Pith. sign in

REVIEW 1 cited by

CLAMP-ViT: Contrastive Data-Free Learning for Adaptive Post-Training Quantization of ViTs

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 2407.05266 v2 pith:Q2K5DHW7 submitted 2024-07-07 cs.CV cs.AIeess.IV

classification cs.CVcs.AIeess.IV
keywords quantizationclamp-vitcontrastivedatalearningaccuracydata-freegeneration
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

We present CLAMP-ViT, a data-free post-training quantization method for vision transformers (ViTs). We identify the limitations of recent techniques, notably their inability to leverage meaningful inter-patch relationships, leading to the generation of simplistic and semantically vague data, impacting quantization accuracy. CLAMP-ViT employs a two-stage approach, cyclically adapting between data generation and model quantization. Specifically, we incorporate a patch-level contrastive learning scheme to generate richer, semantically meaningful data. Furthermore, we leverage contrastive learning in layer-wise evolutionary search for fixed- and mixed-precision quantization to identify optimal quantization parameters while mitigating the effects of a non-smooth loss landscape. Extensive evaluations across various vision tasks demonstrate the superiority of CLAMP-ViT, with performance improvements of up to 3% in top-1 accuracy for classification, 0.6 mAP for object detection, and 1.5 mIoU for segmentation at similar or better compression ratio over existing alternatives. Code is available at https://github.com/georgia-tech-synergy-lab/CLAMP-ViT.git

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. AIRCHITECT v2: Learning the Hardware Accelerator Design Space through Unified Representations

    cs.LG 2025-01 conditional novelty 5.0 of 10

    Contrastive learning and a unified ordinal output let a transformer predict optimal accelerator hardware configurations for DNN workloads at constant time, with 91% accuracy on a MAESTRO-based dataset.

Pith tools