SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.09859 · CVPR · 2021

RSG: A Simple but Effective Module for Learning Imbalanced Datasets

Xiaolin Hu, Thomas Lukasiewicz, Jianfeng Wang, Jianfei Cai, Conv Conv, Zhenghua Xu

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 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; 0 failures of our instrument; 0 no recorded run), measured 2026-11-22; 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/2106.09859.json · badge: /api/ran/2106.09859.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
Jianf-Wang/RSG marked official in Papers with Code
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
RSG Ran
ran on a synthesized input
Jianf-Wang/RSG/Imbalanced_Classification/models/RSG.py
code served (permissive licence) · get_code("54209fecacac35e9")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 0, dtype family float; no output shape is stated. 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 and ndim 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 numpy as np

# INIT_ARGS for RSG.__init__
INIT_ARGS = {
    'n_center': 3,
    'feature_maps_shape': [8, 4, 4],  # [C, H, W] - small feature map
    'num_classes': 5,
    'contrastive_module_dim': 16,
    'head_class_lists': [],
    'transfer_strength': 1.0,
    'epoch_thresh': 100
}

# Create the module
# Note: The class has .cuda() calls in __init__, which will fail on CPU-only
# We need to modify or work around this, but per instructions we let it fail on its own terms
# Actually, we can construct tensors on CPU and the class will try to move them

# For the forward/computation call, we need to identify which method does computation
# Looking at the class, there are two main methods: compute_cesc_loss and compute_mv_loss
# We'll use compute_cesc_loss as the primary computation method

METHOD = 'compute_cesc_loss'

# ARGS for compute_cesc_loss(self, feature_maps, c, gamma, target, epoch)
batch_size = 4  # Must be even since code splits in half
C = INIT_ARGS['feature_maps_shape'][0]  # 8
H = INIT_ARGS['feature_maps_shape'][1]  # 4
W = INIT_ARGS['feature_maps_shape'][2]  # 4
n_center = INIT_ARGS['n_center']  # 3
num_classes = INIT_ARGS['num_classes']  # 5

ARGS = {
    'feature_maps': torch.randn(batch_size, C, H, W),
    'c': torch.randn(batch_size, n_center, C, H, W),
    'gamma': torch.randn(batch_size, n_center),
    'target': torch.randint(0, num_classes, (batch_size,)),
    'epoch': 50  # Below epoch_thresh to trigger full loss computation
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 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 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.

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

Imbalanced datasets widely exist in practice and are a great challenge for training deep neural models with a good generalization on infrequent classes. In this work, we propose a new rare-class sample generator (RSG) to solve this problem. RSG aims to generate some new samples for rare classes during training, and it has in particular the following advantages: (1) it is convenient to use and highly versatile, because it can be easily integrated into any kind of convolutional neural network, and it works well when combined with different loss functions, and (2) it is only used during the training phase, and therefore, no additional burden is imposed on deep neural networks during the testing phase. In extensive experimental evaluations, we verify the effectiveness of RSG. Furthermore, by leveraging RSG, we obtain competitive results on Imbalanced CIFAR and new state-of-the-art results on Places-LT, ImageNet-LT, and iNaturalist 2018. The source code is available at https://github.com/Jianf-Wang/RSG.

For agents

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

get_harvested_code_for_paper("2106.09859")
get_code_for_paper("2106.09859")
have("2106.09859")

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

curl https://syntology.ai/api/ran/2106.09859.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.09859.svg)](https://syntology.ai/paper/2106.09859)

Connect an agent — have() is free.