paper-with-me

홈 › Papers

Visual Words Meet BM25: Sparse Auto-Encoder Visual Word Scoring for Image Retrieval

2026-03-06 · Donghoon Han, Eunhwan Park, Seunghyeon Seo arxiv

Dense image retrieval is accurate but offers limited interpretability and attribution, and it can be compute-intensive at scale. We present \textbf{BM25-V}, which applies Okapi BM25 scoring to sparse visual-word activations from a Sparse Auto-Encoder (SAE) on Vision Transformer patch features. Across a large gallery, visual-word document frequencies are highly imbalanced and follow a Zipfian-like distribution, making BM25's inverse document frequency (IDF) weighting well suited for suppressing ubiquitous, low-information words and emphasizing rare, discriminative ones. BM25-V retrieves high-recall candidates via sparse inverted-index operations and serves as an efficient first-stage retriever for dense reranking. Across seven benchmarks, BM25-V achieves Recall@200 $\geq$ 0.993, enabling a two-stage pipeline that reranks only $K{=}200$ candidates per query and recovers near-dense accuracy within $0.2$\% on average. An SAE trained once on ImageNet-1K transfers zero-shot to seven fine-grained benchmarks without fine-tuning, and BM25-V retrieval decisions are attributable to specific visual words with quantified IDF contributions.

📄 PDF Abstract BibTeX arXiv:2603.05781

Code (0)

등록된 구현이 없습니다.

Tasks

Image Retrieval

Similar Papers 제목 키워드 기반

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words

2025-01-09 · Gouki Minegishi, Hiroki Furuta, Yusuke Iwasawa, Yutaka Matsuo

Sparse autoencoders (SAEs) have gained a lot of attention as a promising tool to improve the interpretability of large language models (LLMs) by mapping the complex superposition of polysemantic neurons into monosemantic…

R-MAE: Regions Meet Masked Autoencoders

2023-06-08 · Duy-Kien Nguyen, Vaibhav Aggarwal, Yanghao Li, Martin R. Oswald 외

In this work, we explore regions as a potential visual analogue of words for self-supervised image representation learning. Inspired by Masked Autoencoding (MAE), a generative pre-training baseline, we propose masked reg…

Contrastive LearningInteractive Segmentationobject-detectionObject Detection+2

TOP-SPIN: TOPic discovery via Sparse Principal component INterference

2013-11-04 · Martin Takáč, Selin Damla Ahipaşaoğlu, Ngai-Man Cheung, Peter Richtárik

We propose a novel topic discovery algorithm for unlabeled images based on the bag-of-words (BoW) framework. We first extract a dictionary of visual words and subsequently for each image compute a visual word occurrence …

Analyzing Visual Aircraft Representations with Sparse Autoencoders

2026-06-13 · Deepshik Sharma arxiv

Vision models can achieve strong performance on classification tasks, but the internal representations supporting their predictions are often difficult to interpret. This work investigates whether sparse autoencoders can…

VideoMAC: Video Masked Autoencoders Meet ConvNets

2024-02-29 · CVPR 2024 1 · Gensheng Pei, Tao Chen, Xiruo Jiang, Huafeng Liu 외

Recently, the advancement of self-supervised learning techniques, like masked autoencoders (MAE), has greatly influenced visual representation learning for images and videos. Nevertheless, it is worth noting that the pre…

Pose TrackingRepresentation LearningSelf-Supervised LearningSemantic Segmentation+2