Pith. sign in

REVIEW 5 cited by

Spreading vectors for similarity search

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1806.03198 v3 pith:3AMVYPD5 submitted 2018-06-08 stat.ML cs.LG

Spreading vectors for similarity search

classification stat.ML cs.LG
keywords dataquantizermethodsneuralproposequantizationquantizersstep
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Discretizing multi-dimensional data distributions is a fundamental step of modern indexing methods. State-of-the-art techniques learn parameters of quantizers on training data for optimal performance, thus adapting quantizers to the data. In this work, we propose to reverse this paradigm and adapt the data to the quantizer: we train a neural net which last layer forms a fixed parameter-free quantizer, such as pre-defined points of a hyper-sphere. As a proxy objective, we design and train a neural network that favors uniformity in the spherical latent space, while preserving the neighborhood structure after the mapping. We propose a new regularizer derived from the Kozachenko--Leonenko differential entropy estimator to enforce uniformity and combine it with a locality-aware triplet loss. Experiments show that our end-to-end approach outperforms most learned quantization methods, and is competitive with the state of the art on widely adopted benchmarks. Furthermore, we show that training without the quantization step results in almost no difference in accuracy, but yields a generic catalyzer that can be applied with any subsequent quantizer.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. A satellite foundation model for improved wealth monitoring

    cs.CY 2026-04 unverdicted novelty 7.0

    Tempov is a self-supervised satellite foundation model that predicts wealth levels and decadal changes at high resolution across Africa from Landsat imagery, outperforming baselines even with limited labels and genera...

  2. Expanding SPHERE-JEPA: A Family of Statistical Regularizers for the Hypersphere

    cs.LG 2026-06 unverdicted novelty 6.0

    Derives deterministic MMD, KSD, and KL objectives with rotationally invariant kernels on the hypersphere, yielding more stable SSL training and dataset-dependent geometry in learned representations.

  3. Self-supervised pretraining for an iterative image size agnostic vision transformer

    cs.CV 2026-04 unverdicted novelty 6.0

    A sequential-to-global SSL method based on DINO pretrains iterative foveal-inspired vision transformers to achieve competitive ImageNet-1K performance with constant compute regardless of input resolution.

  4. DoReMi: Bridging 3D Domains via Topology-Aware Domain-Representation Mixture of Experts

    cs.CV 2025-11 unverdicted novelty 6.0

    DoReMi uses self-supervised pre-training on topological and texture variations plus domain-aware experts with spatial-guided routing and entropy-controlled allocation to reach 80.1% mIoU on ScanNet and 77.2% mIoU on S3DIS.

  5. Resolution scaling governs DINOv3 transfer performance in chest radiograph classification

    cs.CV 2025-10 conditional novelty 5.0

    DINOv3 at 512x512 resolution with ConvNeXt-B outperforms prior initializations for adult chest X-ray classification but shows no benefit in pediatric cohorts or at 1024 resolution.