{
  "annotation_id": "a927a18f-3a52-4326-98e1-1e50f7f06354",
  "date_created": "2026-02-17T05:53:20.475000Z",
  "date_modified": "2026-02-17T05:53:20.475000Z",
  "file_hash": "3956eaa976980f4f7cd12907d091f4bc06db70eb4eff4666d9686eac75446ec4",
  "private": false,
  "record": {
    "abstract": "End-to-end backpropagation couples all layers through a global error signal, enabling coordinated learning but requiring long-range credit assignment. Motivated by recent progress in blockwise self-supervised learning (BWSSL), we ask whether masked video transformers can be trained without end-to-end backpropagation. Applying BWSSL to masked video modeling remains relatively underexplored and must handle spatiotemporal context and long-range temporal structure. More broadly, analyses that compare BWSSL and end-to-end training in terms of learning dynamics and depth-wise representation development remain sparse. We apply blockwise learning to a masked autoencoding video vision transformer by partitioning the encoder into blocks, each of which is optimized with a local masked reconstruction loss. Across model sizes and partition granularities, training converges and yields representations close to matched end-to-end baselines under linear-probe and retrieval proxies. In order to compare intermediate representations, we analyze depth-wise decodability, inter-block similarity, and patch-level diagnostics. Blockwise training exposes higher-level structure earlier, while later blocks saturate and operate in a more geometry-preserving regime. It can also induce token-level shifts consistent with stronger early mixing that pooled metrics can miss. These findings point to late-block saturation and interface formation as contributors to the remaining gap.",
    "arxiv_id": "2601.09040",
    "authors": [
      "Jonas R\u00f6mer",
      "Timo Dickscheid"
    ],
    "categories": [
      "cs.CV"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "title": "Depth-Wise Representation Development Under Blockwise Self-Supervised Learning for Video Vision Transformers",
    "url": "https://arxiv.org/abs/2601.09040",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "2076301c-91da-4ec2-989e-2e0be9436821",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}