SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2103.05950 · CVPR · 2021

FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding

Chi Zhang, Ye Yuan, Banghuai Li, Bo Sun, Shengcai Cai

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; 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/2103.05950.json · badge: /api/ran/2103.05950.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
MegviiDetection/FSCE marked official in Papers with Code
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
SupConLoss Ran
ran on a synthesized input
MegviiDetection/FSCE/fsdet/modeling/contrastive_loss.py
code served (permissive licence) · get_code("a99e005b92d2d1b4")
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

class SupConLoss(nn.Module):
    """Supervised Contrastive LOSS as defined in https://arxiv.org/pdf/2004.11362.pdf."""

    def __init__(self, temperature=0.2, iou_threshold=0.5, reweight_func='none'):
        """Args:
            tempearture: a constant to be divided by consine similarity to enlarge the magnitude
            iou_threshold: consider proposals with higher credibility to increase consistency.
        """
        super().__init__()
        self.temperature = temperature
        self.iou_threshold = iou_threshold
        self.reweight_func = reweight_func

    def forward(self, features, labels, ious):
        """
        Args:
            features (tensor): shape of [M, K] where M is the number of features to be compared,
                and K is the feature_dim.   e.g., [8192, 128]
            labels (tensor): shape of [M].  e.g., [8192]
        """
        assert features.shape[0] == labels.shape[0] == ious.shape[0]
        if len(labels.shape) == 1:
            labels = labels.reshape(-1, 1)
        label_mask = torch.eq(labels, labels.T).float().cuda()
        similarity = torch.div(torch.matmul(features, features.T), self.temperature)
        sim_row_max, _ = torch.max(similarity, dim=1, keepdim=True)
        similarity = similarity - sim_row_max.detach()
        logits_mask = torch.ones_like(similarity)
        logits_mask.fill_diagonal_(0)
        exp_sim = torch.exp(similarity) * logits_mask
        log_prob = similarity - torch.log(exp_sim.sum(dim=1, keepdim=True))
        per_label_log_prob = (log_prob * logits_mask * label_mask).sum(1) / label_mask.sum(1)
        keep = ious >= self.iou_threshold
        per_label_log_prob = per_label_log_prob[keep]
        loss = -per_label_log_prob
        coef = self._get_reweight_func(self.reweight_func)(ious)
        coef = coef[keep]
        loss = loss * coef
        return loss.mean()

    @staticmethod
    def _get_reweight_func(option):

        def trivial(iou):
            return torch.ones_like(iou)

        def exp_decay(iou):
            return torch.exp(iou) - 1

        def linear(iou):
            return iou
        if option == 'none':
            return trivial
        elif option == 'linear':
            return linear
        elif option == 'exp':
            return exp_decay


INIT_ARGS = {
    'temperature': 0.2,
    'iou_threshold': 0.5,
    'reweight_func': 'none'
}

ARGS = {
    'features': torch.randn(6, 4),
    'labels': torch.tensor([0, 0, 1, 1, 2, 2]),
    'ious': torch.tensor([0.6, 0.7, 0.55, 0.8, 0.9, 0.65])
}

if __name__ == '__main__':
    model = SupConLoss(**INIT_ARGS)
    try:
        output = model(**ARGS)
        print(f"Loss output: {output}")
    except RuntimeError as e:
        print(f"Expected error (CUDA not available): {e}")
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
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

Recent researches demonstrate that good feature embedding is the key to reach favorable few-shot learning performance. We observe object proposals with different Intersection-of-Union (IoU) scores are analogous to the intra-image augmentation used in contrastive visual representation learning. And we exploit this analogy and incorporate supervised contrastive learning to achieve more robust objects representations in FSOD. We present Few-Shot object detection via Contrastive proposals Encoding (FSCE), a simple yet effective approach to learning contrastive-aware object proposal encodings that facilitate the classification of detected objects. We notice the degradation of average precision (AP) for rare objects mainly comes from misclassifying novel instances as confusable classes. And we ease the misclassification issues by promoting instance level intraclass compactness and inter-class variance via our contrastive proposal encoding loss (CPE loss). Our design outperforms current state-of-the-art works in any shot and all data splits, with up to +8.8% on standard benchmark PASCAL VOC and +2.7% on challenging COCO benchmark. Code is available at: https://github.com/ MegviiDetection/FSCE.

For agents

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

get_harvested_code_for_paper("2103.05950")
get_code_for_paper("2103.05950")
have("2103.05950")

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

curl https://syntology.ai/api/ran/2103.05950.json

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

[![Syntology run record](https://syntology.ai/api/ran/2103.05950.svg)](https://syntology.ai/paper/2103.05950)

Connect an agent — have() is free.