Search

Recent advances in Large Language Models (LLMs) have catalyzed the development of Large Multimodal Models (LMMs). However, existing research primarily focuses on tuning language and image instructions, ignoring the critical pretraining phase where models learn to process textual and visual modalities jointly. In this paper, we propose a new pretraining paradigm for LMMs to enhance the visual comprehension capabilities of LLMs by introducing a novel cross-modal comprehension stage. Specifically, we design a dynamically learnable prompt token pool and employ the Hungarian algorithm to replace part of the original visual tokens with the most relevant prompt tokens. Then, we conceptualize visual tokens as analogous to a "foreign language" for the LLMs and propose a mixed attention mechanism with bidirectional visual attention and unidirectional textual attention to comprehensively enhance the understanding of visual tokens. Meanwhile, we integrate a detailed caption generation task, leveraging rich descriptions to further facilitate LLMs in understanding visual semantic information. After pretraining on 1.5 million publicly accessible data, we present a new foundation model called Croc. Experimental results demonstrate that Croc achieves new state-of-the-art performance on massive vision-language benchmarks. To support reproducibility and facilitate further research, we release the training code and pre-trained model weights at https://github.com/deepglint/Croc., Comment: 18 pages, 11 figures

Contrastive Language-Image Pre-training (CLIP) has achieved excellent performance over a wide range of tasks. However, the effectiveness of CLIP heavily relies on a substantial corpus of pre-training data, resulting in notable consumption of computational resources. Although knowledge distillation has been widely applied in single modality models, how to efficiently expand knowledge distillation to vision-language foundation models with extensive data remains relatively unexplored. In this paper, we introduce CLIP-CID, a novel distillation mechanism that effectively transfers knowledge from a large vision-language foundation model to a smaller model. We initially propose a simple but efficient image semantic balance method to reduce transfer learning bias and improve distillation efficiency. This method filters out 43.7% of image-text pairs from the LAION400M while maintaining superior performance. After that, we leverage cluster-instance discrimination to facilitate knowledge transfer from the teacher model to the student model, thereby empowering the student model to acquire a holistic semantic comprehension of the pre-training data. Experimental results demonstrate that CLIP-CID achieves state-of-the-art performance on various downstream tasks including linear probe and zero-shot classification., Comment: 11 pages,8 figures

Contrastive Language Image Pre-training (CLIP) has recently demonstrated success across various tasks due to superior feature representation empowered by image-text contrastive learning. However, the instance discrimination method used by CLIP can hardly encode the semantic structure of training data. To handle this limitation, cluster discrimination has been proposed through iterative cluster assignment and classification. Nevertheless, most cluster discrimination approaches only define a single pseudo-label for each image, neglecting multi-label signals in the image. In this paper, we propose a novel Multi-Label Cluster Discrimination method named MLCD to enhance representation learning. In the clustering step, we first cluster the large-scale LAION-400M dataset into one million centers based on off-the-shelf embedding features. Considering that natural images frequently contain multiple visual objects or attributes, we select the multiple closest centers as auxiliary class labels. In the discrimination step, we design a novel multi-label classification loss, which elegantly separates losses from positive classes and negative classes, and alleviates ambiguity on decision boundary. We validate the proposed multi-label cluster discrimination method with experiments on different scales of models and pre-training datasets. Experimental results show that our method achieves state-of-the-art performance on multiple downstream tasks including linear probe, zero-shot classification, and image-text retrieval., Comment: Accepted by ECCV2024

Recent 3D face reconstruction methods have made significant progress in shape estimation, but high-fidelity facial albedo reconstruction remains challenging. Existing methods depend on expensive light-stage captured data to learn facial albedo maps. However, a lack of diversity in subjects limits their ability to recover high-fidelity results. In this paper, we present a novel facial albedo reconstruction model, HiFiAlbedo, which recovers the albedo map directly from a single image without the need for captured albedo data. Our key insight is that the albedo map is the illumination invariant texture map, which enables us to use inexpensive texture data to derive an albedo estimation by eliminating illumination. To achieve this, we first collect large-scale ultra-high-resolution facial images and train a high-fidelity facial texture codebook. By using the FFHQ dataset and limited UV textures, we then fine-tune the encoder for texture reconstruction from the input image with adversarial supervision in both image and UV space. Finally, we train a cross-attention module and utilize group identity loss to learn the adaptation from facial texture to the albedo domain. Extensive experimentation has demonstrated that our method exhibits excellent generalizability and is capable of achieving high-fidelity results for in-the-wild facial albedo recovery. Our code, pre-trained weights, and training data will be made publicly available at https://hifialbedo.github.io/.

Contrastive Language-Image Pre-training (CLIP) has significantly improved performance in various vision-language tasks by expanding the dataset with image-text pairs obtained from websites. This paper further explores CLIP from the perspectives of data and model architecture. To address the prevalence of noisy data and enhance the quality of large-scale image-text data crawled from the internet, we introduce a diverse description generation framework that can leverage Large Language Models (LLMs) to synthesize and refine content from web-based texts, synthetic captions, and detection tags. Furthermore, we propose RWKV-CLIP, the first RWKV-driven vision-language representation learning model that combines the effective parallel training of transformers with the efficient inference of RNNs. Comprehensive experiments across various model scales and pre-training datasets demonstrate that RWKV-CLIP is a robust and efficient vision-language representation learner, it achieves state-of-the-art performance in several downstream tasks, including linear probe, zero-shot classification, and zero-shot image-text retrieval. To facilitate future research, the code and pre-trained models are released at https://github.com/deepglint/RWKV-CLIP, Comment: 14 pages, 10 figures, EMNLP2024 Main

To approximate sums of values in key-value data streams, sketches are widely used in databases and networking systems. They offer high-confidence approximations for any given key while ensuring low time and space overhead. While existing sketches are proficient in estimating individual keys, they struggle to maintain this high confidence across all keys collectively, an objective that is critically important in both algorithm theory and its practical applications. We propose ReliableSketch, the first to control the error of all keys to less than $\Lambda$ with a small failure probability $\Delta$, requiring only $O(1 + \Delta\ln\ln(\frac{N}{\Lambda}))$ amortized time and $O(\frac{N}{\Lambda} + \ln(\frac{1}{\Delta}))$ space. Furthermore, its simplicity makes it hardware-friendly, and we implement it on CPU servers, FPGAs, and programmable switches. Our experiments show that under the same small space, ReliableSketch not only keeps all keys' errors below $\Lambda$ but also achieves near-optimal throughput, outperforming competitors with thousands of uncontrolled estimations. We have made our source code publicly available.

This paper presents the winning solution for the 1st SkatingVerse Challenge. We propose a method that involves several steps. To begin, we leverage the DINO framework to extract the Region of Interest (ROI) and perform precise cropping of the raw video footage. Subsequently, we employ three distinct models, namely Unmasked Teacher, UniformerV2, and InfoGCN, to capture different aspects of the data. By ensembling the prediction results based on logits, our solution attains an impressive leaderboard score of 95.73%., Comment: 3 pages, 1st SkatingVerse Challenge, 18th IEEE International Conference on Automatic Face and Gesture Recognition workshop

Medical visual question answering (Med-VQA) aims to automate the prediction of correct answers for medical images and questions, thereby assisting physicians in reducing repetitive tasks and alleviating their workload. Existing approaches primarily focus on pre-training models using additional and comprehensive datasets, followed by fine-tuning to enhance performance in downstream tasks. However, there is also significant value in exploring existing models to extract clinically relevant information. In this paper, we propose the Latent Prompt Assist model (LaPA) for medical visual question answering. Firstly, we design a latent prompt generation module to generate the latent prompt with the constraint of the target answer. Subsequently, we propose a multi-modal fusion block with latent prompt fusion module that utilizes the latent prompt to extract clinical-relevant information from uni-modal and multi-modal features. Additionally, we introduce a prior knowledge fusion module to integrate the relationship between diseases and organs with the clinical-relevant information. Finally, we combine the final integrated information with image-language cross-modal information to predict the final answers. Experimental results on three publicly available Med-VQA datasets demonstrate that LaPA outperforms the state-of-the-art model ARL, achieving improvements of 1.83%, 0.63%, and 1.80% on VQA-RAD, SLAKE, and VQA-2019, respectively. The code is publicly available at https://github.com/GaryGuTC/LaPA_model., Comment: 10 pages, 4 figures, Accepted by CVPRW2024

Contrastive Language-Image Pre-training (CLIP) has significantly boosted the performance of various vision-language tasks by scaling up the dataset with image-text pairs collected from the web. However, the presence of intrinsic noise and unmatched image-text pairs in web data can potentially affect the performance of representation learning. To address this issue, we first utilize the OFA model to generate synthetic captions that focus on the image content. The generated captions contain complementary information that is beneficial for pre-training. Then, we propose an Adaptive Language-Image Pre-training (ALIP), a bi-path model that integrates supervision from both raw text and synthetic caption. As the core components of ALIP, the Language Consistency Gate (LCG) and Description Consistency Gate (DCG) dynamically adjust the weights of samples and image-text/caption pairs during the training process. Meanwhile, the adaptive contrastive loss can effectively reduce the impact of noise data and enhances the efficiency of pre-training data. We validate ALIP with experiments on different scales of models and pre-training datasets. Experiments results show that ALIP achieves state-of-the-art performance on multiple downstream tasks including zero-shot image-text retrieval and linear probe. To facilitate future research, the code and pre-trained models are released at https://github.com/deepglint/ALIP., Comment: 15pages, 10figures, ICCV2023

Modern image retrieval methods typically rely on fine-tuning pre-trained encoders to extract image-level descriptors. However, the most widely used models are pre-trained on ImageNet-1K with limited classes. The pre-trained feature representation is therefore not universal enough to generalize well to the diverse open-world classes. In this paper, we first cluster the large-scale LAION400M into one million pseudo classes based on the joint textual and visual features extracted by the CLIP model. Due to the confusion of label granularity, the automatically clustered dataset inevitably contains heavy inter-class conflict. To alleviate such conflict, we randomly select partial inter-class prototypes to construct the margin-based softmax loss. To further enhance the low-dimensional feature representation, we randomly select partial feature dimensions when calculating the similarities between embeddings and class-wise prototypes. The dual random partial selections are with respect to the class dimension and the feature dimension of the prototype matrix, making the classification conflict-robust and the feature embedding compact. Our method significantly outperforms state-of-the-art unsupervised and supervised image retrieval approaches on multiple benchmarks. The code and pre-trained models are released to facilitate future research https://github.com/deepglint/unicom., Comment: Accepted at ICLR2023

Flow-level network measurement is critical to many network applications. Among various measurement tasks, packet loss detection and heavy-hitter detection are two most important measurement tasks, which we call the two key tasks. In practice, the two key tasks are often required at the same time, but existing works seldom handle both tasks. In this paper, we design ChameleMon to support the two key tasks simultaneously. One key design/novelty of ChameleMon is to shift measurement attention as network state changes, through two dimensions of dynamics: 1) dynamically allocating memory between the two key tasks; 2) dynamically monitoring the flows of importance. To realize the key design, we propose a key technique, leveraging Fermat's little theorem to devise a flexible data structure, namely FermatSketch. FermatSketch is dividable, additive, and subtractive, supporting the two key tasks. We have fully implemented a ChameleMon prototype on a testbed with a Fat-tree topology. We conduct extensive experiments and the results show ChameleMon supports the two key tasks with low memory/bandwidth overhead, and more importantly, it can automatically shift measurement attention as network state changes., Comment: This is a preprint of ChameleMon: Shifting Measurement Attention as Network State Changes, to appear in SIGCOMM 2023

Inter-modal interaction plays an indispensable role in multimodal sentiment analysis. Due to different modalities sequences are usually non-alignment, how to integrate relevant information of each modality to learn fusion representations has been one of the central challenges in multimodal learning. In this paper, a Self-Adjusting Fusion Representation Learning Model (SA-FRLM) is proposed to learn robust crossmodal fusion representations directly from the unaligned text and audio sequences. Different from previous works, our model not only makes full use of the interaction between different modalities but also maximizes the protection of the unimodal characteristics. Specifically, we first employ a crossmodal alignment module to project different modalities features to the same dimension. The crossmodal collaboration attention is then adopted to model the inter-modal interaction between text and audio sequences and initialize the fusion representations. After that, as the core unit of the SA-FRLM, the crossmodal adjustment transformer is proposed to protect original unimodal characteristics. It can dynamically adapt the fusion representations by using single modal streams. We evaluate our approach on the public multimodal sentiment analysis datasets CMU-MOSI and CMU-MOSEI. The experiment results show that our model has significantly improved the performance of all the metrics on the unaligned text-audio sequences., Comment: 8 pages

Flow scheduling is crucial in data centers, as it directly influences user experience of applications. According to different assumptions and design goals, there are four typical flow scheduling problems/solutions: SRPT, LAS, Fair Queueing, and Deadline-Aware scheduling. When implementing these solutions in commodity switches with limited number of queues, they need to set static parameters by measuring traffic in advance, while optimal parameters vary across time and space. This paper proposes a generic framework, namely QCluster, to adapt all scheduling problems for limited number of queues. The key idea of QCluster is to cluster packets with similar weights/properties into the same queue. QCluster is implemented in Tofino switches, and can cluster packets at a speed of 3.2 Tbps. To the best of our knowledge, QCluster is the fastest clustering algorithm. Experimental results in testbed with programmable switches and ns-2 show that QCluster reduces the average flow completion time (FCT) for short flows up to 56.6%, and reduces the overall average FCT up to 21.7% over state-of-the-art. All the source code in ns-2 is available in Github without.

The massive spread of digital misinformation has been identified as a major global risk and has been alleged to influence elections and threaten democracies. Communication, cognitive, social, and computer scientists are engaged in efforts to study the complex causes for the viral diffusion of misinformation online and to develop solutions, while search and social media platforms are beginning to deploy countermeasures. With few exceptions, these efforts have been mainly informed by anecdotal evidence rather than systematic data. Here we analyze 14 million messages spreading 400 thousand articles on Twitter during and following the 2016 U.S. presidential campaign and election. We find evidence that social bots played a disproportionate role in amplifying low-credibility content. Accounts that actively spread articles from low-credibility sources are significantly more likely to be bots. Automated accounts are particularly active in amplifying content in the very early spreading moments, before an article goes viral. Bots also target users with many followers through replies and mentions. Humans are vulnerable to this manipulation, retweeting bots who post links to low-credibility content. Successful low-credibility sources are heavily supported by social bots. These results suggest that curbing social bots may be an effective strategy for mitigating the spread of online misinformation., Comment: 41 pages, 20 figures, 3 tables