{"paper":{"title":"EmbodiTTA: Resource-Efficient Test-Time Adaptation for Embodied Visual Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"OD-TTA adapts models on edge devices only when domain shifts are detected, cutting energy use while matching full adaptation accuracy.","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Dong Ma, Xiao Ma, Young D. Kwon","submitted_at":"2025-05-02T04:19:07Z","abstract_excerpt":"Continual Test-time adaptation (CTTA) continuously adapts the deployed model on every incoming batch of data. While achieving optimal accuracy, existing CTTA approaches present poor real-world applicability on resource-constrained edge devices, due to the substantial memory overhead and energy consumption. In this work, we first introduce a novel paradigm -- on-demand TTA -- which triggers adaptation only when a significant domain shift is detected. Then, we present OD-TTA, an on-demand TTA framework for accurate and efficient adaptation on edge devices. OD-TTA comprises three innovative techn"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"OD-TTA achieves comparable and even better performance while reducing the energy and computation overhead remarkably, making TTA a practical reality.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The lightweight domain shift detection mechanism reliably identifies when adaptation is truly needed without missing important shifts or triggering too often on noise.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"OD-TTA enables resource-efficient test-time adaptation on edge devices by triggering updates only on detected domain shifts, achieving comparable accuracy with lower energy and computation costs for embodied visual systems.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"OD-TTA adapts models on edge devices only when domain shifts are detected, cutting energy use while matching full adaptation accuracy.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d02da766e34a8ec7e37e78594a32f85bfc49e06d9a81c2da1931c9886f3a3ef1"},"source":{"id":"2505.00986","kind":"arxiv","version":3},"verdict":{"id":"6a2ea992-80ea-4483-a931-86bbca8c6896","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-22T16:30:41.202009Z","strongest_claim":"OD-TTA achieves comparable and even better performance while reducing the energy and computation overhead remarkably, making TTA a practical reality.","one_line_summary":"OD-TTA enables resource-efficient test-time adaptation on edge devices by triggering updates only on detected domain shifts, achieving comparable accuracy with lower energy and computation costs for embodied visual systems.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The lightweight domain shift detection mechanism reliably identifies when adaptation is truly needed without missing important shifts or triggering too often on noise.","pith_extraction_headline":"OD-TTA adapts models on edge devices only when domain shifts are detected, cutting energy use while matching full adaptation accuracy."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.00986/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"ed80b0da352c312e21273503dba6449d8f7403beae54a17e8ebd3f616e3b6138"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}