iLLaVA: An Image is Worth Fewer Than 1/3 Input Tokens in Large Multimodal Models

In this paper, we introduce iLLaVA, a simple method that can be seamlessly deployed upon current Large Vision-Language Models (LVLMs) to greatly increase the throughput with nearly lossless model performance, without a further requirement to train. iLLaVA achieves this by finding and gradually merging the redundant tokens with an accurate and fast algorithm, which can merge hundreds of tokens within only one step. While some previous methods have explored directly pruning or merging tokens in the inference stage to accelerate models, our method excels in both performance and throughput by two key designs. First, while most previous methods only try to save the computations of Large Language Models (LLMs), our method accelerates the forward pass of both image encoders and LLMs in LVLMs, which both occupy a significant part of time during inference. Second, our method recycles the beneficial information from the pruned tokens into existing tokens, which avoids directly dropping context tokens like previous methods to cause performance loss. iLLaVA can nearly 2$\times$ the throughput, and reduce the memory costs by half with only a 0.2\% - 0.5\% performance drop across models of different scales including 7B, 13B and 34B. On tasks across different domains including single-image, multi-images and videos, iLLaVA demonstrates strong generalizability with consistently promising efficiency. We finally offer abundant visualizations to show the merging processes of iLLaVA in each step, which show insights into the distribution of computing resources in LVLMs. Code is available at https://github.com/hulianyuyy/iLLaVA.

Conjunction Subspaces Test for Conformal and Selective Classification

In this paper, we present a new classifier, which integrates significance testing results over different random subspaces to yield consensus p-values for quantifying the uncertainty of classification decision. The null hypothesis is that the test sample has no association with the target class on a randomly chosen subspace, and hence the classification problem can be formulated as a problem of testing for the conjunction of hypotheses. The proposed classifier can be easily deployed for the purpose of conformal prediction and selective classification with reject and refine options by simply thresholding the consensus p-values. The theoretical analysis on the generalization error bound of the proposed classifier is provided and empirical studies on real data sets are conducted as well to demonstrate its effectiveness.

Deep Correlated Prompting for Visual Recognition with Missing Modalities

Large-scale multimodal models have shown excellent performance over a series of tasks powered by the large corpus of paired multimodal training data. Generally, they are always assumed to receive modality-complete inputs. However, this simple assumption may not always hold in the real world due to privacy constraints or collection difficulty, where models pretrained on modality-complete data easily demonstrate degraded performance on missing-modality cases. To handle this issue, we refer to prompt learning to adapt large pretrained multimodal models to handle missing-modality scenarios by regarding different missing cases as different types of input. Instead of only prepending independent prompts to the intermediate layers, we present to leverage the correlations between prompts and input features and excavate the relationships between different layers of prompts to carefully design the instructions. We also incorporate the complementary semantics of different modalities to guide the prompting design for each modality. Extensive experiments on three commonly-used datasets consistently demonstrate the superiority of our method compared to the previous approaches upon different missing scenarios. Plentiful ablations are further given to show the generalizability and reliability of our method upon different modality-missing ratios and types.

Pose-Guided Fine-Grained Sign Language Video Generation

Sign language videos are an important medium for spreading and learning sign language. However, most existing human image synthesis methods produce sign language images with details that are distorted, blurred, or structurally incorrect. They also produce sign language video frames with poor temporal consistency, with anomalies such as flickering and abrupt detail changes between the previous and next frames. To address these limitations, we propose a novel Pose-Guided Motion Model (PGMM) for generating fine-grained and motion-consistent sign language videos. Firstly, we propose a new Coarse Motion Module (CMM), which completes the deformation of features by optical flow warping, thus transfering the motion of coarse-grained structures without changing the appearance; Secondly, we propose a new Pose Fusion Module (PFM), which guides the modal fusion of RGB and pose features, thus completing the fine-grained generation. Finally, we design a new metric, Temporal Consistency Difference (TCD) to quantitatively assess the degree of temporal consistency of a video by comparing the difference between the frames of the reconstructed video and the previous and next frames of the target video. Extensive qualitative and quantitative experiments show that our method outperforms state-of-the-art methods in most benchmark tests, with visible improvements in details and temporal consistency.

Interpretable Clustering: A Survey

In recent years, much of the research on clustering algorithms has primarily focused on enhancing their accuracy and efficiency, frequently at the expense of interpretability. However, as these methods are increasingly being applied in high-stakes domains such as healthcare, finance, and autonomous systems, the need for transparent and interpretable clustering outcomes has become a critical concern. This is not only necessary for gaining user trust but also for satisfying the growing ethical and regulatory demands in these fields. Ensuring that decisions derived from clustering algorithms can be clearly understood and justified is now a fundamental requirement. To address this need, this paper provides a comprehensive and structured review of the current state of explainable clustering algorithms, identifying key criteria to distinguish between various methods. These insights can effectively assist researchers in making informed decisions about the most suitable explainable clustering methods for specific application contexts, while also promoting the development and adoption of clustering algorithms that are both efficient and transparent.

Interpretable Multi-View Clustering

Multi-view clustering has become a significant area of research, with numerous methods proposed over the past decades to enhance clustering accuracy. However, in many real-world applications, it is crucial to demonstrate a clear decision-making process-specifically, explaining why samples are assigned to particular clusters. Consequently, there remains a notable gap in developing interpretable methods for clustering multi-view data. To fill this crucial gap, we make the first attempt towards this direction by introducing an interpretable multi-view clustering framework. Our method begins by extracting embedded features from each view and generates pseudo-labels to guide the initial construction of the decision tree. Subsequently, it iteratively optimizes the feature representation for each view along with refining the interpretable decision tree. Experimental results on real datasets demonstrate that our method not only provides a transparent clustering process for multi-view data but also delivers performance comparable to state-of-the-art multi-view clustering methods. To the best of our knowledge, this is the first effort to design an interpretable clustering framework specifically for multi-view data, opening a new avenue in this field.

CorrNet+: Sign Language Recognition and Translation via Spatial-Temporal Correlation

In sign language, the conveyance of human body trajectories predominantly relies upon the coordinated movements of hands and facial expressions across successive frames. Despite the recent advancements of sign language understanding methods, they often solely focus on individual frames, inevitably overlooking the inter-frame correlations that are essential for effectively modeling human body trajectories. To address this limitation, this paper introduces a spatial-temporal correlation network, denoted as CorrNet+, which explicitly identifies body trajectories across multiple frames. In specific, CorrNet+ employs a correlation module and an identification module to build human body trajectories. Afterwards, a temporal attention module is followed to adaptively evaluate the contributions of different frames. The resultant features offer a holistic perspective on human body movements, facilitating a deeper understanding of sign language. As a unified model, CorrNet+ achieves new state-of-the-art performance on two extensive sign language understanding tasks, including continuous sign language recognition (CSLR) and sign language translation (SLT). Especially, CorrNet+ surpasses previous methods equipped with resource-intensive pose-estimation networks or pre-extracted heatmaps for hand and facial feature extraction. Compared with CorrNet, CorrNet+ achieves a significant performance boost across all benchmarks while halving the computational overhead. A comprehensive comparison with previous spatial-temporal reasoning methods verifies the superiority of CorrNet+. Code is available at https://github.com/hulianyuyy/CorrNet_Plus.

Improving Continuous Sign Language Recognition with Adapted Image Models

The increase of web-scale weakly labelled image-text pairs have greatly facilitated the development of large-scale vision-language models (e.g., CLIP), which have shown impressive generalization performance over a series of downstream tasks. However, the massive model size and scarcity of available data limit their applications to fine-tune the whole model in downstream tasks. Besides, fully fine-tuning the model easily forgets the generic essential knowledge acquired in the pretraining stage and overfits the downstream data. To enable high efficiency when adapting these large vision-language models (e.g., CLIP) to performing continuous sign language recognition (CSLR) while preserving their generalizability, we propose a novel strategy (AdaptSign). Especially, CLIP is adopted as the visual backbone to extract frame-wise features whose parameters are fixed, and a set of learnable modules are introduced to model spatial sign variations or capture temporal sign movements. The introduced additional modules are quite lightweight, only owning 3.2% extra computations with high efficiency. The generic knowledge acquired in the pretraining stage is well-preserved in the frozen CLIP backbone in this process. Extensive experiments show that despite being efficient, AdaptSign is able to demonstrate superior performance across a series of CSLR benchmarks including PHOENIX14, PHOENIX14-T, CSL-Daily and CSL compared to existing methods. Visualizations show that AdaptSign could learn to dynamically pay major attention to the informative spatial regions and cross-frame trajectories in sign videos.

Dynamic Spatial-Temporal Aggregation for Skeleton-Aware Sign Language Recognition

Skeleton-aware sign language recognition (SLR) has gained popularity due to its ability to remain unaffected by background information and its lower computational requirements. Current methods utilize spatial graph modules and temporal modules to capture spatial and temporal features, respectively. However, their spatial graph modules are typically built on fixed graph structures such as graph convolutional networks or a single learnable graph, which only partially explore joint relationships. Additionally, a simple temporal convolution kernel is used to capture temporal information, which may not fully capture the complex movement patterns of different signers. To overcome these limitations, we propose a new spatial architecture consisting of two concurrent branches, which build input-sensitive joint relationships and incorporates specific domain knowledge for recognition, respectively. These two branches are followed by an aggregation process to distinguishe important joint connections. We then propose a new temporal module to model multi-scale temporal information to capture complex human dynamics. Our method achieves state-of-the-art accuracy compared to previous skeleton-aware methods on four large-scale SLR benchmarks. Moreover, our method demonstrates superior accuracy compared to RGB-based methods in most cases while requiring much fewer computational resources, bringing better accuracy-computation trade-off. Code is available at https://github.com/hulianyuyy/DSTA-SLR.

COMMA: Co-Articulated Multi-Modal Learning

Pretrained large-scale vision-language models such as CLIP have demonstrated excellent generalizability over a series of downstream tasks. However, they are sensitive to the variation of input text prompts and need a selection of prompt templates to achieve satisfactory performance. Recently, various methods have been proposed to dynamically learn the prompts as the textual inputs to avoid the requirements of laboring hand-crafted prompt engineering in the fine-tuning process. We notice that these methods are suboptimal in two aspects. First, the prompts of the vision and language branches in these methods are usually separated or uni-directionally correlated. Thus, the prompts of both branches are not fully correlated and may not provide enough guidance to align the representations of both branches. Second, it's observed that most previous methods usually achieve better performance on seen classes but cause performance degeneration on unseen classes compared to CLIP. This is because the essential generic knowledge learned in the pretraining stage is partly forgotten in the fine-tuning process. In this paper, we propose Co-Articulated Multi-Modal Learning (COMMA) to handle the above limitations. Especially, our method considers prompts from both branches to generate the prompts to enhance the representation alignment of both branches. Besides, to alleviate forgetting about the essential knowledge, we minimize the feature discrepancy between the learned prompts and the embeddings of hand-crafted prompts in the pre-trained CLIP in the late transformer layers. We evaluate our method across three representative tasks of generalization to novel classes, new target datasets and unseen domain shifts. Experimental results demonstrate the superiority of our method by exhibiting a favorable performance boost upon all tasks with high efficiency.