@inproceedings{poornima-mathias-2026-whitening,
title = "Whitening and Fine-Tuning Are Substitutes: One-Shot {I}ndian {S}ign {L}anguage Recognition",
author = "Poornima, Galiveeti and
Mathias, Sandeep",
editor = "Singh, Sanjeet and
Joshi, Abhinav and
Dattatreya, Pokala and
Artiaga, Keren and
Pujara, Khushi Jaydeep and
{\v{Z}}elezn{\'y}, Tom{\'a}{\v{s}} and
Gruber, Ivan and
Honz{\'i}k, Jakub and
Kamila, Sabyasachi and
Quiroga, Facundo Manuel and
Hr{\'u}z, Marek and
Hasanuzzaman, Mohammed and
Modi, Ashutosh",
booktitle = "Proceedings of the Second Workshop on Sign Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.wslp-1.4/",
pages = "32--42",
ISBN = "979-8-89176-488-0",
abstract = "We describe our submission to the WSLP 2026 shared task on Isolated Sign Language Recognition. The task is one-shot retrieval over 4,361 Indian Sign Language word classes with roughly one training clip per class. Our final system placed 3rd on top-1 accuracy at 0.6825 and 2nd on top-10 at 0.7357. The system is deliberately simple. It combines MediaPipe keypoints, a graph attention backbone pretrained on a different ISL corpus, PCA whitening, and nearest-exemplar cosine retrieval against an enriched gallery. Our main finding concerns how two very differently priced interventions relate. PCA whitening of the frozen cross-corpus encoder is worth +18.85 points on a leave-one-out gallery evaluation. Fine-tuning that encoder end-to-end is worth a comparable amount. The two do not compose. Once the encoder has been fine-tuned, whitening adds +0.38 points, an interaction of {\ensuremath{-}}18.5. Whitening and fine-tuning act as substitutes because both correct the same embedding anisotropy, and a transform that is fitted in seconds captures most of what a day of GPU training buys. We also report fifteen interventions that produced no usable gain: twelve indistinguishable from zero and three actively harmful. These were evaluated with McNemar tests on a 2,030-query held-out split with a minimum detectable effect of 1.23 points. We argue that the 526-clip official test set is too small to support the comparisons participants routinely make with it."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="poornima-mathias-2026-whitening">
<titleInfo>
<title>Whitening and Fine-Tuning Are Substitutes: One-Shot Indian Sign Language Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Galiveeti</namePart>
<namePart type="family">Poornima</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandeep</namePart>
<namePart type="family">Mathias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Sign Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sanjeet</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhinav</namePart>
<namePart type="family">Joshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pokala</namePart>
<namePart type="family">Dattatreya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Keren</namePart>
<namePart type="family">Artiaga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khushi</namePart>
<namePart type="given">Jaydeep</namePart>
<namePart type="family">Pujara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomáš</namePart>
<namePart type="family">Železný</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Gruber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jakub</namePart>
<namePart type="family">Honzík</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sabyasachi</namePart>
<namePart type="family">Kamila</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Facundo</namePart>
<namePart type="given">Manuel</namePart>
<namePart type="family">Quiroga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marek</namePart>
<namePart type="family">Hrúz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="family">Hasanuzzaman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashutosh</namePart>
<namePart type="family">Modi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-488-0</identifier>
</relatedItem>
<abstract>We describe our submission to the WSLP 2026 shared task on Isolated Sign Language Recognition. The task is one-shot retrieval over 4,361 Indian Sign Language word classes with roughly one training clip per class. Our final system placed 3rd on top-1 accuracy at 0.6825 and 2nd on top-10 at 0.7357. The system is deliberately simple. It combines MediaPipe keypoints, a graph attention backbone pretrained on a different ISL corpus, PCA whitening, and nearest-exemplar cosine retrieval against an enriched gallery. Our main finding concerns how two very differently priced interventions relate. PCA whitening of the frozen cross-corpus encoder is worth +18.85 points on a leave-one-out gallery evaluation. Fine-tuning that encoder end-to-end is worth a comparable amount. The two do not compose. Once the encoder has been fine-tuned, whitening adds +0.38 points, an interaction of \ensuremath-18.5. Whitening and fine-tuning act as substitutes because both correct the same embedding anisotropy, and a transform that is fitted in seconds captures most of what a day of GPU training buys. We also report fifteen interventions that produced no usable gain: twelve indistinguishable from zero and three actively harmful. These were evaluated with McNemar tests on a 2,030-query held-out split with a minimum detectable effect of 1.23 points. We argue that the 526-clip official test set is too small to support the comparisons participants routinely make with it.</abstract>
<identifier type="citekey">poornima-mathias-2026-whitening</identifier>
<location>
<url>https://aclanthology.org/2026.wslp-1.4/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>32</start>
<end>42</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Whitening and Fine-Tuning Are Substitutes: One-Shot Indian Sign Language Recognition
%A Poornima, Galiveeti
%A Mathias, Sandeep
%Y Singh, Sanjeet
%Y Joshi, Abhinav
%Y Dattatreya, Pokala
%Y Artiaga, Keren
%Y Pujara, Khushi Jaydeep
%Y Železný, Tomáš
%Y Gruber, Ivan
%Y Honzík, Jakub
%Y Kamila, Sabyasachi
%Y Quiroga, Facundo Manuel
%Y Hrúz, Marek
%Y Hasanuzzaman, Mohammed
%Y Modi, Ashutosh
%S Proceedings of the Second Workshop on Sign Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-488-0
%F poornima-mathias-2026-whitening
%X We describe our submission to the WSLP 2026 shared task on Isolated Sign Language Recognition. The task is one-shot retrieval over 4,361 Indian Sign Language word classes with roughly one training clip per class. Our final system placed 3rd on top-1 accuracy at 0.6825 and 2nd on top-10 at 0.7357. The system is deliberately simple. It combines MediaPipe keypoints, a graph attention backbone pretrained on a different ISL corpus, PCA whitening, and nearest-exemplar cosine retrieval against an enriched gallery. Our main finding concerns how two very differently priced interventions relate. PCA whitening of the frozen cross-corpus encoder is worth +18.85 points on a leave-one-out gallery evaluation. Fine-tuning that encoder end-to-end is worth a comparable amount. The two do not compose. Once the encoder has been fine-tuned, whitening adds +0.38 points, an interaction of \ensuremath-18.5. Whitening and fine-tuning act as substitutes because both correct the same embedding anisotropy, and a transform that is fitted in seconds captures most of what a day of GPU training buys. We also report fifteen interventions that produced no usable gain: twelve indistinguishable from zero and three actively harmful. These were evaluated with McNemar tests on a 2,030-query held-out split with a minimum detectable effect of 1.23 points. We argue that the 526-clip official test set is too small to support the comparisons participants routinely make with it.
%U https://aclanthology.org/2026.wslp-1.4/
%P 32-42
Markdown (Informal)
[Whitening and Fine-Tuning Are Substitutes: One-Shot Indian Sign Language Recognition](https://aclanthology.org/2026.wslp-1.4/) (Poornima & Mathias, WSLP 2026)
ACL