state-of-the-art on six of them.
  arXiv  Detail & Related papers  (2024-11-26T16:41:09Z)
• SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree [79.26409013413003]
  We introduce SAM2Long, an improved training-free video object segmentation strategy. It considers the segmentation uncertainty within each frame and chooses the video-level optimal results from multiple segmentation pathways. SAM2Long achieves an average improvement of 3.0 points across all 24 head-to-head comparisons.
  arXiv  Detail & Related papers  (2024-10-21T17:59:19Z)
• SAM2-UNet: Segment Anything 2 Makes Strong Encoder for Natural and Medical Image Segmentation [51.90445260276897]
  We prove that the Segment Anything Model 2 (SAM2) can be a strong encoder for U-shaped segmentation models. We propose a simple but effective framework, termed SAM2-UNet, for versatile image segmentation.
  arXiv  Detail & Related papers  (2024-08-16T17:55:38Z)
• From SAM to SAM 2: Exploring Improvements in Meta's Segment Anything Model [0.5639904484784127]
  The Segment Anything Model (SAM) was introduced to the computer vision community by Meta in April 2023. SAM excels in zero-shot performance, segmenting unseen objects without additional training, stimulated by a large dataset of over one billion image masks. SAM 2 expands this functionality to video, leveraging memory from preceding and subsequent frames to generate accurate segmentation across entire videos.
  arXiv  Detail & Related papers  (2024-08-12T17:17:35Z)
• TinySAM: Pushing the Envelope for Efficient Segment Anything Model [73.06322749886483]
  We propose a framework to obtain a tiny segment anything model (TinySAM) while maintaining the strong zero-shot performance. With all these proposed methods, our TinySAM leads to orders of magnitude computational reduction and pushes the envelope for efficient segment anything task.
  arXiv  Detail & Related papers  (2023-12-21T12:26:11Z)
• EdgeSAM: Prompt-In-the-Loop Distillation for On-Device Deployment of SAM [71.868623296582]
  EdgeSAM is an accelerated variant of the Segment Anything Model (SAM) Our approach involves distilling the original ViT-based SAM image encoder into a purely CNN-based architecture. It is the first SAM variant that can run at over 30 FPS on an iPhone 14.
  arXiv  Detail & Related papers  (2023-12-11T18:59:52Z)
• Region Aware Video Object Segmentation with Deep Motion Modeling [56.95836951559529]
  Region Aware Video Object (RAVOS) is a method that predicts regions of interest for efficient object segmentation and memory storage. For efficient segmentation, object features are extracted according to the ROIs, and an object decoder is designed for object-level segmentation. For efficient memory storage, we propose motion path memory to filter out redundant context by memorizing the features within the motion path of objects between two frames.
  arXiv  Detail & Related papers  (2022-07-21T01:44:40Z)

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.