SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1705.07115 · 2017

Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics

arXiv · PDF · Open in the Atlas

Code that ran

2 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/1705.07115.json · badge: /api/ran/1705.07115.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
Lukeasargen/targetClassifier reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 2 no recorded run
ranandalon/mtl reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
pred_list2dict Ran
ran; our contract draft was wrong, not the code
ranandalon/mtl/src/inference.py
code served (permissive licence) · get_code("fe01d93285cd6b2f")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Based on the function, pred_list is a list that gets .pop() called on it
# The number of pops depends on the INF_FLAGS
# INF_FLAGS = {'use_label_type': True, 'use_label_inst': False, 'use_label_disp': False}
# So only 'use_label_type' is True, meaning .pop() is called once

# Each popped item has .squeeze() called on it, so they should be tensors
# We need to construct a list with 1 tensor (since only one flag is True)

# The list is popped in reverse order of the if statements:
# 1. disp (if use_label_disp) - not used
# 2. instance (if use_label_inst) - not used  
# 3. label (if use_label_type) - YES, this will be popped

# Since pop() removes from the end, the list should have the label tensor at the end

pred_list = [
    torch.randn(2, 4, 3)  # label tensor with some shape
]

ARGS = {'pred_list': pred_list}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
rotate_2d Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Lukeasargen/targetClassifier/generate_targets.py
pointer only (licence: NONE) · get_code("dab11d8b10137d95")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Lukeasargen/targetClassifier when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

BuildMultiTaskResnet Not yet run
unverified (harvested, no recorded run)
Lukeasargen/targetClassifier/models/multitask.py
pointer only (licence: NONE) · get_code("a7e804e0909b8135")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Lukeasargen/targetClassifier when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

load_multitask_resnet Not yet run
unverified (harvested, no recorded run)
Lukeasargen/targetClassifier/models/multitask.py
pointer only (licence: NONE) · get_code("1c497cef0290295e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Lukeasargen/targetClassifier when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 4 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Numerous deep learning applications benefit from multi-task learning with multiple regression and classification objectives. In this paper we make the observation that the performance of such systems is strongly dependent on the relative weighting between each task's loss. Tuning these weights by hand is a difficult and expensive process, making multi-task learning prohibitive in practice. We propose a principled approach to multi-task deep learning which weighs multiple loss functions by considering the homoscedastic uncertainty of each task. This allows us to simultaneously learn various quantities with different units or scales in both classification and regression settings. We demonstrate our model learning per-pixel depth regression, semantic and instance segmentation from a monocular input image. Perhaps surprisingly, we show our model can learn multi-task weightings and outperform separate models trained individually on each task.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1705.07115")
get_code_for_paper("1705.07115")
have("1705.07115")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1705.07115.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1705.07115.svg)](https://syntology.ai/paper/1705.07115)

Connect an agent — have() is free.