SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.03871 · ECCV · 2022

Discriminability-Transferability Trade-Off: An Information-Theoretic Perspective

Bingchen Zhao, Boyan Zhou, Jiajun Liang, Borui Zhao, Renjie Song, Osamu Yoshie, Quan Cui, Zhao-Min Chen

arXiv · PDF · Open in the Atlas

Code that ran

5 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (4 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 0 failures of our instrument; 1 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/2203.03871.json · badge: /api/ran/2203.03871.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
dtennant/dt-tradeoff marked official in Papers with Code
Papers with Code archive
5 ran · 1 no recorded run
FunctionStatusWhere it lives
AliasMethod Ran
ran on a synthesized input · constructed an object; no result was computed
dtennant/dt-tradeoff/ctc/criterion.py
pointer only (licence: NONE) · get_code("0623387d3fc470ae")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dtennant/dt-tradeoff 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.

ContrastLoss Ran
ran on a synthesized input
dtennant/dt-tradeoff/ctc/criterion.py
pointer only (licence: NONE) · get_code("ac6ff5b3409890d5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dtennant/dt-tradeoff 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.

ContrastMemory Ran
ran on a synthesized input · constructed an object; no result was computed
dtennant/dt-tradeoff/ctc/criterion.py
pointer only (licence: NONE) · get_code("1a66230ccdff534e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dtennant/dt-tradeoff 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.

Embed Ran
ran on a synthesized input · constructed an object; no result was computed
dtennant/dt-tradeoff/ctc/criterion.py
pointer only (licence: NONE) · get_code("b6c6cecd56066877")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dtennant/dt-tradeoff 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.

Normalize Ran
ran on a synthesized input · constructed an object; no result was computed
dtennant/dt-tradeoff/ctc/criterion.py
pointer only (licence: NONE) · get_code("f863c8104c19474d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dtennant/dt-tradeoff 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.

ContrastiveLoss Not yet run
unverified (harvested, no recorded run)
dtennant/dt-tradeoff/ctc/criterion.py
pointer only (licence: NONE) · get_code("47efee388b17abe8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dtennant/dt-tradeoff 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 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 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 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.

FunctionAlso present inEarliest-datedOthers named
Normalize
brick of this paper's assembly: helper
7 other papers
3 dated earlier, 1 the same month, 3 later · 6 only as an assembly brick
2009.14167 (2020-09)
Contrastive Distillation on Intermediate Representations for Language Model Compression
2103.16367 (2021-03)
Complementary Relation Contrastive Distillation
2104.02366 (2021-04)
Neural Feature Search for RGB-Infrared Person Re-Identification
and 4 more not named here
AliasMethod
brick of this paper's assembly: helper
3 other papers
3 dated earlier · 2 only as an assembly brick
1805.01978 (2018-05)
Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination
2009.14167 (2020-09)
Contrastive Distillation on Intermediate Representations for Language Model Compression
2103.16367 (2021-03)
Complementary Relation Contrastive Distillation

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

This work simultaneously considers the discriminability and transferability properties of deep representations in the typical supervised learning task, i.e., image classification. By a comprehensive temporal analysis, we observe a trade-off between these two properties. The discriminability keeps increasing with the training progressing while the transferability intensely diminishes in the later training period. From the perspective of information-bottleneck theory, we reveal that the incompatibility between discriminability and transferability is attributed to the over-compression of input information. More importantly, we investigate why and how the InfoNCE loss can alleviate the over-compression, and further present a learning framework, named contrastive temporal coding (CTC), to counteract the over-compression and alleviate the incompatibility. Extensive experiments validate that CTC successfully mitigates the incompatibility, yielding discriminative and transferable representations. Noticeable improvements are achieved on the image classification task and challenging transfer learning tasks. We hope that this work will raise the significance of the transferability property in the conventional supervised learning setting.

For agents

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

get_harvested_code_for_paper("2203.03871")
get_code_for_paper("2203.03871")
have("2203.03871")

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

curl https://syntology.ai/api/ran/2203.03871.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.03871.svg)](https://syntology.ai/paper/2203.03871)

Connect an agent — have() is free.