18 citations · 26 across the 8 of their papers we have counts for
8 papers
1+1>2: A Synergistic Sparse and Low-Rank Compression Method for Large Language Models
Zeliang Zong, Kai Zhang, Zheyang Li +4
Large Language Models (LLMs) have demonstrated remarkable proficiency in language comprehension and generation; however, their widespread adoption is constrained by substantial ban…
Bridging Cross-task Protocol Inconsistency for Distillation in Dense Object Detection
Longrong Yang, Xianpan Zhou, Xuewei Li +5
Knowledge distillation (KD) has shown potential for learning compact models in dense object detection. However, the commonly used softmax-based distillation ignores the absolute cl…
Language Adaptive Weight Generation for Multi-task Visual Grounding
Wei Su, Peihan Miao, Huanzhang Dou +4
Although the impressive performance in visual grounding, the prevailing approaches usually exploit the visual backbone in a passive way, i.e., the visual backbone extracts features…
Understanding and Unifying Fourteen Attribution Methods with Taylor Interactions
Huiqi Deng, Na Zou, Mengnan Du +5
Various attribution methods have been developed to explain deep neural networks (DNNs) by inferring the attribution/importance/contribution score of each input variable to the fina…
Unified Normalization for Accelerating and Stabilizing Transformers
Qiming Yang, Kai Zhang, Chaoxiang Lan +5
Solid results from Transformers have made them prevailing architectures in various natural language and vision tasks. As a default component in Transformers, Layer Normalization (L…
Bidirectional Self-Training with Multiple Anisotropic Prototypes for Domain Adaptive Semantic Segmentation
Yulei Lu, Yawei Luo, Li Zhang +3
A thriving trend for domain adaptive segmentation endeavors to generate the high-quality pseudo labels for target domain and retrain the segmentor on them. Under this self-training…
UWC: Unit-wise Calibration Towards Rapid Network Compression
Chen Lin, Zheyang Li, Bo Peng +4
This paper introduces a post-training quantization~(PTQ) method achieving highly efficient Convolutional Neural Network~ (CNN) quantization with high performance. Previous PTQ meth…
Extreme Network Compression via Filter Group Approximation
Bo Peng, Wenming Tan, Zheyang Li +3
In this paper we propose a novel decomposition method based on filter group approximation, which can significantly reduce the redundancy of deep convolutional neural networks (CNNs…