Semantics-Preserving Quantization (SPQ), which gives more calibration weight to concept-sensitive parameters, preserves residual features, and corrects the mean error in video memory, is proposed.
Abstract
Segment Anything Model 3 (SAM 3) can segment objects from text prompts and track them across video, but its memory and computation costs make deployment difficult. Post-training quantization (PTQ) reduces these costs by using fewer bits. However, a quantized model can select the wrong object or lose track of its target across frames. We call this prompt-alignment drift. Controlled tests show that perturbing low-variance feature directions strongly affects target selection. We propose Semantics-Preserving Quantization (SPQ), which gives more calibration weight to concept-sensitive parameters, preserves residual features, and corrects the mean error in video memory. Fixed text concepts guide calibration without task annotations. All three components operate offline and add no inference operators. With a W4A8 image encoder, SPQ improves RefCOCO Pr@0.5 from 42.1 to 72.5 over PTQ4SAM while retaining 54.8 COCO mask AP. Experiments on LVIS, RefCOCO variants, and SA-V show consistent gains. A CLIP study also shows improved image-text retrieval.
G$^2$PTQ is presented, a unified PTQ framework with Generalized Gradient Compensation that integrates both first- and second-order information under a globally supervised, block-wise optimization objective and enables better alignment with the full-precision model, outperforming state-of-the-art baselines.
Rui-Kang Liu, Hao-Li Bai, Yuxuan Sun et al.· arXiv.org· 0 citations
HaRP-ViT (Hadamard Rotation for Post-Training Quantization of Vision Transformers), a training-free randomized Hadamard transform applied exclusively after the GELU activation is proposed, making the post-GELU tensor better suited to standard per-tensor uniform quantization.
Mustafa Ibrahim Aksu, F. Ş. Torun· 2026 11th International Conf...· 0 citations
Post-Training Quantization (PTQ) enables efficient deployment of Large Language Models (LLMs), yet activation outliers remain a key challenge for low-bit quantization. Existing global transformation methods overlook heterogeneous channel sensitivity to quantization noise, leading to suboptimal accuracy-efficiency trade...
De-Sheng Xu, Hang Li, Tian-Chen Song et al.· Conference on Empirical Meth...· 0 citations
Experiments on multiple LVLMs show that the Balanced Fitting method consistently outperforms prior PTQ approaches under both weight-only and weight-activation quantization, while lower reconstruction loss does not reliably translate into better downstream performance.
Min-Chan Kang, Kyeonghye Park, Seungyeon Sa et al.· arXiv.org· 0 citations
SPeaR (Steering Primitive for Realigning Representations) is introduced, which inserts lightweight learnable modules at stage boundaries and optimizes them directly from the test stream, requiring neither source data nor supervised warm-up.
Muhammad Sudipto Siam Dip, Ali Etemad· arXiv.org· 0 citations
Monocular depth estimation (MDE) has advanced rapidly with the emergence of foundation models such as Depth Anything. Their transformer-based architectures provide strong generalization across diverse scenes and domains, but also incur high computational and memory cost, making efficient deployment challenging. Post-Tr...
J. Choi, Jincheol Yang, Nahyun Lim et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.