Qihang Fan

Qihang Fan, Huaibo Huang, Mingrui Chen et al.

Vision Transformer (ViT) has gained increasing attention in the computer vision community in recent years. However, the core component of ViT, Self-Attention, lacks explicit spatial priors and bears a quadratic computational complexity, thereby constraining the applicability of ViT. To alleviate these issues, we draw inspiration from the recent Retentive Network (RetNet) in the field of NLP, and propose RMT, a strong vision backbone with explicit spatial prior for general purposes. Specifically, we extend the RetNet's temporal decay mechanism to the spatial domain, and propose a spatial decay matrix based on the Manhattan distance to introduce the explicit spatial prior to Self-Attention. Additionally, an attention decomposition form that adeptly adapts to explicit spatial prior is proposed, aiming to reduce the computational burden of modeling global information without disrupting the spatial decay matrix. Based on the spatial decay matrix and the attention decomposition form, we can flexibly integrate explicit spatial prior into the vision backbone with linear complexity. Extensive experiments demonstrate that RMT exhibits exceptional performance across various vision tasks. Specifically, without extra training data, RMT achieves **84.8%** and **86.1%** top-1 acc on ImageNet-1k with **27M/4.5GFLOPs** and **96M/18.2GFLOPs**. For downstream tasks, RMT achieves **54.5** box AP and **47.2** mask AP on the COCO detection task, and **52.8** mIoU on the ADE20K semantic segmentation task. Code is available at https://github.com/qhfan/RMT

Qihang Fan, Huaibo Huang, Jiyang Guan et al.

Vision Transformers (ViTs) have been shown to be effective in various vision tasks. However, resizing them to a mobile-friendly size leads to significant performance degradation. Therefore, developing lightweight vision transformers has become a crucial area of research. This paper introduces CloFormer, a lightweight vision transformer that leverages context-aware local enhancement. CloFormer explores the relationship between globally shared weights often used in vanilla convolutional operators and token-specific context-aware weights appearing in attention, then proposes an effective and straightforward module to capture high-frequency local information. In CloFormer, we introduce AttnConv, a convolution operator in attention's style. The proposed AttnConv uses shared weights to aggregate local information and deploys carefully designed context-aware weights to enhance local features. The combination of the AttnConv and vanilla attention which uses pooling to reduce FLOPs in CloFormer enables the model to perceive high-frequency and low-frequency information. Extensive experiments were conducted in image classification, object detection, and semantic segmentation, demonstrating the superiority of CloFormer. The code is available at \url{https://github.com/qhfan/CloFormer}.

Qihang Fan, Huaibo Huang, Xiaoqiang Zhou et al.

Recent advancements in vision backbones have significantly improved their performance by simultaneously modeling images' local and global contexts. However, the bidirectional interaction between these two contexts has not been well explored and exploited, which is important in the human visual system. This paper proposes a Fully Adaptive Self-Attention (FASA) mechanism for vision transformer to model the local and global information as well as the bidirectional interaction between them in context-aware ways. Specifically, FASA employs self-modulated convolutions to adaptively extract local representation while utilizing self-attention in down-sampled space to extract global representation. Subsequently, it conducts a bidirectional adaptation process between local and global representation to model their interaction. In addition, we introduce a fine-grained downsampling strategy to enhance the down-sampled self-attention mechanism for finer-grained global perception capability. Based on FASA, we develop a family of lightweight vision backbones, Fully Adaptive Transformer (FAT) family. Extensive experiments on multiple vision tasks demonstrate that FAT achieves impressive performance. Notably, FAT accomplishes a 77.6% accuracy on ImageNet-1K using only 4.5M parameters and 0.7G FLOPs, which surpasses the most advanced ConvNets and Transformers with similar model size and computational costs. Moreover, our model exhibits faster speed on modern GPU compared to other models. Code will be available at https://github.com/qhfan/FAT.

Xiaotian Han, Yiren Jian, Xuefeng Hu et al.

Pre-training on large-scale, high-quality datasets is crucial for enhancing the reasoning capabilities of Large Language Models (LLMs), especially in specialized domains such as mathematics. Despite the recognized importance, the Multimodal LLMs (MLLMs) field currently lacks a comprehensive open-source pre-training dataset specifically designed for mathematical reasoning. To address this gap, we introduce InfiMM-WebMath-40B, a high-quality dataset of interleaved image-text documents. It comprises 24 million web pages, 85 million associated image URLs, and 40 billion text tokens, all meticulously extracted and filtered from CommonCrawl. We provide a detailed overview of our data collection and processing pipeline. To demonstrate the robustness of InfiMM-WebMath-40B, we conducted evaluations in both text-only and multimodal settings. Our evaluations on text-only benchmarks show that, despite utilizing only 40 billion tokens, our dataset significantly enhances the performance of our 1.3B model, delivering results comparable to DeepSeekMath-1.3B, which uses 120 billion tokens for the same model size. Nevertheless, with the introduction of our multi-modal math pre-training dataset, our models set a new state-of-the-art among open-source models on multi-modal math benchmarks such as MathVerse and We-Math. We release our data at https://huggingface.co/datasets/Infi-MM/InfiMM-WebMath-40B.

Tingkai Liu, Yunzhe Tao, Haogeng Liu et al.

We present a novel human annotated dataset for evaluating the ability for visual-language models to generate both short and long descriptions for real-world video clips, termed DeVAn (Dense Video Annotation). The dataset contains 8.5K YouTube video clips of 20-60 seconds in duration and covers a wide range of topics and interests. Each video clip is independently annotated by 5 human annotators, producing both captions (1 sentence) and summaries (3-10 sentences). Given any video selected from the dataset and its corresponding ASR information, we evaluate visuallanguage models on either caption or summary generation that is grounded in both the visual and auditory content of the video. Additionally, models are also evaluated on caption- and summary-based retrieval tasks, where the summary-based retrieval task requires the identification of a target video given excerpts of a given summary. Given the novel nature of the paragraph-length video summarization task, we compared different existing evaluation metrics and their alignment with human preferences and found that model-based evaluation metrics provide more semantically-oriented and human-aligned evaluation. Finally, we benchmarked a wide range of current video-language models on DeVAn, and we aim for DeVAn to serve as a useful evaluation set in the age of large language models and complex multi-modal tasks. Code is available at https: //github.com/TK-21st/DeVAn.

Haogeng Liu, Qihang Fan, Tingkai Liu et al.

This paper proposes Video-Teller, a video-language foundation model that leverages multi-modal fusion and fine-grained modality alignment to significantly enhance the video-to-text generation task. Video-Teller boosts the training efficiency by utilizing frozen pretrained vision and language modules. It capitalizes on the robust linguistic capabilities of large language models, enabling the generation of both concise and elaborate video descriptions. To effectively integrate visual and auditory information, Video-Teller builds upon the image-based BLIP-2 model and introduces a cascaded Q-Former which fuses information across frames and ASR texts. To better guide video summarization, we introduce a fine-grained modality alignment objective, where the cascaded Q-Former's output embedding is trained to align with the caption/summary embedding created by a pretrained text auto-encoder. Experimental results demonstrate the efficacy of our proposed video-language foundation model in accurately comprehending videos and generating coherent and precise language descriptions. It is worth noting that the fine-grained alignment enhances the model's capabilities (4% improvement of CIDEr score on MSR-VTT) with only 13% extra parameters in training and zero additional cost in inference.

Qihang Fan, Huaibo Huang, Ran He

The Softmax attention mechanism in Transformer models is notoriously computationally expensive, particularly due to its quadratic complexity, posing significant challenges in vision applications. In contrast, linear attention provides a far more efficient solution by reducing the complexity to linear levels. However, compared to Softmax attention, linear attention often experiences significant performance degradation. Our experiments indicate that this performance drop is due to the low-rank nature of linear attention's feature map, which hinders its ability to adequately model complex spatial information. In this paper, to break the low-rank dilemma of linear attention, we conduct rank analysis from two perspectives: the KV buffer and the output features. Consequently, we introduce Rank-Augmented Linear Attention (RALA), which rivals the performance of Softmax attention while maintaining linear complexity and high efficiency. Based on RALA, we construct the Rank-Augmented Vision Linear Transformer (RAVLT). Extensive experiments demonstrate that RAVLT achieves excellent performance across various vision tasks. Specifically, without using any additional labels, data, or supervision during training, RAVLT achieves an 84.4% Top-1 accuracy on ImageNet-1k with only 26M parameters and 4.6G FLOPs. This result significantly surpasses previous linear attention mechanisms, fully illustrating the potential of RALA. Code will be available at https://github.com/qhfan/RALA.

Qihang Fan, Quanzeng You, Xiaotian Han et al.

This paper tackles a significant challenge faced by Vision Transformers (ViTs): their constrained scalability across different image resolutions. Typically, ViTs experience a performance decline when processing resolutions different from those seen during training. Our work introduces two key innovations to address this issue. Firstly, we propose a novel module for dynamic resolution adjustment, designed with a single Transformer block, specifically to achieve highly efficient incremental token integration. Secondly, we introduce fuzzy positional encoding in the Vision Transformer to provide consistent positional awareness across multiple resolutions, thereby preventing overfitting to any single training resolution. Our resulting model, ViTAR (Vision Transformer with Any Resolution), demonstrates impressive adaptability, achieving 83.3\% top-1 accuracy at a 1120x1120 resolution and 80.4\% accuracy at a 4032x4032 resolution, all while reducing computational costs. ViTAR also shows strong performance in downstream tasks such as instance and semantic segmentation and can easily combined with self-supervised learning techniques like Masked AutoEncoder. Our work provides a cost-effective solution for enhancing the resolution scalability of ViTs, paving the way for more versatile and efficient high-resolution image processing.

Yuguang Zhang, Qihang Fan, Huaibo Huang

In recent years, Transformers have achieved remarkable progress in computer vision tasks. However, their global modeling often comes with substantial computational overhead, in stark contrast to the human eye's efficient information processing. Inspired by the human eye's sparse scanning mechanism, we propose a \textbf{S}parse \textbf{S}can \textbf{S}elf-\textbf{A}ttention mechanism ($\rm{S}^3\rm{A}$). This mechanism predefines a series of Anchors of Interest for each token and employs local attention to efficiently model the spatial information around these anchors, avoiding redundant global modeling and excessive focus on local information. This approach mirrors the human eye's functionality and significantly reduces the computational load of vision models. Building on $\rm{S}^3\rm{A}$, we introduce the \textbf{S}parse \textbf{S}can \textbf{Vi}sion \textbf{T}ransformer (SSViT). Extensive experiments demonstrate the outstanding performance of SSViT across a variety of tasks. Specifically, on ImageNet classification, without additional supervision or training data, SSViT achieves top-1 accuracies of \textbf{84.4\%/85.7\%} with \textbf{4.4G/18.2G} FLOPs. SSViT also excels in downstream tasks such as object detection, instance segmentation, and semantic segmentation. Its robustness is further validated across diverse datasets.

Yuang Ai, Huaibo Huang, Tao Wu et al.

Transformer-based models have made remarkable progress in image restoration (IR) tasks. However, the quadratic complexity of self-attention in Transformer hinders its applicability to high-resolution images. Existing methods mitigate this issue with sparse or window-based attention, yet inherently limit global context modeling. Linear attention, a variant of softmax attention, demonstrates promise in global context modeling while maintaining linear complexity, offering a potential solution to the above challenge. Despite its efficiency benefits, vanilla linear attention suffers from a significant performance drop in IR, largely due to the low-rank nature of its attention map. To counter this, we propose Rank Enhanced Linear Attention (RELA), a simple yet effective method that enriches feature representations by integrating a lightweight depthwise convolution. Building upon RELA, we propose an efficient and effective image restoration Transformer, named LAformer. LAformer achieves effective global perception by integrating linear attention and channel attention, while also enhancing local fitting capabilities through a convolutional gated feed-forward network. Notably, LAformer eliminates hardware-inefficient operations such as softmax and window shifting, enabling efficient processing of high-resolution images. Extensive experiments across 7 IR tasks and 21 benchmarks demonstrate that LAformer outperforms SOTA methods and offers significant computational advantages.

Qihang Fan, Huaibo Huang, Mingrui Chen et al.

The Vision Transformer (ViT) has gained prominence for its superior relational modeling prowess. However, its global attention mechanism's quadratic complexity poses substantial computational burdens. A common remedy spatially groups tokens for self-attention, reducing computational requirements. Nonetheless, this strategy neglects semantic information in tokens, possibly scattering semantically-linked tokens across distinct groups, thus compromising the efficacy of self-attention intended for modeling inter-token dependencies. Motivated by these insights, we introduce a fast and balanced clustering method, named Semantic Equitable Clustering (SEC). SEC clusters tokens based on their global semantic relevance in an efficient, straightforward manner. In contrast to traditional clustering methods requiring multiple iterations, our method achieves token clustering in a single pass. Additionally, SEC regulates the number of tokens per cluster, ensuring a balanced distribution for effective parallel processing on current computational platforms without necessitating further optimization. Capitalizing on SEC, we propose a versatile vision backbone, SECViT. Comprehensive experiments in image classification, object detection, instance segmentation, and semantic segmentation validate the effectiveness of SECViT. Moreover, SEC can be conveniently and swiftly applied to multimodal large language models (MLLM), such as LLaVA, to serve as a vision language connector, effectively accelerating the model's efficiency while maintaining unchanged or better performance.