Haojun Jiang

Zanlin Ni, Yulin Wang, Jiangwei Yu et al. · tsinghua

Recent years have witnessed a remarkable success of large deep learning models. However, training these models is challenging due to high computational costs, painfully slow convergence, and overfitting issues. In this paper, we present Deep Incubation, a novel approach that enables the efficient and effective training of large models by dividing them into smaller sub-modules that can be trained separately and assembled seamlessly. A key challenge for implementing this idea is to ensure the compatibility of the independently trained sub-modules. To address this issue, we first introduce a global, shared meta model, which is leveraged to implicitly link all the modules together, and can be designed as an extremely small network with negligible computational overhead. Then we propose a module incubation algorithm, which trains each sub-module to replace the corresponding component of the meta model and accomplish a given learning task. Despite the simplicity, our approach effectively encourages each sub-module to be aware of its role in the target large model, such that the finally-learned sub-modules can collaborate with each other smoothly after being assembled. Empirically, our method outperforms end-to-end (E2E) training in terms of both final accuracy and training efficiency. For example, on top of ViT-Huge, it improves the accuracy by 2.7% on ImageNet or achieves similar performance with 4x less training time. Notably, the gains are significant for downstream tasks as well (e.g., object detection and image segmentation on COCO and ADE20K). Code is available at https://github.com/LeapLabTHU/Deep-Incubation.

Haojun Jiang, Yuanze Lin, Dongchen Han et al.

Visual grounding, i.e., localizing objects in images according to natural language queries, is an important topic in visual language understanding. The most effective approaches for this task are based on deep learning, which generally require expensive manually labeled image-query or patch-query pairs. To eliminate the heavy dependence on human annotations, we present a novel method, named Pseudo-Q, to automatically generate pseudo language queries for supervised training. Our method leverages an off-the-shelf object detector to identify visual objects from unlabeled images, and then language queries for these objects are obtained in an unsupervised fashion with a pseudo-query generation module. Then, we design a task-related query prompt module to specifically tailor generated pseudo language queries for visual grounding tasks. Further, in order to fully capture the contextual relationships between images and language queries, we develop a visual-language model equipped with multi-level cross-modality attention mechanism. Extensive experimental results demonstrate that our method has two notable benefits: (1) it can reduce human annotation costs significantly, e.g., 31% on RefCOCO without degrading original model's performance under the fully supervised setting, and (2) without bells and whistles, it achieves superior or comparable performance compared to state-of-the-art weakly-supervised visual grounding methods on all the five datasets we have experimented. Code is available at https://github.com/LeapLabTHU/Pseudo-Q.

Haojun Jiang, Jianke Zhang, Rui Huang et al. · tsinghua

Vision-language retrieval is an important multi-modal learning topic, where the goal is to retrieve the most relevant visual candidate for a given text query. Recently, pre-trained models, e.g., CLIP, show great potential on retrieval tasks. However, as pre-trained models are scaling up, fully fine-tuning them on donwstream retrieval datasets has a high risk of overfitting. Moreover, in practice, it would be costly to train and store a large model for each task. To overcome the above issues, we present a novel Cross-Modal Adapter for parameter-efficient transfer learning. Inspired by adapter-based methods, we adjust the pre-trained model with a few parameterization layers. However, there are two notable differences. First, our method is designed for the multi-modal domain. Secondly, it allows encoder-level implicit cross-modal interactions between vision and language encoders. Although surprisingly simple, our approach has three notable benefits: (1) reduces the vast majority of fine-tuned parameters, (2) saves training time, and (3) allows all the pre-trained parameters to be fixed, enabling the pre-trained model to be shared across datasets. Extensive experiments demonstrate that, without bells and whistles, our approach outperforms adapter-based methods on image-text retrieval datasets (MSCOCO, Flickr30K) and video-text retrieval datasets (MSR-VTT, DiDeMo, and ActivityNet).

Rui Huang, Xuran Pan, Henry Zheng et al.

Recent advancements in vision-language pre-training (e.g. CLIP) have shown that vision models can benefit from language supervision. While many models using language modality have achieved great success on 2D vision tasks, the joint representation learning of 3D point cloud with text remains under-explored due to the difficulty of 3D-Text data pair acquisition and the irregularity of 3D data structure. In this paper, we propose a novel Text4Point framework to construct language-guided 3D point cloud models. The key idea is utilizing 2D images as a bridge to connect the point cloud and the language modalities. The proposed Text4Point follows the pre-training and fine-tuning paradigm. During the pre-training stage, we establish the correspondence of images and point clouds based on the readily available RGB-D data and use contrastive learning to align the image and point cloud representations. Together with the well-aligned image and text features achieved by CLIP, the point cloud features are implicitly aligned with the text embeddings. Further, we propose a Text Querying Module to integrate language information into 3D representation learning by querying text embeddings with point cloud features. For fine-tuning, the model learns task-specific 3D representations under informative language guidance from the label set without 2D images. Extensive experiments demonstrate that our model shows consistent improvement on various downstream tasks, such as point cloud semantic segmentation, instance segmentation, and object detection. The code will be available here: https://github.com/LeapLabTHU/Text4Point

Haojun Jiang, Teng Wang, Zhenguo Sun et al.

Echocardiography is an essential medical technique for diagnosing cardiovascular diseases, but its high operational complexity has led to a shortage of trained professionals. To address this issue, we introduce a novel probe movement guidance algorithm that has the potential to be applied in guiding robotic systems or novices with probe pose adjustment for high-quality standard plane image acquisition.Cardiac ultrasound faces two major challenges: (1) the inherently complex structure of the heart, and (2) significant individual variations. Previous works have only learned the population-averaged structure of the heart rather than personalized cardiac structures, leading to a performance bottleneck. Clinically, we observe that sonographers dynamically adjust their interpretation of a patient's cardiac anatomy based on prior scanning sequences, consequently refining their scanning strategies. Inspired by this, we propose a novel sequence-aware self-supervised pre-training method. Specifically, our approach learns personalized three-dimensional cardiac structural features by predicting the masked-out image features and probe movement actions in a scanning sequence. We hypothesize that if the model can predict the missing content it has acquired a good understanding of personalized cardiac structure. Extensive experiments on a large-scale expert scanning dataset with 1.67 million samples demonstrate that our proposed sequence-aware paradigm can effectively reduce probe guidance errors compared to other advanced baseline methods.

Xukun Li, Yu Sun, Lei Zhang et al.

Bimanual dexterous manipulation relies on integrating multimodal inputs to perform complex real-world tasks. To address the challenges of effectively combining these modalities, we propose DECO, a decoupled multimodal diffusion transformer that disentangles vision, proprioception, and tactile signals through specialized conditioning pathways, enabling structured and controllable integration of multimodal inputs, with a lightweight adapter for parameter-efficient injection of additional signals. Alongside DECO, we release DECO-50 dataset for bimanual dexterous manipulation with tactile sensing, consisting of 50 hours of data and over 5M frames, collected via teleoperation on real dual-arm robots. We train DECO on DECO-50 and conduct extensive real-world evaluation with over 2,000 robot rollouts. Experimental results show that DECO achieves the best performance across all tasks, with a 72.25% average success rate and a 21% improvement over the baseline. Moreover, the tactile adapter brings an additional 10.25% average success rate across all tasks and a 20% gain on complex contact-rich tasks while tuning less than 10% of the model parameters.

Yang Yue, Yulin Wang, Haojun Jiang et al.

Echocardiography is crucial for cardiovascular disease detection but relies heavily on experienced sonographers. Echocardiography probe guidance systems, which provide real-time movement instructions for acquiring standard plane images, offer a promising solution for AI-assisted or fully autonomous scanning. However, developing effective machine learning models for this task remains challenging, as they must grasp heart anatomy and the intricate interplay between probe motion and visual signals. To address this, we present EchoWorld, a motion-aware world modeling framework for probe guidance that encodes anatomical knowledge and motion-induced visual dynamics, while effectively leveraging past visual-motion sequences to enhance guidance precision. EchoWorld employs a pre-training strategy inspired by world modeling principles, where the model predicts masked anatomical regions and simulates the visual outcomes of probe adjustments. Built upon this pre-trained model, we introduce a motion-aware attention mechanism in the fine-tuning stage that effectively integrates historical visual-motion data, enabling precise and adaptive probe guidance. Trained on more than one million ultrasound images from over 200 routine scans, EchoWorld effectively captures key echocardiographic knowledge, as validated by qualitative analysis. Moreover, our method significantly reduces guidance errors compared to existing visual backbones and guidance frameworks, excelling in both single-frame and sequential evaluation protocols. Code is available at https://github.com/LeapLabTHU/EchoWorld.

Yulin Wang, Yang Yue, Yang Yue et al. · tsinghua

Human vision is highly adaptive, efficiently sampling intricate environments by sequentially fixating on task-relevant regions. In contrast, prevailing machine vision models passively process entire scenes at once, resulting in excessive resource demands scaling with spatial-temporal input resolution and model size, yielding critical limitations impeding both future advancements and real-world application. Here we introduce AdaptiveNN, a general framework aiming to drive a paradigm shift from 'passive' to 'active, adaptive' vision models. AdaptiveNN formulates visual perception as a coarse-to-fine sequential decision-making process, progressively identifying and attending to regions pertinent to the task, incrementally combining information across fixations, and actively concluding observation when sufficient. We establish a theory integrating representation learning with self-rewarding reinforcement learning, enabling end-to-end training of the non-differentiable AdaptiveNN without additional supervision on fixation locations. We assess AdaptiveNN on 17 benchmarks spanning 9 tasks, including large-scale visual recognition, fine-grained discrimination, visual search, processing images from real driving and medical scenarios, language-driven embodied AI, and side-by-side comparisons with humans. AdaptiveNN achieves up to 28x inference cost reduction without sacrificing accuracy, flexibly adapts to varying task demands and resource budgets without retraining, and provides enhanced interpretability via its fixation patterns, demonstrating a promising avenue toward efficient, flexible, and interpretable computer vision. Furthermore, AdaptiveNN exhibits closely human-like perceptual behaviors in many cases, revealing its potential as a valuable tool for investigating visual cognition. Code is available at https://github.com/LeapLabTHU/AdaptiveNN.

Teng Wang, Haojun Jiang, Yuxuan Wang et al.

Echocardiography is a critical tool for detecting heart diseases. Recently, ultrasound foundation models have demonstrated remarkable capabilities in cardiac ultrasound image analysis. However, obtaining high-quality ultrasound images is a prerequisite for accurate diagnosis. Due to the exceptionally high operational difficulty of cardiac ultrasound, there is a shortage of highly skilled personnel, which hinders patients from receiving timely examination services. In this paper, we aim to adapt the medical knowledge learned by foundation models from vast datasets to the probe guidance task, which is designed to provide real-time operational recommendations for junior sonographers to acquire high-quality ultrasound images. Moreover, inspired by the practice where experts optimize action decisions based on past explorations, we meticulously design a parameter-efficient Vision-Action Adapter (VA-Adapter) to enable foundation model's image encoder to encode vision-action sequences, thereby enhancing guidance performance. With built-in sequential reasoning capabilities in a compact design, the VA-Adapter enables a pre-trained ultrasound foundation model to learn precise probe adjustment strategies by fine-tuning only a small subset of parameters. Extensive experiments demonstrate that the VA-Adapter can surpass strong probe guidance models. Our code will be released after acceptance.

Gao Huang, Yulin Wang, Kangchen Lv et al.

Spatial redundancy widely exists in visual recognition tasks, i.e., discriminative features in an image or video frame usually correspond to only a subset of pixels, while the remaining regions are irrelevant to the task at hand. Therefore, static models which process all the pixels with an equal amount of computation result in considerable redundancy in terms of time and space consumption. In this paper, we formulate the image recognition problem as a sequential coarse-to-fine feature learning process, mimicking the human visual system. Specifically, the proposed Glance and Focus Network (GFNet) first extracts a quick global representation of the input image at a low resolution scale, and then strategically attends to a series of salient (small) regions to learn finer features. The sequential process naturally facilitates adaptive inference at test time, as it can be terminated once the model is sufficiently confident about its prediction, avoiding further redundant computation. It is worth noting that the problem of locating discriminant regions in our model is formulated as a reinforcement learning task, thus requiring no additional manual annotations other than classification labels. GFNet is general and flexible as it is compatible with any off-the-shelf backbone models (such as MobileNets, EfficientNets and TSM), which can be conveniently deployed as the feature extractor. Extensive experiments on a variety of image classification and video recognition tasks and with various backbone models demonstrate the remarkable efficiency of our method. For example, it reduces the average latency of the highly efficient MobileNet-V3 on an iPhone XS Max by 1.3x without sacrificing accuracy. Code and pre-trained models are available at https://github.com/blackfeather-wang/GFNet-Pytorch.

Yulin Wang, Yang Yue, Yuanze Lin et al.

Recent works have shown that the computational efficiency of video recognition can be significantly improved by reducing the spatial redundancy. As a representative work, the adaptive focus method (AdaFocus) has achieved a favorable trade-off between accuracy and inference speed by dynamically identifying and attending to the informative regions in each video frame. However, AdaFocus requires a complicated three-stage training pipeline (involving reinforcement learning), leading to slow convergence and is unfriendly to practitioners. This work reformulates the training of AdaFocus as a simple one-stage algorithm by introducing a differentiable interpolation-based patch selection operation, enabling efficient end-to-end optimization. We further present an improved training scheme to address the issues introduced by the one-stage formulation, including the lack of supervision, input diversity and training stability. Moreover, a conditional-exit technique is proposed to perform temporal adaptive computation on top of AdaFocus without additional training. Extensive experiments on six benchmark datasets (i.e., ActivityNet, FCVID, Mini-Kinetics, Something-Something V1&V2, and Jester) demonstrate that our model significantly outperforms the original AdaFocus and other competitive baselines, while being considerably more simple and efficient to train. Code is available at https://github.com/LeapLabTHU/AdaFocusV2.

Yulin Wang, Zhaoxi Chen, Haojun Jiang et al.

In this paper, we explore the spatial redundancy in video recognition with the aim to improve the computational efficiency. It is observed that the most informative region in each frame of a video is usually a small image patch, which shifts smoothly across frames. Therefore, we model the patch localization problem as a sequential decision task, and propose a reinforcement learning based approach for efficient spatially adaptive video recognition (AdaFocus). In specific, a light-weighted ConvNet is first adopted to quickly process the full video sequence, whose features are used by a recurrent policy network to localize the most task-relevant regions. Then the selected patches are inferred by a high-capacity network for the final prediction. During offline inference, once the informative patch sequence has been generated, the bulk of computation can be done in parallel, and is efficient on modern GPU devices. In addition, we demonstrate that the proposed method can be easily extended by further considering the temporal redundancy, e.g., dynamically skipping less valuable frames. Extensive experiments on five benchmark datasets, i.e., ActivityNet, FCVID, Mini-Kinetics, Something-Something V1&V2, demonstrate that our method is significantly more efficient than the competitive baselines. Code is available at https://github.com/blackfeather-wang/AdaFocus.

Teng Wang, Haojun Jiang, Chenxi Li et al.

Echocardiography is critical for diagnosing cardiovascular diseases, yet the shortage of skilled sonographers hinders timely patient care, due to high operational difficulties. Consequently, research on automated probe navigation has significant clinical potential. To achieve robust navigation, it is essential to leverage historical scanning information, mimicking how experts rely on past feedback to adjust subsequent maneuvers. Practical scanning data collected from sonographers typically consists of noisy trajectories inherently generated through trial-and-error exploration. However, existing methods typically model this history as a sequential chain, forcing models to overfit these noisy paths, leading to performance degradation on long sequences. In this paper, we propose UltraStar, which reformulates probe navigation from path regression to anchor-based global localization. By establishing a Star Graph, UltraStar treats historical keyframes as spatial anchors connected directly to the current view, explicitly modeling geometric constraints for precise positioning. We further enhance the Star Graph with a semantic-aware sampling strategy that actively selects the representative landmarks from massive history logs, reducing redundancy for accurate anchoring. Extensive experiments on a dataset with over 1.31 million samples demonstrate that UltraStar outperforms baselines and scales better with longer input lengths, revealing a more effective topology for history modeling under noisy exploration.

Haojun Jiang, Jiawei Sun, Jie Li et al.

Graph representation learning (GRL) makes considerable progress recently, which encodes graphs with topological structures into low-dimensional embeddings. Meanwhile, the time-consuming and costly process of annotating graph labels manually prompts the growth of self-supervised learning (SSL) techniques. As a dominant approach of SSL, Contrastive learning (CL) learns discriminative representations by differentiating between positive and negative samples. However, when applied to graph data, it overemphasizes global patterns while neglecting local structures. To tackle the above issue, we propose \underline{Local}-aware \underline{G}raph \underline{C}ontrastive \underline{L}earning (\textbf{\methnametrim}), a self-supervised learning framework that supplementarily captures local graph information with masking-based modeling compared with vanilla contrastive learning. Extensive experiments validate the superiority of \methname against state-of-the-art methods, demonstrating its promise as a comprehensive graph representation learner.

Haojun Jiang, Meng Li, Zhenguo Sun et al.

The complex structure of the heart leads to significant challenges in echocardiography, especially in acquisition cardiac ultrasound images. Successful echocardiography requires a thorough understanding of the structures on the two-dimensional plane and the spatial relationships between planes in three-dimensional space. In this paper, we innovatively propose a large-scale self-supervised pre-training method to acquire a cardiac structure-aware world model. The core innovation lies in constructing a self-supervised task that requires structural inference by predicting masked structures on a 2D plane and imagining another plane based on pose transformation in 3D space. To support large-scale pre-training, we collected over 1.36 million echocardiograms from ten standard views, along with their 3D spatial poses. In the downstream probe guidance task, we demonstrate that our pre-trained model consistently reduces guidance errors across the ten most common standard views on the test set with 0.29 million samples from 74 routine clinical scans, indicating that structure-aware pre-training benefits the scanning.

Haojun Jiang, Zhenguo Sun, Ning Jia et al.

Echocardiography is the only technique capable of real-time imaging of the heart and is vital for diagnosing the majority of cardiac diseases. However, there is a severe shortage of experienced cardiac sonographers, due to the heart's complex structure and significant operational challenges. To mitigate this situation, we present a Cardiac Copilot system capable of providing real-time probe movement guidance to assist less experienced sonographers in conducting freehand echocardiography. This system can enable non-experts, especially in primary departments and medically underserved areas, to perform cardiac ultrasound examinations, potentially improving global healthcare delivery. The core innovation lies in proposing a data-driven world model, named Cardiac Dreamer, for representing cardiac spatial structures. This world model can provide structure features of any cardiac planes around the current probe position in the latent space, serving as an precise navigation map for autonomous plane localization. We train our model with real-world ultrasound data and corresponding probe motion from 110 routine clinical scans with 151K sample pairs by three certified sonographers. Evaluations on three standard planes with 37K sample pairs demonstrate that the world model can reduce navigation errors by up to 33\% and exhibit more stable performance.

Le Yang, Haojun Jiang, Ruojin Cai et al.

Reusing features in deep networks through dense connectivity is an effective way to achieve high computational efficiency. The recent proposed CondenseNet has shown that this mechanism can be further improved if redundant features are removed. In this paper, we propose an alternative approach named sparse feature reactivation (SFR), aiming at actively increasing the utility of features for reusing. In the proposed network, named CondenseNetV2, each layer can simultaneously learn to 1) selectively reuse a set of most important features from preceding layers; and 2) actively update a set of preceding features to increase their utility for later layers. Our experiments show that the proposed models achieve promising performance on image classification (ImageNet and CIFAR) and object detection (MS COCO) in terms of both theoretical efficiency and practical speed.