Image Retrieval

Description from the archive archive 2025-07-28; Papers-with-Code links inside it are rewritten to this site.

Benchmarks archive 2025-07-28

56 leaderboard tables shown for this task, 56 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 56 until expanded.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

87 datasets whose archive record lists this task, ordered by the archive's paper count. 30 shown of 87 until expanded.

Subtasks archive 2025-07-28

10 subtasks in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 835 papers with code (2,239 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Emerging Properties in Self-Supervised Vision Transformers
  29 Apr 2021 32 repositories listed Syntology ran 5 of 20 samples · 15 unverified · 2 pointer-only (licence)
  In this paper, we question if self-supervised learning provides new properties to Vision Transformer (ViT) that stand out compared to convolutional networks (convnets).
• DINOv2: Learning Robust Visual Features without Supervision
  14 Apr 2023 26 repositories listed Syntology ran 21 of 46 samples · 25 unverified · 12 pointer-only (licence)
  The recent breakthroughs in natural language processing for model pretraining on large quantities of data have opened the way for similar foundation models in computer vision.
• VGGFace2: A dataset for recognising faces across pose and age
  23 Oct 2017 24 repositories listed Syntology ran 5 of 8 samples · 3 unverified · 5 pointer-only (licence)
  The dataset was collected with three goals in mind: (i) to have both a large number of identities and also a large number of images for each identity; (ii) to cover a large range of pose, age and ethnicity; and (iii) to…
• BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
  30 Jan 2023 17 repositories listed Syntology ran 4 of 8 samples · 4 unverified · 1 pointer-only (licence)
  The cost of vision-and-language pre-training has become increasingly prohibitive due to end-to-end training of large-scale models.
• Circle Loss: A Unified Perspective of Pair Similarity Optimization
  25 Feb 2020 16 repositories listed Syntology ran 2 of 2 samples · 0 unverified · 1 pointer-only (licence)
  This paper provides a pair similarity optimization viewpoint on deep feature learning, aiming to maximize the within-class similarity sₚ and minimize the between-class similarity sₙ.
• Fine-tuning CNN Image Retrieval with No Human Annotation
  3 Nov 2017 14 repositories listed Syntology ran 3 of 24 samples · 21 unverified · 2 pointer-only (licence)
  We show that both hard-positive and hard-negative examples, selected by exploiting the geometry and the camera positions available from the 3D models, enhance the performance of particular-object retrieval.
• NetVLAD: CNN architecture for weakly supervised place recognition
  23 Nov 2015 14 repositories listed Syntology ran 0 of 12 samples · 12 unverified
  We tackle the problem of large scale visual place recognition, where the task is to quickly and accurately recognize the location of a given query photograph.
• Visual Instruction Tuning
  17 Apr 2023 13 repositories listed Syntology ran 16 of 51 samples · 35 unverified
  Instruction tuning large language models (LLMs) using machine-generated instruction-following data has improved zero-shot capabilities on new tasks, but the idea is less explored in the multimodal field.
• Large-Scale Image Retrieval with Attentive Deep Local Features
  19 Dec 2016 13 repositories listed Syntology ran 3 of 12 samples · 9 unverified
  We propose an attentive local feature descriptor suitable for large-scale image retrieval, referred to as DELF (DEep Local Feature).
• GPT-4 Technical Report
  15 Mar 2023 11 repositories listed Syntology ran 2 of 5 samples · 3 unverified · 1 pointer-only (licence)
  We report the development of GPT-4, a large-scale, multimodal model which can accept image and text inputs and produce text outputs.
• ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
  6 Aug 2019 11 repositories listed Syntology ran 10 of 34 samples · 24 unverified · 34 pointer-only (licence)
  We present ViLBERT (short for Vision-and-Language BERT), a model for learning task-agnostic joint representations of image content and natural language.
• VSE++: Improving Visual-Semantic Embeddings with Hard Negatives
  18 Jul 2017 10 repositories listed Syntology ran 2 of 5 samples · 3 unverified · 4 pointer-only (licence)
  We present a new technique for learning visual-semantic embeddings for cross-modal retrieval.
• Looking at Outfit to Parse Clothing
  4 Mar 2017 9 repositories listed
  This paper extends fully-convolutional neural networks (FCN) for the clothing parsing problem.
• Learning Deep Representations of Fine-grained Visual Descriptions
  17 May 2016 9 repositories listed
  State-of-the-art methods for zero-shot visual recognition formulate learning as a joint embedding problem of images and side information.
• Combination of Multiple Global Descriptors for Image Retrieval
  26 Mar 2019 7 repositories listed Syntology ran 0 of 5 samples · 5 unverified
  Recent studies in image retrieval task have shown that ensembling different models and combining multiple global descriptors lead to performance improvement.
• ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision
  5 Feb 2021 6 repositories listed Syntology ran 1 of 4 samples · 3 unverified · 1 pointer-only (licence)
  Vision-and-Language Pre-training (VLP) has improved performance on various joint vision-and-language downstream tasks.
• Stacked Cross Attention for Image-Text Matching
  21 Mar 2018 6 repositories listed Syntology ran 7 of 16 samples · 9 unverified · 1 pointer-only (licence)
  Prior work either simply aggregates the similarity of all possible pairs of regions and words without attending differentially to more and less important words or regions, or uses a multi-step attentional process to…
• Sampling Matters in Deep Embedding Learning
  23 Jun 2017 6 repositories listed Syntology ran 2 of 2 samples · 0 unverified
  In addition, we show that a simple margin based loss is sufficient to outperform all other loss functions.
• Particular object retrieval with integral max-pooling of CNN activations
  18 Nov 2015 6 repositories listed Syntology ran 0 of 4 samples · 4 unverified
  Recently, image representation built upon Convolutional Neural Network (CNN) has been shown to provide effective descriptors for image search, outperforming pre-CNN features as short-vector representations.
• DOLG: Single-Stage Image Retrieval with Deep Orthogonal Fusion of Local and Global Features
  6 Aug 2021 5 repositories listed Syntology ran 10 of 23 samples · 13 unverified
  Components orthogonal to the global image representation are then extracted from the local information.
• Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrieval
  3 Apr 2020 5 repositories listed
  GLDv2 is the largest such dataset to date by a large margin, including over 5M images and 200k distinct instance labels.
• DeepEMD: Differentiable Earth Mover's Distance for Few-Shot Learning
  15 Mar 2020 5 repositories listed Syntology ran 2 of 7 samples · 5 unverified
  We employ the Earth Mover's Distance (EMD) as a metric to compute a structural distance between dense image representations to determine image relevance.
• Unifying Deep Local and Global Features for Image Search
  14 Jan 2020 5 repositories listed
  Image retrieval is the problem of searching an image database for items that are similar to a query image.
• Cross-Batch Memory for Embedding Learning
  14 Dec 2019 5 repositories listed
  This suggests that the features of instances computed at preceding iterations can be used to considerably approximate their features extracted by the current model.
• 12-in-1: Multi-Task Vision and Language Representation Learning
  5 Dec 2019 5 repositories listed Syntology ran 4 of 20 samples · 16 unverified · 20 pointer-only (licence)
  Much of vision-and-language research focuses on a small but diverse set of independent tasks and supporting datasets often studied in isolation; however, the visually-grounded language understanding skills required for…
• Kornia: an Open Source Differentiable Computer Vision Library for PyTorch
  5 Oct 2019 5 repositories listed Syntology ran 0 of 20 samples · 20 unverified
  This work presents Kornia -- an open source computer vision library which consists of a set of differentiable routines and modules to solve generic computer vision problems.
• SoftTriple Loss: Deep Metric Learning Without Triplet Sampling
  11 Sep 2019 5 repositories listed Syntology ran 2 of 4 samples · 2 unverified · 2 pointer-only (licence)
  The set of triplet constraints has to be sampled within the mini-batch.
• Batch DropBlock Network for Person Re-identification and Beyond
  17 Nov 2018 5 repositories listed Syntology ran 3 of 12 samples · 9 unverified
  In this paper, we propose the Batch DropBlock (BDB) Network which is a two branch network composed of a conventional ResNet-50 as the global branch and a feature dropping branch.
• CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples
  8 Apr 2016 5 repositories listed Syntology ran 0 of 2 samples · 2 unverified · 2 pointer-only (licence)
  Convolutional Neural Networks (CNNs) achieve state-of-the-art performance in many computer vision tasks.
• Improving zero-shot learning by mitigating the hubness problem
  20 Dec 2014 5 repositories listed
  The zero-shot paradigm exploits vector-based word representations extracted from text corpora with unsupervised methods to learn general mapping functions from other feature spaces onto word space, where the words…

Syntology lines on 24 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.