SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2010.05063 · 2020

Adaptive Aggregation Networks for Class-Incremental Learning

arXiv · PDF · Open in the Atlas

Code that ran

4 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 1 has no contract verdict; 3 failures of our instrument; 0 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/2010.05063.json · badge: /api/ran/2010.05063.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
yaoyao-liu/class-incremental-learning canonical (classifier label)
classifier basis: census
4 ran · 0 no recorded run
FunctionStatusWhere it lives
conv3x3 Ran
ran; our contract draft was wrong, not the code
yaoyao-liu/class-incremental-learning/adaptive-aggregation-networks/models/modified_resnet_cifar.py
pointer only (licence: MIT); the stored copy get_code serves, from lixiaotong97/DSU, is pointer only (licence: NONE) · get_code("fac5364e2f53c6db")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from lixiaotong97/DSU, and GitHub detected no licence in that repository 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.

conv3x3 Ran
ran; our contract draft was wrong, not the code
yaoyao-liu/class-incremental-learning/adaptive-aggregation-networks/models/modified_resnet.py
pointer only (licence: MIT); the stored copy get_code serves, from amerch/CIFAR100-Training, is pointer only (licence: NONE) · get_code("583f9780bdd00a45")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from amerch/CIFAR100-Training, and GitHub detected no licence in that repository 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.

incremental_train_and_eval Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yaoyao-liu/class-incremental-learning/mnemonics-training/1_train/trainer/incremental.py
code served (permissive licence) · get_code("a99cc76d5a5b058b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned SimpleModel. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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
import torch.nn as nn
import torch.nn.functional as F

torch.manual_seed(0)

# Define a minimal target model
class SimpleModel(nn.Module):
    def __init__(self, num_classes=10):
        super().__init__()
        self.conv1 = nn.Conv2d(3, 8, kernel_size=3, padding=1)
        self.bn1 = nn.BatchNorm2d(8)
        self.fc = nn.Linear(8 * 32 * 32, num_classes)
    
    def forward(self, x):
        x = self.bn1(self.conv1(x))
        x = x.view(x.size(0), -1)
        x = self.fc(x)
        return x

# Define a reference model (for iteration > start_iteration case)
class RefModel(nn.Module):
    def __init__(self, num_classes=5):
        super().__init__()
        self.conv1 = nn.Conv2d(3, 8, kernel_size=3, padding=1)
        self.bn1 = nn.BatchNorm2d(8)
        self.fc = nn.Linear(8 * 32 * 32, num_classes)
    
    def forward(self, x):
        x = self.bn1(self.conv1(x))
        x = x.view(x.size(0), -1)
        x = self.fc(x)
        return x

# Create models
tg_model = SimpleModel(num_classes=10)
ref_model = RefModel(num_classes=5)
free_model = SimpleModel(num_classes=10)
ref_free_model = RefModel(num_classes=5)

# Create optimizer and scheduler
tg_optimizer = torch.optim.SGD(tg_model.parameters(), lr=0.1)
tg_lr_scheduler = torch.optim.lr_scheduler.StepLR(tg_optimizer, step_size=1, gamma=0.1)

# Create dummy data loaders
def create_dataloader(batch_size=2, num_batches=2, num_classes=10, img_size=32):
    data = []
    for _ in range(num_batches):
        inputs = torch.randn(batch_size, 3, img_size, img_size)
        targets = torch.randint(0, num_classes, (batch_size,))
        data.append((inputs, targets))
    return data

trainloader = create_dataloader(batch_size=2, num_batches=2, num_classes=10)
testloader = create_dataloader(batch_size=2, num_batches=1, num_classes=10)

# Create weight_per_class
weight_per_class = torch.ones(10)

ARGS = {
    'epochs': 1,
    'tg_model': tg_model,
    'ref_model': ref_model,
    'free_model': free_model,
    'ref_free_model': ref_free_model,
    'tg_optimizer': tg_optimizer,
    'tg_lr_scheduler': tg_lr_scheduler,
    'trainloader': trainloader,
    'testloader': testloader,
    'iteration': 0,
    'start_iteration': 0,
    'lamda': 1.0,
    'dist': 'cosine',
    'K': 5,
    'lw_mr': 0.5,
    'fix_bn': False,
    'weight_per_class': weight_per_class,
    'device': torch.device('cpu')
}
Setup block drafted by
a language model, Claude Haiku 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 SimpleModel — a SimpleModel output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleModel 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
map_labels Ran
ran on a synthesized input
yaoyao-liu/class-incremental-learning/adaptive-aggregation-networks/trainer/incremental_lucir.py
code served (permissive licence) · get_code("368a74858ba14c36")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 1, dtype family int, shape (3,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 numpy as np

# map_labels takes:
# 1. order_list: a list that supports .index() method - needs to contain elements that can be looked up
# 2. Y_set: an iterable of indices/labels that will be searched in order_list

# Create a simple order_list with some distinct values
order_list = [10, 20, 30, 40, 50]

# Create Y_set with values that exist in order_list
Y_set = [30, 10, 50]

ARGS = {
    "order_list": order_list,
    "Y_set": Y_set
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family int, shape (3,) — shape (3,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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

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 3 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 1 the same month, 1 later) and 1 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.

FunctionAlso present inEarliest-datedOthers named
conv3x3 686 other papers
261 dated earlier, 7 the same month, 417 later, 1 same year, order not determinable · 31 only as an assembly brick
1406.2661 (2014-06)
Generative Adversarial Networks
1409.0575 (2014-09)
ImageNet Large Scale Visual Recognition Challenge
1412.6572 (2014-12)
Explaining and Harnessing Adversarial Examples
and 683 more not named here
incremental_train_and_eval 1 other paper
1 dated earlier
1606.09282 (2016-06)
Learning without Forgetting

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

Class-Incremental Learning (CIL) aims to learn a classification model with the number of classes increasing phase-by-phase. An inherent problem in CIL is the stability-plasticity dilemma between the learning of old and new classes, i.e., high-plasticity models easily forget old classes, but high-stability models are weak to learn new classes. We alleviate this issue by proposing a novel network architecture called Adaptive Aggregation Networks (AANets), in which we explicitly build two types of residual blocks at each residual level (taking ResNet as the baseline architecture): a stable block and a plastic block. We aggregate the output feature maps from these two blocks and then feed the results to the next-level blocks. We adapt the aggregation weights in order to balance these two types of blocks, i.e., to balance stability and plasticity, dynamically. We conduct extensive experiments on three CIL benchmarks: CIFAR-100, ImageNet-Subset, and ImageNet, and show that many existing CIL methods can be straightforwardly incorporated into the architecture of AANets to boost their performances.

For agents

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

get_harvested_code_for_paper("2010.05063")
get_code_for_paper("2010.05063")
have("2010.05063")

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

curl https://syntology.ai/api/ran/2010.05063.json

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

[![Syntology run record](https://syntology.ai/api/ran/2010.05063.svg)](https://syntology.ai/paper/2010.05063)

Connect an agent — have() is free.