Search Results for author: Zizheng Pan

Found 16 papers, 12 papers with code

MiniCache: KV Cache Compression in Depth Dimension for Large Language Models

no code implementations23 May 2024 Akide Liu, Jing Liu, Zizheng Pan, Yefei He, Gholamreza Haffari, Bohan Zhuang

In this paper, we present a simple yet effective approach, called MiniCache, to compress the KV cache across layers from a novel depth perspective, significantly reducing the memory footprint for LLM inference.


T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitching

1 code implementation21 Feb 2024 Zizheng Pan, Bohan Zhuang, De-An Huang, Weili Nie, Zhiding Yu, Chaowei Xiao, Jianfei Cai, Anima Anandkumar

Sampling from diffusion probabilistic models (DPMs) is often expensive for high-quality image generation and typically requires many steps with a large model.

Image Generation

Efficient Stitchable Task Adaptation

1 code implementation29 Nov 2023 Haoyu He, Zizheng Pan, Jing Liu, Jianfei Cai, Bohan Zhuang

In this work, we present a novel framework, Efficient Stitchable Task Adaptation (ESTA), to efficiently produce a palette of fine-tuned models that adhere to diverse resource constraints.


Stitched ViTs are Flexible Vision Backbones

1 code implementation30 Jun 2023 Zizheng Pan, Jing Liu, Haoyu He, Jianfei Cai, Bohan Zhuang

With extensive experiments on ImageNet-1K, ADE20K, COCO-Stuff-10K and NYUv2, SN-Netv2 demonstrates superior performance over SN-Netv1 on downstream dense predictions and shows strong ability as a flexible vision backbone, achieving great advantages in both training efficiency and deployment flexibility.

Stitchable Neural Networks

2 code implementations CVPR 2023 Zizheng Pan, Jianfei Cai, Bohan Zhuang

As each model family consists of pretrained models with diverse scales (e. g., DeiT-Ti/S/B), it naturally arises a fundamental question of how to efficiently assemble these readily available models in a family for dynamic accuracy-efficiency trade-offs at runtime.

Image Classification

A Survey on Efficient Training of Transformers

no code implementations2 Feb 2023 Bohan Zhuang, Jing Liu, Zizheng Pan, Haoyu He, Yuetian Weng, Chunhua Shen

Recent advances in Transformers have come with a huge requirement on computing resources, highlighting the importance of developing efficient training techniques to make Transformer training faster, at lower cost, and to higher accuracy by the efficient use of computation and memory resources.

EcoFormer: Energy-Saving Attention with Linear Complexity

1 code implementation19 Sep 2022 Jing Liu, Zizheng Pan, Haoyu He, Jianfei Cai, Bohan Zhuang

To this end, we propose a new binarization paradigm customized to high-dimensional softmax attention via kernelized hashing, called EcoFormer, to map the original queries and keys into low-dimensional binary codes in Hamming space.


An Efficient Spatio-Temporal Pyramid Transformer for Action Detection

no code implementations21 Jul 2022 Yuetian Weng, Zizheng Pan, Mingfei Han, Xiaojun Chang, Bohan Zhuang

The task of action detection aims at deducing both the action category and localization of the start and end moment for each action instance in a long, untrimmed video.

Action Detection Video Understanding

Fast Vision Transformers with HiLo Attention

5 code implementations26 May 2022 Zizheng Pan, Jianfei Cai, Bohan Zhuang

Therefore, we propose to disentangle the high/low frequency patterns in an attention layer by separating the heads into two groups, where one group encodes high frequencies via self-attention within each local window, and another group encodes low frequencies by performing global attention between the average-pooled low-frequency keys and values from each window and each query position in the input feature map.

Benchmarking Efficient ViTs +2

Dynamic Focus-aware Positional Queries for Semantic Segmentation

2 code implementations CVPR 2023 Haoyu He, Jianfei Cai, Zizheng Pan, Jing Liu, Jing Zhang, DaCheng Tao, Bohan Zhuang

In this paper, we propose a simple yet effective query design for semantic segmentation termed Dynamic Focus-aware Positional Queries (DFPQ), which dynamically generates positional queries conditioned on the cross-attention scores from the preceding decoder block and the positional encodings for the corresponding image features, simultaneously.

Decoder Semantic Segmentation

Mesa: A Memory-saving Training Framework for Transformers

3 code implementations22 Nov 2021 Zizheng Pan, Peng Chen, Haoyu He, Jing Liu, Jianfei Cai, Bohan Zhuang

While Transformers have delivered significant performance improvements, training such networks is extremely memory intensive owing to storing all intermediate activations that are needed for gradient computation during backpropagation, especially for long sequences.


Less is More: Pay Less Attention in Vision Transformers

2 code implementations29 May 2021 Zizheng Pan, Bohan Zhuang, Haoyu He, Jing Liu, Jianfei Cai

Transformers have become one of the dominant architectures in deep learning, particularly as a powerful alternative to convolutional neural networks (CNNs) in computer vision.

Image Classification Instance Segmentation +3

The Road to Know-Where: An Object-and-Room Informed Sequential BERT for Indoor Vision-Language Navigation

1 code implementation ICCV 2021 Yuankai Qi, Zizheng Pan, Yicong Hong, Ming-Hsuan Yang, Anton Van Den Hengel, Qi Wu

Vision-and-Language Navigation (VLN) requires an agent to find a path to a remote location on the basis of natural-language instructions and a set of photo-realistic panoramas.

Vision and Language Navigation Vision-Language Navigation

Scalable Vision Transformers with Hierarchical Pooling

2 code implementations ICCV 2021 Zizheng Pan, Bohan Zhuang, Jing Liu, Haoyu He, Jianfei Cai

However, the routine of the current ViT model is to maintain a full-length patch sequence during inference, which is redundant and lacks hierarchical representation.

Efficient ViTs

Object-and-Action Aware Model for Visual Language Navigation

no code implementations ECCV 2020 Yuankai Qi, Zizheng Pan, Shengping Zhang, Anton Van Den Hengel, Qi Wu

The first is object description (e. g., 'table', 'door'), each presenting as a tip for the agent to determine the next action by finding the item visible in the environment, and the second is action specification (e. g., 'go straight', 'turn left') which allows the robot to directly predict the next movements without relying on visual perceptions.

Object Vision and Language Navigation

Cannot find the paper you are looking for? You can Submit a new open access paper.