arXiv subjects

Jiajun Liu

Publications and source records attributed to Jiajun Liu.

At least 91 records · Page 5Linked to original sources

arXiv2024

GTP-ViT: Efficient Vision Transformers via Graph-based Token Propagation

Vision Transformers (ViTs) have revolutionized the field of computer vision, yet their deployments on resource-constrained devices remain challenging due to high computational demands. To expedite pre-trained ViTs, token pruning and token merging approaches have been developed, which aim at reducing the number of tokens involved in the computation. However, these methods still have some limitations, such as image information loss from pruned tokens and inefficiency in the token-matching process. In this paper, we introduce a novel Graph-based Token Propagation (GTP) method to resolve the challenge of balancing model efficiency and information preservation for efficient ViTs. Inspired by graph summarization algorithms, GTP meticulously propagates less significant tokens' information to spatially and semantically connected tokens that are of greater importance. Consequently, the remaining few tokens serve as a summarization of the entire token graph, allowing the method to reduce computational complexity while preserving essential information of eliminated tokens. Combined with an innovative token selection strategy, GTP can efficiently identify image tokens to be propagated. Extensive experiments have validated GTP's effectiveness, demonstrating both efficiency and performance improvements. Specifically, GTP decreases the computational complexity of both DeiT-S and DeiT-B by up to 26% with only a minimal 0.3% accuracy drop on ImageNet-1K without finetuning, and remarkably surpasses the state-of-the-art token merging method on various backbones at an even faster inference speed. The source code is available at https://github.com/Ackesnal/GTP-ViT.

cs.CV↗

arXiv2023

SegRefiner: Towards Model-Agnostic Segmentation Refinement with Discrete Diffusion Process

In this paper, we explore a principal way to enhance the quality of object masks produced by different segmentation models. We propose a model-agnostic solution called SegRefiner, which offers a novel perspective on this problem by interpreting segmentation refinement as a data generation process. As a result, the refinement process can be smoothly implemented through a series of denoising diffusion steps. Specifically, SegRefiner takes coarse masks as inputs and refines them using a discrete diffusion process. By predicting the label and corresponding states-transition probabilities for each pixel, SegRefiner progressively refines the noisy masks in a conditional denoising manner. To assess the effectiveness of SegRefiner, we conduct comprehensive experiments on various segmentation tasks, including semantic segmentation, instance segmentation, and dichotomous image segmentation. The results demonstrate the superiority of our SegRefiner from multiple aspects. Firstly, it consistently improves both the segmentation metrics and boundary metrics across different types of coarse masks. Secondly, it outperforms previous model-agnostic refinement methods by a significant margin. Lastly, it exhibits a strong capability to capture extremely fine details when refining high-resolution images. The source code and trained models are available at https://github.com/MengyuWang826/SegRefiner.

cs.CV↗

arXiv2023

No Token Left Behind: Efficient Vision Transformer via Dynamic Token Idling

Vision Transformers (ViTs) have demonstrated outstanding performance in computer vision tasks, yet their high computational complexity prevents their deployment in computing resource-constrained environments. Various token pruning techniques have been introduced to alleviate the high computational burden of ViTs by dynamically dropping image tokens. However, some undesirable pruning at early stages may result in permanent loss of image information in subsequent layers, consequently hindering model performance. To address this problem, we propose IdleViT, a dynamic token-idle-based method that achieves an excellent trade-off between performance and efficiency. Specifically, in each layer, IdleViT selects a subset of the image tokens to participate in computations while keeping the rest of the tokens idle and directly passing them to this layer's output. By allowing the idle tokens to be re-selected in the following layers, IdleViT mitigates the negative impact of improper pruning in the early stages. Furthermore, inspired by the normalized graph cut, we devise a token cut loss on the attention map as regularization to improve IdleViT's token selection ability. Our method is simple yet effective and can be extended to pyramid ViTs since no token is completely dropped. Extensive experimental results on various ViT architectures have shown that IdleViT can diminish the complexity of pretrained ViTs by up to 33\% with no more than 0.2\% accuracy decrease on ImageNet, after finetuning for only 30 epochs. Notably, when the keep ratio is 0.5, IdleViT outperforms the state-of-the-art EViT on DeiT-S by 0.5\% higher accuracy and even faster inference speed. The source code is available in the supplementary material.

cs.CV↗

arXiv2023

Understanding the Effects of Projectors in Knowledge Distillation

Conventionally, during the knowledge distillation process (e.g. feature distillation), an additional projector is often required to perform feature transformation due to the dimension mismatch between the teacher and the student networks. Interestingly, we discovered that even if the student and the teacher have the same feature dimensions, adding a projector still helps to improve the distillation performance. In addition, projectors even improve logit distillation if we add them to the architecture too. Inspired by these surprising findings and the general lack of understanding of the projectors in the knowledge distillation process from existing literature, this paper investigates the implicit role that projectors play but so far have been overlooked. Our empirical study shows that the student with a projector (1) obtains a better trade-off between the training accuracy and the testing accuracy compared to the student without a projector when it has the same feature dimensions as the teacher, (2) better preserves its similarity to the teacher beyond shallow and numeric resemblance, from the view of Centered Kernel Alignment (CKA), and (3) avoids being over-confident as the teacher does at the testing phase. Motivated by the positive effects of projectors, we propose a projector ensemble-based feature distillation method to further improve distillation performance. Despite the simplicity of the proposed strategy, empirical results from the evaluation of classification tasks on benchmark datasets demonstrate the superior classification performance of our method on a broad range of teacher-student pairs and verify from the aspects of CKA and model calibration that the student's features are of improved quality with the projector ensemble design.

cs.CV↗

arXiv2023

Plug n' Play: Channel Shuffle Module for Enhancing Tiny Vision Transformers

Vision Transformers (ViTs) have demonstrated remarkable performance in various computer vision tasks. However, the high computational complexity hinders ViTs' applicability on devices with limited memory and computing resources. Although certain investigations have delved into the fusion of convolutional layers with self-attention mechanisms to enhance the efficiency of ViTs, there remains a knowledge gap in constructing tiny yet effective ViTs solely based on the self-attention mechanism. Furthermore, the straightforward strategy of reducing the feature channels in a large but outperforming ViT often results in significant performance degradation despite improved efficiency. To address these challenges, we propose a novel channel shuffle module to improve tiny-size ViTs, showing the potential of pure self-attention models in environments with constrained computing resources. Inspired by the channel shuffle design in ShuffleNetV2 \cite{ma2018shufflenet}, our module expands the feature channels of a tiny ViT and partitions the channels into two groups: the \textit{Attended} and \textit{Idle} groups. Self-attention computations are exclusively employed on the designated \textit{Attended} group, followed by a channel shuffle operation that facilitates information exchange between the two groups. By incorporating our module into a tiny ViT, we can achieve superior performance while maintaining a comparable computational complexity to the vanilla model. Specifically, our proposed channel shuffle module consistently improves the top-1 accuracy on the ImageNet-1K dataset for various tiny ViT models by up to 2.8\%, with the changes in model complexity being less than 0.03 GMACs.

cs.CV↗

arXiv2023

Dynamic Token Pruning in Plain Vision Transformers for Semantic Segmentation

Vision transformers have achieved leading performance on various visual tasks yet still suffer from high computational complexity. The situation deteriorates in dense prediction tasks like semantic segmentation, as high-resolution inputs and outputs usually imply more tokens involved in computations. Directly removing the less attentive tokens has been discussed for the image classification task but can not be extended to semantic segmentation since a dense prediction is required for every patch. To this end, this work introduces a Dynamic Token Pruning (DToP) method based on the early exit of tokens for semantic segmentation. Motivated by the coarse-to-fine segmentation process by humans, we naturally split the widely adopted auxiliary-loss-based network architecture into several stages, where each auxiliary block grades every token's difficulty level. We can finalize the prediction of easy tokens in advance without completing the entire forward pass. Moreover, we keep $k$ highest confidence tokens for each semantic category to uphold the representative context information. Thus, computational complexity will change with the difficulty of the input, akin to the way humans do segmentation. Experiments suggest that the proposed DToP architecture reduces on average $20\% - 35\%$ of computational cost for current semantic segmentation methods based on plain vision transformers without accuracy degradation.

cs.CV↗

arXiv2023

Object Detection Difficulty: Suppressing Over-aggregation for Faster and Better Video Object Detection

Current video object detection (VOD) models often encounter issues with over-aggregation due to redundant aggregation strategies, which perform feature aggregation on every frame. This results in suboptimal performance and increased computational complexity. In this work, we propose an image-level Object Detection Difficulty (ODD) metric to quantify the difficulty of detecting objects in a given image. The derived ODD scores can be used in the VOD process to mitigate over-aggregation. Specifically, we train an ODD predictor as an auxiliary head of a still-image object detector to compute the ODD score for each image based on the discrepancies between detection results and ground-truth bounding boxes. The ODD score enhances the VOD system in two ways: 1) it enables the VOD system to select superior global reference frames, thereby improving overall accuracy; and 2) it serves as an indicator in the newly designed ODD Scheduler to eliminate the aggregation of frames that are easy to detect, thus accelerating the VOD process. Comprehensive experiments demonstrate that, when utilized for selecting global reference frames, ODD-VOD consistently enhances the accuracy of Global-frame-based VOD models. When employed for acceleration, ODD-VOD consistently improves the frames per second (FPS) by an average of 73.3% across 8 different VOD models without sacrificing accuracy. When combined, ODD-VOD attains state-of-the-art performance when competing with many VOD methods in both accuracy and speed. Our work represents a significant advancement towards making VOD more practical for real-world applications.

cs.CV↗

arXiv2023

OCHID-Fi: Occlusion-Robust Hand Pose Estimation in 3D via RF-Vision

Hand Pose Estimation (HPE) is crucial to many applications, but conventional cameras-based CM-HPE methods are completely subject to Line-of-Sight (LoS), as cameras cannot capture occluded objects. In this paper, we propose to exploit Radio-Frequency-Vision (RF-vision) capable of bypassing obstacles for achieving occluded HPE, and we introduce OCHID-Fi as the first RF-HPE method with 3D pose estimation capability. OCHID-Fi employs wideband RF sensors widely available on smart devices (e.g., iPhones) to probe 3D human hand pose and extract their skeletons behind obstacles. To overcome the challenge in labeling RF imaging given its human incomprehensible nature, OCHID-Fi employs a cross-modality and cross-domain training process. It uses a pre-trained CM-HPE network and a synchronized CM/RF dataset, to guide the training of its complex-valued RF-HPE network under LoS conditions. It further transfers knowledge learned from labeled LoS domain to unlabeled occluded domain via adversarial learning, enabling OCHID-Fi to generalize to unseen occluded scenarios. Experimental results demonstrate the superiority of OCHID-Fi: it achieves comparable accuracy to CM-HPE under normal conditions while maintaining such accuracy even in occluded scenarios, with empirical evidence for its generalizability to new domains.

cs.CV↗

arXiv2023

Global Knowledge Calibration for Fast Open-Vocabulary Segmentation

Recent advancements in pre-trained vision-language models, such as CLIP, have enabled the segmentation of arbitrary concepts solely from textual inputs, a process commonly referred to as open-vocabulary semantic segmentation (OVS). However, existing OVS techniques confront a fundamental challenge: the trained classifier tends to overfit on the base classes observed during training, resulting in suboptimal generalization performance to unseen classes. To mitigate this issue, recent studies have proposed the use of an additional frozen pre-trained CLIP for classification. Nonetheless, this approach incurs heavy computational overheads as the CLIP vision encoder must be repeatedly forward-passed for each mask, rendering it impractical for real-world applications. To address this challenge, our objective is to develop a fast OVS model that can perform comparably or better without the extra computational burden of the CLIP image encoder during inference. To this end, we propose a core idea of preserving the generalizable representation when fine-tuning on known classes. Specifically, we introduce a text diversification strategy that generates a set of synonyms for each training category, which prevents the learned representation from collapsing onto specific known category names. Additionally, we employ a text-guided knowledge distillation method to preserve the generalizable knowledge of CLIP. Extensive experiments demonstrate that our proposed model achieves robust generalization performance across various datasets. Furthermore, we perform a preliminary exploration of open-vocabulary video segmentation and present a benchmark that can facilitate future open-vocabulary research in the video domain.

cs.CV↗

arXiv2023

Decoupled Graph Neural Networks for Large Dynamic Graphs

Real-world graphs, such as social networks, financial transactions, and recommendation systems, often demonstrate dynamic behavior. This phenomenon, known as graph stream, involves the dynamic changes of nodes and the emergence and disappearance of edges. To effectively capture both the structural and temporal aspects of these dynamic graphs, dynamic graph neural networks have been developed. However, existing methods are usually tailored to process either continuous-time or discrete-time dynamic graphs, and cannot be generalized from one to the other. In this paper, we propose a decoupled graph neural network for large dynamic graphs, including a unified dynamic propagation that supports efficient computation for both continuous and discrete dynamic graphs. Since graph structure-related computations are only performed during the propagation process, the prediction process for the downstream task can be trained separately without expensive graph computations, and therefore any sequence model can be plugged-in and used. As a result, our algorithm achieves exceptional scalability and expressiveness. We evaluate our algorithm on seven real-world datasets of both continuous-time and discrete-time dynamic graphs. The experimental results demonstrate that our algorithm achieves state-of-the-art performance in both kinds of dynamic graphs. Most notably, the scalability of our algorithm is well illustrated by its successful application to large graphs with up to over a billion temporal edges and over a hundred million nodes.

cs.LG↗

arXiv2023

Improved Feature Distillation via Projector Ensemble

In knowledge distillation, previous feature distillation methods mainly focus on the design of loss functions and the selection of the distilled layers, while the effect of the feature projector between the student and the teacher remains under-explored. In this paper, we first discuss a plausible mechanism of the projector with empirical evidence and then propose a new feature distillation method based on a projector ensemble for further performance improvement. We observe that the student network benefits from a projector even if the feature dimensions of the student and the teacher are the same. Training a student backbone without a projector can be considered as a multi-task learning process, namely achieving discriminative feature extraction for classification and feature matching between the student and the teacher for distillation at the same time. We hypothesize and empirically verify that without a projector, the student network tends to overfit the teacher's feature distributions despite having different architecture and weights initialization. This leads to degradation on the quality of the student's deep features that are eventually used in classification. Adding a projector, on the other hand, disentangles the two learning tasks and helps the student network to focus better on the main feature extraction task while still being able to utilize teacher features as a guidance through the projector. Motivated by the positive effect of the projector in feature distillation, we propose an ensemble of projectors to further improve the quality of student features. Experimental results on different datasets with a series of teacher-student pairs illustrate the effectiveness of the proposed method.

cs.CV↗

arXiv2022

Point-Syn2Real: Semi-Supervised Synthetic-to-Real Cross-Domain Learning for Object Classification in 3D Point Clouds

Object classification using LiDAR 3D point cloud data is critical for modern applications such as autonomous driving. However, labeling point cloud data is labor-intensive as it requires human annotators to visualize and inspect the 3D data from different perspectives. In this paper, we propose a semi-supervised cross-domain learning approach that does not rely on manual annotations of point clouds and performs similar to fully-supervised approaches. We utilize available 3D object models to train classifiers that can generalize to real-world point clouds. We simulate the acquisition of point clouds by sampling 3D object models from multiple viewpoints and with arbitrary partial occlusions. We then augment the resulting set of point clouds through random rotations and adding Gaussian noise to better emulate the real-world scenarios. We then train point cloud encoding models, e.g., DGCNN, PointNet++, on the synthesized and augmented datasets and evaluate their cross-domain classification performance on corresponding real-world datasets. We also introduce Point-Syn2Real, a new benchmark dataset for cross-domain learning on point clouds. The results of our extensive experiments with this dataset demonstrate that the proposed cross-domain learning approach for point clouds outperforms the related baseline and state-of-the-art approaches in both indoor and outdoor settings in terms of cross-domain generalizability. The code and data will be available upon publishing.

cs.CV↗

arXiv2022

Multimodal sensor data fusion for in-situ classification of animal behavior using accelerometry and GNSS data

In this paper, we examine the use of data from multiple sensing modes, i.e., accelerometry and global navigation satellite system (GNSS), for classifying animal behavior. We extract three new features from the GNSS data, namely, distance from water point, median speed, and median estimated horizontal position error. We combine the information available from the accelerometry and GNSS data via two approaches. The first approach is based on concatenating the features extracted from both sensor data and feeding the concatenated feature vector into a multi-layer perceptron (MLP) classifier. The second approach is based on fusing the posterior probabilities predicted by two MLP classifiers. The input to each classifier is the features extracted from the data of one sensing mode. We evaluate the performance of the developed multimodal animal behavior classification algorithms using two real-world datasets collected via smart cattle collar tags and ear tags. The leave-one-animal-out cross-validation results show that both approaches improve the classification performance appreciably compared with using data of only one sensing mode. This is more notable for the infrequent but important behaviors of walking and drinking. The algorithms developed based on both approaches require little computational and memory resources hence are suitable for implementation on embedded systems of our collar tags and ear tags. However, the multimodal animal behavior classification algorithm based on posterior probability fusion is preferable to the one based on feature concatenation as it delivers better classification accuracy, has less computational and memory complexity, is more robust to sensor data failure, and enjoys better modularity.

cs.LG↗

arXiv2022

InvisibiliTee: Angle-agnostic Cloaking from Person-Tracking Systems with a Tee

After a survey for person-tracking system-induced privacy concerns, we propose a black-box adversarial attack method on state-of-the-art human detection models called InvisibiliTee. The method learns printable adversarial patterns for T-shirts that cloak wearers in the physical world in front of person-tracking systems. We design an angle-agnostic learning scheme which utilizes segmentation of the fashion dataset and a geometric warping process so the adversarial patterns generated are effective in fooling person detectors from all camera angles and for unseen black-box detection models. Empirical results in both digital and physical environments show that with the InvisibiliTee on, person-tracking systems' ability to detect the wearer drops significantly.

cs.CV↗

arXiv2022

STAR-GNN: Spatial-Temporal Video Representation for Content-based Retrieval

We propose a video feature representation learning framework called STAR-GNN, which applies a pluggable graph neural network component on a multi-scale lattice feature graph. The essence of STAR-GNN is to exploit both the temporal dynamics and spatial contents as well as visual connections between regions at different scales in the frames. It models a video with a lattice feature graph in which the nodes represent regions of different granularity, with weighted edges that represent the spatial and temporal links. The contextual nodes are aggregated simultaneously by graph neural networks with parameters trained with retrieval triplet loss. In the experiments, we show that STAR-GNN effectively implements a dynamic attention mechanism on video frame sequences, resulting in the emphasis for dynamic and semantically rich content in the video, and is robust to noise and redundancies. Empirical results show that STAR-GNN achieves state-of-the-art performance for Content-Based Video Retrieval.

cs.CV↗

arXiv2022

A Real-time Edge-AI System for Reef Surveys

Crown-of-Thorn Starfish (COTS) outbreaks are a major cause of coral loss on the Great Barrier Reef (GBR) and substantial surveillance and control programs are ongoing to manage COTS populations to ecologically sustainable levels. In this paper, we present a comprehensive real-time machine learning-based underwater data collection and curation system on edge devices for COTS monitoring. In particular, we leverage the power of deep learning-based object detection techniques, and propose a resource-efficient COTS detector that performs detection inferences on the edge device to assist marine experts with COTS identification during the data collection phase. The preliminary results show that several strategies for improving computational efficiency (e.g., batch-wise processing, frame skipping, model input size) can be combined to run the proposed detection model on edge hardware with low resource consumption and low information loss.

cs.LG↗

arXiv2022

Instant Graph Neural Networks for Dynamic Graphs

Graph Neural Networks (GNNs) have been widely used for modeling graph-structured data. With the development of numerous GNN variants, recent years have witnessed groundbreaking results in improving the scalability of GNNs to work on static graphs with millions of nodes. However, how to instantly represent continuous changes of large-scale dynamic graphs with GNNs is still an open problem. Existing dynamic GNNs focus on modeling the periodic evolution of graphs, often on a snapshot basis. Such methods suffer from two drawbacks: first, there is a substantial delay for the changes in the graph to be reflected in the graph representations, resulting in losses on the model's accuracy; second, repeatedly calculating the representation matrix on the entire graph in each snapshot is predominantly time-consuming and severely limits the scalability. In this paper, we propose Instant Graph Neural Network (InstantGNN), an incremental computation approach for the graph representation matrix of dynamic graphs. Set to work with dynamic graphs with the edge-arrival model, our method avoids time-consuming, repetitive computations and allows instant updates on the representation and instant predictions. Graphs with dynamic structures and dynamic attributes are both supported. The upper bounds of time complexity of those updates are also provided. Furthermore, our method provides an adaptive training strategy, which guides the model to retrain at moments when it can make the greatest performance gains. We conduct extensive experiments on several real-world and synthetic datasets. Empirical results demonstrate that our model achieves state-of-the-art accuracy while having orders-of-magnitude higher efficiency than existing methods.

cs.LG↗

arXiv2022

Spatiotemporal continuous estimates of daily 1-km PM2.5 from 2000 to present under the Tracking Air Pollution in China (TAP) framework

High spatial resolution PM2.5 data covering a long time period are urgently needed to support population exposure assessment and refined air quality management. In this study, we provided complete-coverage PM2.5 predictions with a 1-km spatial resolution from 2000 to the present under the Tracking Air Pollution in China (TAP, http://tapdata.org.cn/) framework. To support high spatial resolution modelling, we collected PM2.5 measurements from both national and local monitoring stations. To correctly reflect the temporal variations in land cover characteristics that affected the local variations in PM2.5, we constructed continuous annual geoinformation datasets, including the road maps and ensemble gridded population maps, in China from 2000 to 2021. We also examined various model structures and predictor combinations to balance the computational cost and model performance. The final model fused 10-km TAP PM2.5 predictions from our previous work, 1-km satellite aerosol optical depth retrievals and land use parameters with a random forest model. Our annual model had an out-of-bag R2 ranging between 0.80 and 0.84, and our hindcast model had a by-year cross-validation R2 of 0.76. This open-access 1-km resolution PM2.5 data product with complete coverage successfully revealed the local-scale spatial variations in PM2.5 and could benefit environmental studies and policy-making.

physics.ao-ph↗