{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/157006"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/157006","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Efficient Segment Anything on the Edge","abstract":"The Segment-Anything Model (SAM) is a vision foundation model facilitating promptable and zero-shot image segmentation. SAM-based models have a wide range of applications including autonomous driving, medical image segmentation, VR, and data annotation. However, SAM models are highly computationally intensive and lack a flexible prompting mechanism. On an NVIDIA A100 GPU, SAM runs at 11 frames/second, missing the mark for real-time performance and preventing the usage of SAM on edge devices. To tackle both the latency constraint and the prompt flexibility constraint, we introduce GazeSAM, a new real-time gaze-prompted image segmentation model. GazeSAM uses face and gaze detection to determine the direction of a user's gaze, object detection to find candidate objects of interest, depth estimation to perform background detection, and image segmentation to generate masks. The final output is a mask segmenting the object at the focus of the user's gaze. By performing algorithmic optimizations, employing inference engines, and applying FP16 and INT8 quantization, we achieve a 24x speedup relative to the baseline FP32 PyTorch implementation. GazeSAM runs at a speed of over 30 FPS, enabling real-time performance on an RTX 4070 GPU.","abstract_html":"The Segment-Anything Model (SAM) is a vision foundation model facilitating promptable and zero-shot image segmentation. SAM-based models have a wide range of applications including autonomous driving, medical image segmentation, VR, and data annotation. However, SAM models are highly computationally intensive and lack a flexible prompting mechanism. On an NVIDIA A100 GPU, SAM runs at 11 frames/second, missing the mark for real-time performance and preventing the usage of SAM on edge devices. To tackle both the latency constraint and the prompt flexibility constraint, we introduce GazeSAM, a new real-time gaze-prompted image segmentation model. GazeSAM uses face and gaze detection to determine the direction of a user's gaze, object detection to find candidate objects of interest, depth estimation to perform background detection, and image segmentation to generate masks. The final output is a mask segmenting the object at the focus of the user's gaze. By performing algorithmic optimizations, employing inference engines, and applying FP16 and INT8 quantization, we achieve a 24x speedup relative to the baseline FP32 PyTorch implementation. GazeSAM runs at a speed of over 30 FPS, enabling real-time performance on an RTX 4070 GPU.","abstract_has_math":false,"creators":["Stiles, Nicole"],"institution":"Massachusetts Institute of Technology","degree_name":"Master","degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","school":null,"contributors":[],"advisors":["Han, Song"],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024-05","date_published":"2024-05","updated_at":"2026-07-22T22:22:25Z","subjects":[],"languages":[],"rights":["Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)","Copyright retained by author(s)"],"rights_urls":["https://creativecommons.org/licenses/by-nc-nd/4.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/157006","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Han, Song"]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["Stiles, Nicole"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2024-09-24T18:26:22Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2024-09-24T18:26:22Z"]},{"key":"dc:date.issued","label":"Date","values":["2024-05"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master","Master of Engineering in Electrical Engineering and Computer Science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)","Copyright retained by author(s)"]},{"key":"dc:rights.uri","label":"Rights URI","values":["https://creativecommons.org/licenses/by-nc-nd/4.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/157006"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["The Segment-Anything Model (SAM) is a vision foundation model facilitating promptable and zero-shot image segmentation. SAM-based models have a wide range of applications including autonomous driving, medical image segmentation, VR, and data annotation. However, SAM models are highly computationally intensive and lack a flexible prompting mechanism. On an NVIDIA A100 GPU, SAM runs at 11 frames/second, missing the mark for real-time performance and preventing the usage of SAM on edge devices. To tackle both the latency constraint and the prompt flexibility constraint, we introduce GazeSAM, a new real-time gaze-prompted image segmentation model. GazeSAM uses face and gaze detection to determine the direction of a user's gaze, object detection to find candidate objects of interest, depth estimation to perform background detection, and image segmentation to generate masks. The final output is a mask segmenting the object at the focus of the user's gaze. By performing algorithmic optimizations, employing inference engines, and applying FP16 and INT8 quantization, we achieve a 24x speedup relative to the baseline FP32 PyTorch implementation. GazeSAM runs at a speed of over 30 FPS, enabling real-time performance on an RTX 4070 GPU."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["M.Eng."]},{"key":"dc:title","label":"Title","values":["Efficient Segment Anything on the Edge"]}]}],"canonical_facts":{"dc:contributor.advisor":["Han, Song"],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"],"dc:creator":["Stiles, Nicole"],"dc:date.accessioned":["2024-09-24T18:26:22Z"],"dc:date.available":["2024-09-24T18:26:22Z"],"dc:date.issued":["2024-05"],"dc:description.abstract":["The Segment-Anything Model (SAM) is a vision foundation model facilitating promptable and zero-shot image segmentation. SAM-based models have a wide range of applications including autonomous driving, medical image segmentation, VR, and data annotation. However, SAM models are highly computationally intensive and lack a flexible prompting mechanism. On an NVIDIA A100 GPU, SAM runs at 11 frames/second, missing the mark for real-time performance and preventing the usage of SAM on edge devices. To tackle both the latency constraint and the prompt flexibility constraint, we introduce GazeSAM, a new real-time gaze-prompted image segmentation model. GazeSAM uses face and gaze detection to determine the direction of a user's gaze, object detection to find candidate objects of interest, depth estimation to perform background detection, and image segmentation to generate masks. The final output is a mask segmenting the object at the focus of the user's gaze. By performing algorithmic optimizations, employing inference engines, and applying FP16 and INT8 quantization, we achieve a 24x speedup relative to the baseline FP32 PyTorch implementation. GazeSAM runs at a speed of over 30 FPS, enabling real-time performance on an RTX 4070 GPU."],"dc:description.degree":["M.Eng."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/157006"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)","Copyright retained by author(s)"],"dc:rights.uri":["https://creativecommons.org/licenses/by-nc-nd/4.0/"],"dc:title":["Efficient Segment Anything on the Edge"],"dc:type":["Thesis"],"thesis:degree_name":["Master","Master of Engineering in Electrical Engineering and Computer Science"]},"updated_at":"2026-07-22T22:22:25Z"}