SOURCE-LINKED INTELLIGENCE

What Does the Encoder Actually Decide? A Controlled Comparison of Vision Backbones on Joint Tree Segmentation and Stereo Depth

arXiv · AI, language, vision and robotics · article · Sep 2, 2026 · UTC

A robot pruning trees needs two facts per pixel: whether it belongs to a tree, and its distance. Both are usually obtained via task heads attached to a vision backbone chosen by reputation rather than measurement. Holding dataset, decoders, losses, schedule, and evaluation fixed, we ask: how much does the encoder choice change joint semantic segmentation and stereo depth on thin vegetation? We build a hard parameter-sharing network with one encoder feeding both branches, swapping only the encoder without downstream retuning. We evaluate [N] encoders across [M] architecture families (CNNs, tran

Read original source ↗ Open in workspace

recordType

paper

region

Global