FIGROTD: A Friendly-to-Handle Dataset for Image Guided Retrieval with Optional Text
Image-Guided Retrieval with Optional Text (IGROT) unifies visual retrieval (without text) and composed retrieval (with text). Despite its relevance in applications like Google Image and Bing, progress has been limited by the lack of an accessible benchmark and methods that balance performance across subtasks. Large-scale datasets such as MagicLens are comprehensive but computationally prohibitive, while existing models often favor either visual or compositional queries. We introduce FIGROTD, a lightweight yet high-quality IGROT dataset with 16,474 training triplets and 1,262 test triplets across CIR, SBIR, and CSTBIR. To reduce redundancy, we propose the Variance Guided Feature Mask (VaGFeM), which selectively enhances discriminative dimensions based on variance statistics. We further adopt a dual-loss design (InfoNCE + Triplet) to improve compositional reasoning. Trained on FIGROTD, VaGFeM achieves competitive results on nine benchmarks, reaching 34.8 mAP@10 on CIRCO and 75.7 mAP@200 on Sketchy, outperforming stronger baselines despite fewer triplets.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Language-Guided Global Image Editing via Cross-Modal Cyclic Mechanism
Editing an image automatically via a linguistic request can significantly save laborious manual work and is friendly to photography novice. In this paper, we focus on the task of language-guided global image editing.…
URIE: Universal Image Enhancement for Visual Recognition in the Wild
Despite the great advances in visual recognition, it has been witnessed that recognition models trained on clean images of common datasets are not robust against distorted images in the real world. To tackle this issue, …
Image EnhancementURIE: Universal Image Enhancement for Visual Recognition in the Wild
Despite the great advances in visual recognition, it has been witnessed that recognition models trained on clean images of common datasets are not robust against distorted images in the real world. To tackle this issue, …
Image EnhancementUniMedSeg: Unified In-Context Learning for Multi-Paradigm 2D/3D Medical Image Segmentation
Medical image segmentation foundation models are expected to generalize across diverse clinical scenarios, yet existing universal methods remain fragmented by prompt paradigms and spatial dimensions. Visual in-context le…
Medical Image SegmentationInteractive SegmentationMAD: Makeup All-in-One with Cross-Domain Diffusion Model
Existing makeup techniques often require designing multiple models to handle different inputs and align features across domains for different makeup tasks, e.g., beauty filter, makeup transfer, and makeup removal, leadin…
AllDecoder