ZooClaw-FashionSigLIP2: Distilled Fine-tuning for Robust Fashion Retrieval

• URL: http://arxiv.org/abs/2606.27708v1
• Date: Fri, 26 Jun 2026 04:13:32 GMT
• Title: ZooClaw-FashionSigLIP2: Distilled Fine-tuning for Robust Fashion Retrieval
• Abstract summary: We present ZooClaw-FashionSigLIP2, a fashion-specialized SigLIP2-base model that resolves this tradeoff with a simple recipe.<n>Under fair evaluation, ZooClaw-FashionSigLIP2 outperforms all baselines on every benchmark in our suite.<n>We release ZooClaw-Fashion, a new high-quality fashion retrieval benchmark, and a systematic quality analysis of widely-used benchmarks.
• Score: 4.984702219381009
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Adapting a foundation vision-language encoder to a specialized retrieval task creates a fundamental tradeoff: gains on the target distribution come at the cost of the foundation model's broad generalization, and fashion retrieval is a stringent instance of this problem. We present ZooClaw-FashionSigLIP2, a fashion-specialized SigLIP2-base model that resolves this tradeoff with a simple recipe -- full fine-tuning with knowledge distillation on curated in-domain data, followed by \wiseft~\citep{wortsman2022wiseft} weight interpolation with the base model -- and outperforms LoRA, larger backbones (up to 1B parameters), and external training data. Under fair evaluation, ZooClaw-FashionSigLIP2 outperforms all baselines on every benchmark in our suite. In addition, we release ZooClaw-Fashion, a new high-quality fashion retrieval benchmark, and a systematic quality analysis of widely-used benchmarks that exposes and mitigates structural biases in their public ground truth. We open-source the model weights and all evaluation artifacts to facilitate future research.

Related papers

• UniScale: Synergistic Entire Space Data and Model Scaling for Search Ranking [16.652956438207962]
  Large Language Models (LLMs) have inspired a surge of scaling law research in industrial search, advertising, and recommendation systems.<n>Existing approaches focus mainly on architectural improvements, overlooking the critical synergy between data and architecture design.<n>We propose UniScale to address these limitations, a novel co-design framework that jointly optimize data and architecture.
  arXiv  Detail & Related papers  (2026-03-25T12:00:26Z)
• Answer First, Reason Later: Aligning Search Relevance via Mode-Balanced Reinforcement Learning [7.006180736433431]
  Building a search relevance model that achieves both low latency and high performance is a long-standing challenge in the search industry.<n>We propose a novel textbfAnswer-First, Reason Later (AFRL) paradigm.<n>This paradigm requires the model to output the definitive relevance score in the very first token, followed by a structured logical explanation.
  arXiv  Detail & Related papers  (2026-02-10T17:28:12Z)
• LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence [61.46575527504109]
  LimiX-16M and LimiX-2M treat structured data as a joint distribution over variables and missingness.<n>We evaluate LimiX models across 11 large structured-data benchmarks with broad regimes of sample size, feature dimensionality, class number, categorical-to-numerical feature ratio, missingness, and sample-to-feature ratios.
  arXiv  Detail & Related papers  (2025-09-03T17:39:08Z)
• FACap: A Large-scale Fashion Dataset for Fine-grained Composed Image Retrieval [40.19988037304243]
  FACap is a large-scale, automatically constructed fashion-domain CIR dataset.<n>FashionBLIP-2 fine-tunes the general-domain BLIP-2 model on FACap with lightweight adapters.<n>FashionBLIP-2 is evaluated with and without additional fine-tuning on the Fashion IQ benchmark.
  arXiv  Detail & Related papers  (2025-07-08T23:02:10Z)
• SMPLest-X: Ultimate Scaling for Expressive Human Pose and Shape Estimation [81.36747103102459]
  Expressive human pose and shape estimation (EHPS) unifies body, hands, and face motion capture with numerous applications.<n>Current state-of-the-art methods focus on training innovative architectural designs on confined datasets.<n>We investigate the impact of scaling up EHPS towards a family of generalist foundation models.
  arXiv  Detail & Related papers  (2025-01-16T18:59:46Z)
• DreamMask: Boosting Open-vocabulary Panoptic Segmentation with Synthetic Data [61.62554324594797]
  We propose DreamMask, which explores how to generate training data in the open-vocabulary setting, and how to train the model with both real and synthetic data.<n>In general, DreamMask significantly simplifies the collection of large-scale training data, serving as a plug-and-play enhancement for existing methods.<n>For instance, when trained on COCO and tested on ADE20K, the model equipped with DreamMask outperforms the previous state-of-the-art by a substantial margin of 2.1% mIoU.
  arXiv  Detail & Related papers  (2025-01-03T19:00:00Z)
• FoundIR: Unleashing Million-scale Training Data to Advance Foundation Models for Image Restoration [66.61201445650323]
  Existing methods suffer from a generalization bottleneck in real-world scenarios.<n>We contribute a million-scale dataset with two notable advantages over existing training data.<n>We propose a robust model, FoundIR, to better address a broader range of restoration tasks in real-world scenarios.
  arXiv  Detail & Related papers  (2024-12-02T12:08:40Z)
• Generative Pre-trained Ranking Model with Over-parameterization at Web-Scale (Extended Abstract) [73.57710917145212]
  Learning to rank is widely employed in web searches to prioritize pertinent webpages based on input queries. We propose a emphulineGenerative ulineSemi-ulineSupervised ulinePre-trained (GS2P) model to address these challenges. We conduct extensive offline experiments on both a publicly available dataset and a real-world dataset collected from a large-scale search engine.
  arXiv  Detail & Related papers  (2024-09-25T03:39:14Z)
• Low-shot Object Learning with Mutual Exclusivity Bias [27.67152913041082]
  This paper introduces Low-shot Object Learning with Mutual Exclusivity Bias (LSME), the first computational framing of mutual exclusivity bias. We provide a novel dataset, comprehensive baselines, and a state-of-the-art method to enable the ML community to tackle this challenging learning task.
  arXiv  Detail & Related papers  (2023-12-06T14:54:10Z)
• Preserving Knowledge Invariance: Rethinking Robustness Evaluation of Open Information Extraction [49.15931834209624]
  We present the first benchmark that simulates the evaluation of open information extraction models in the real world.<n>We design and annotate a large-scale testbed in which each example is a knowledge-invariant clique.<n>By further elaborating the robustness metric, a model is judged to be robust if its performance is consistently accurate on the overall cliques.
  arXiv  Detail & Related papers  (2023-05-23T12:05:09Z)
• Universal Domain Adaptation from Foundation Models: A Baseline Study [58.51162198585434]
  We make empirical studies of state-of-the-art UniDA methods using foundation models. We introduce textitCLIP distillation, a parameter-free method specifically designed to distill target knowledge from CLIP models. Although simple, our method outperforms previous approaches in most benchmark tasks.
  arXiv  Detail & Related papers  (2023-05-18T16:28:29Z)
• SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval [11.38022203865326]
  SPLADE model provides highly sparse representations and competitive results with respect to state-of-the-art dense and sparse approaches. We modify the pooling mechanism, benchmark a model solely based on document expansion, and introduce models trained with distillation. Overall, SPLADE is considerably improved with more than $9$% gains on NDCG@10 on TREC DL 2019, leading to state-of-the-art results on the BEIR benchmark.
  arXiv  Detail & Related papers  (2021-09-21T10:43:42Z)
• Explaining a Series of Models by Propagating Local Feature Attributions [9.66840768820136]
  Pipelines involving several machine learning models improve performance in many domains but are difficult to understand. We introduce a framework to propagate local feature attributions through complex pipelines of models based on a connection to the Shapley value. Our framework enables us to draw higher-level conclusions based on groups of gene expression features for Alzheimer's and breast cancer histologic grade prediction.
  arXiv  Detail & Related papers  (2021-04-30T22:20:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.