arXiv Computer Vision

Project and Mix: Task-Semantic Prototypes for Few-Shot Image Classification

arXiv Computer Vision
Oct 16

Flow-CLIP: Image-Conditioned Residual Scoring for CompositionalImage-Text Matching

Flow-CLIP introduces a method to improve compositional image-text matching by refining global image-text alignment with image-conditioned changes in token–patch evidence. It combines Global Compatibility Calibration (GCC) for sentence-level similarity, Image-Conditioned Evidence Refinement (ICER) to incorporate visual patch context, and Cross-Image Margin Ranking (CIMR) to enhance ranking margins when images support correct descriptions. Experiments demonstrate that Flow-CLIP outperforms pretrained CLIP and other global alignment approaches on binding accuracy and reduces reliance on language priors.

By Minghong Wei, Enguang Zhu, Pu Cao, Lu Yang, Qing Song
arXiv AI
6d ago

Aligning Forest and Trees in Images & Long Captions for Visually Grounded Understanding

The paper introduces CAFT, a vision‑language model that improves understanding of long, detail‑rich captions by aligning local text regions with image parts before forming a global representation. It uses a fine‑to‑coarse image encoder and a part‑to‑whole text encoder to discover localized semantics and compose them into a holistic image‑text embedding. Trained on 30 M image‑text pairs, CAFT outperforms existing methods on six long‑text retrieval benchmarks and scales well, learning fine‑grained representations without explicit region supervision.

By Byeongju Woo, Zilin Wang, Byeonghyun Pak, Sangwoo Mo, Stella X. Yu
arXiv AI
Oct 16

UniFGVC: Universal Training-Free Few-Shot Fine-Grained Vision Classification via Attribute-Aware Multimodal Retrieval

UniFGVC introduces a training‑free framework for few‑shot fine‑grained visual classification that reframes the task as a multimodal retrieval problem. It uses a Category‑Discriminative Visual Captioner to generate attribute‑aware textual descriptions, then matches image‑description pairs with category templates via pre‑trained encoders. Experiments on 12 datasets show that UniFGVC consistently outperforms existing CLIP‑based and fully‑supervised MLLM methods, demonstrating the effectiveness of the retrieval paradigm.

By Haiyun Guo, Hongyu Guo, Xiangzhao Hao, Jiarui Guo, Jinqiao Wang, Tat-Seng Chua
arXiv Computer Vision
Sep 28

ProCAP: Probabilistic Cross-Attentive Prompt Learning for Vision-Language Models

ProCAP introduces a probabilistic cross-attentive prompt learning framework for vision-language models like CLIP, enabling improved cross-modal interaction without updating the backbone. It jointly learns visual and textual prompt tokens, linking them via stacked bidirectional multi-head cross-attention to refine each branch across prompt depth. The method incorporates Gaussian parameterization of prompt tokens, lightweight KL and L2 regularization, and a compact symmetric InfoNCE head to align image features with class-level text representations, achieving strong few-shot base-to-novel performance and competitive transfer results across multiple datasets and benchmarks.

By Hiwa Azeez Abbas, Fatemeh Daneshfar, Moloud Abdar
arXiv AI
Sep 30

One Geometry, Different Outcomes: Readout-Dependent Effects of the Modality Gap in Vision-Language Models

The paper investigates how the modality gap— the separation between image and text representations in contrastive vision‑language models—affects different downstream tasks. By showing that a single dominant direction accounts for most of the image‑text mean separation, the authors explain why reducing or removing this gap can improve zero‑shot classification, degrade retrieval, or restore performance depending on the task. The study provides a geometric framework that clarifies when and why gap interventions should be applied in vision‑language systems.

By Aditya Sharma, Divya Saxena