Learning Fine-Grained Visual Classification with Text as Privileged Information via Multimodal Distillation

Few-shot fine-grained visual classification (FGVC) aims to discriminate between subtly different categories with very limited data. While Multimodal Large Language Models (MLLM) exhibit strong capabilities in both fine-grained visual understanding and open-world category recognition, directly fine-tuning them on few-shot FGVC tasks typically leads to overfitting on sparse samples, which erodes their valuable open-world knowledge and compromises generalization. To fundamentally overcome this limitation, we present UniFGVC, a universal training-free framework that shifts the paradigm from parameter fine-tuning to training-free retrieval-based inference. UniFGVC reframes few-shot FGVC as a multimodal retrieval problem using predefined category templates. Its core is the Category-Discriminative Visual Captioner (CDV-Captioner), an attribute-aware module designed to leverage MLLM for generating structured textual descriptions that explicitly pinpoint discriminative visual attributes between similar classes. By integrating chain-of-thought reasoning and visual references, CDV-Captioner mitigates hallucination and maximizes the discriminative power of textual captions, thereby converting images into attribute-enriched image-description pairs. Subsequently, utilizing arbitrary pre-trained visual and textual encoders in a plug-and-play manner, UniFGVC extracts features from both modalities and computes their similarity with all category templates for recognition. Extensive experiments on 12 FGVC datasets demonstrate UniFGVC's universal compatibility and consistent superiority. It not only outperforms existing few-shot CLIP-based methods but also surpasses several fully-supervised MLLM-based approaches, confirming the general advantage of the proposed retrieval paradigm.

Multimodal large language models are typically trained end-to-end to predict ground-truth answers, yet supervision signals are applied exclusively to text tokens. Visual tokens, the core carriers of visual information, are optimized only implicitly as part of the context, leading to coarse-grained visual understanding. Prior works attempt to supervise visual inputs but inevitably rely on auxiliary components such as additional decoders or forward passes, because visual tokens lack readily interpretable labels. This limits their practical applicability. In this work, we propose Direct Vision Supervised Fine-Tuning (DV-SFT), which constructs explicit, token-level supervision for visual tokens and trains them through the same next-token prediction objective used for text. Specifically, we exploit the direct vision--text correspondence in OCR-related scenarios and automatically label each visual token with the word in its corresponding image patch. DV-SFT treats the MLLM as a black box, requiring no architectural modifications or additional forward passes. Extensive experiments demonstrate the superiority of direct vision supervision. DV-SFT consistently outperforms standard SFT across three in-domain and four out-of-domain benchmarks. Further analyses show that vision supervision effectively enhances fine-grained visual understanding and achieves higher multimodal alignment efficiency.

An image may be worth a thousand words, but most captioning models describe it in only a few. Modern vision-language models produce fluent high-level captions, yet routinely miss the attributes, counts, textures, materials, and spatial relations that make an image visually specific. Recent multi-stage systems recover some of these details through generation, decomposition, verification, and rewriting, but they do so at the expense of substantially higher inference latency. We propose SimLoss, a reference-free embedding-space objective for single-pass fine-grained image captioning. SimLoss trains a vision-language model to align its projected hidden-state representation with a frozen image embedding through an InfoNCE contrastive loss, supplying a dense visual supervision signal before any text is decoded, and requiring neither human-written fine-grained captions nor pseudo-captions from a multi-stage pipeline. We instantiate it as SimLoss FFT, which backpropagates through a locally available embedding model, and SimLoss GRPO, which treats that model as a black-box reward. Compared with single-pass, multi-stage verification, reward-optimized, and perception-aware baselines, the fully differentiable fine-tuning variant, SimLoss FFT, achieves the highest precision while nearly matching the F1 score of the multi-stage method, all while retaining single-pass inference and running roughly 20 times faster than the multi-stage pipeline. The reward-based variant SimLoss GRPO attains the strongest recall. Together, these results show that embedding-space supervision can recover the quality of multi-stage verification at the latency of a single-pass captioner.