MQuant quantizes multimodal LLMs to W4A8 using per-modality static scales, token reordering, and Hadamard-outlier suppression, claiming near-floating-point accuracy and up to 30% latency reduction on five MLLMs.
PTQ4RIS: Post-Training Quantization for Referring Image Segmentation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Referring Image Segmentation (RIS), aims to segment the object referred by a given sentence in an image by understanding both visual and linguistic information. However, existing RIS methods tend to explore top-performance models, disregarding considerations for practical applications on resources-limited edge devices. This oversight poses a significant challenge for on-device RIS inference. To this end, we propose an effective and efficient post-training quantization framework termed PTQ4RIS. Specifically, we first conduct an in-depth analysis of the root causes of performance degradation in RIS model quantization and propose dual-region quantization (DRQ) and reorder-based outlier-retained quantization (RORQ) to address the quantization difficulties in visual and text encoders. Extensive experiments on three benchmarks with different bits settings (from 8 to 4 bits) demonstrates its superior performance. Importantly, we are the first PTQ method specifically designed for the RIS task, highlighting the feasibility of PTQ in RIS applications. Code and video are available at {https://github.com/gugu511yy/PTQ4RIS}.
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MQuant: Unleashing the Inference Potential of Multimodal Large Language Models via Full Static Quantization
MQuant quantizes multimodal LLMs to W4A8 using per-modality static scales, token reordering, and Hadamard-outlier suppression, claiming near-floating-point accuracy and up to 30% latency reduction on five MLLMs.