Haichao Zhang

Haichao Zhang, Kuangrong Hao, Witold Pedrycz et al.

Transformers exhibit great advantages in handling computer vision tasks. They model image classification tasks by utilizing a multi-head attention mechanism to process a series of patches consisting of split images. However, for complex tasks, Transformer in computer vision not only requires inheriting a bit of dynamic attention and global context, but also needs to introduce features concerning noise reduction, shifting, and scaling invariance of objects. Therefore, here we take a step forward to study the structural characteristics of Transformer and convolution and propose an architecture search method-Vision Transformer with Convolutions Architecture Search (VTCAS). The high-performance backbone network searched by VTCAS introduces the desirable features of convolutional neural networks into the Transformer architecture while maintaining the benefits of the multi-head attention mechanism. The searched block-based backbone network can extract feature maps at different scales. These features are compatible with a wider range of visual tasks, such as image classification (32 M parameters, 82.0% Top-1 accuracy on ImageNet-1K) and object detection (50.4% mAP on COCO2017). The proposed topology based on the multi-head attention mechanism and CNN adaptively associates relational features of pixels with multi-scale features of objects. It enhances the robustness of the neural network for object recognition, especially in the low illumination indoor scene.

Haichao Zhang, Yao Lu, Lichen Wang et al.

Video Large Language Models (VLLMs) unlock world-knowledge-aware video understanding through pretraining on internet-scale data and have already shown promise on tasks such as movie analysis and video question answering. However, deploying VLLMs for downstream tasks such as video recommendation remains challenging, since real systems require multi-video inputs, lightweight backbones, low-latency sequential inference, and rapid response. In practice, (1) decode-only generation yields high latency for sequential inference, (2) typical interfaces do not support multi-video inputs, and (3) constraining outputs to language discards fine-grained visual details that matter for downstream vision tasks. We argue that these limitations stem from the absence of a representation that preserves pixel-level detail while leveraging world knowledge. We present LinkedOut, a representation that extracts VLLM world knowledge directly from video to enable fast inference, supports multi-video histories, and removes the language bottleneck. LinkedOut extracts semantically grounded, knowledge-aware tokens from raw frames using VLLMs, guided by promptable queries and optional auxiliary modalities. We introduce a cross-layer knowledge fusion MoE that selects the appropriate level of abstraction from the rich VLLM features, enabling personalized, interpretable, and low-latency recommendation. To our knowledge, LinkedOut is the first VLLM-based video recommendation method that operates on raw frames without handcrafted labels, achieving state-of-the-art results on standard benchmarks. Interpretability studies and ablations confirm the benefits of layer diversity and layer-wise fusion, pointing to a practical path that fully leverages VLLM world-knowledge priors and visual reasoning for downstream vision tasks such as recommendation.

Haichao Zhang, Yi Xu, Yun Fu

Trajectory prediction is a critical task in computer vision and autonomous systems, playing a key role in autonomous driving, robotics, surveillance, and virtual reality. Existing methods often rely on complete and noise-free observational data, overlooking the challenges associated with out-of-sight objects and the inherent noise in sensor data caused by limited camera coverage, obstructions, and the absence of ground truth for denoised trajectories. These limitations pose safety risks and hinder reliable prediction in real-world scenarios. In this extended work, we present advancements in Out-of-Sight Trajectory (OST), a novel task that predicts the noise-free visual trajectories of out-of-sight objects using noisy sensor data. Building on our previous research, we broaden the scope of Out-of-Sight Trajectory Prediction (OOSTraj) to include pedestrians and vehicles, extending its applicability to autonomous driving, robotics, surveillance, and virtual reality. Our enhanced Vision-Positioning Denoising Module leverages camera calibration to establish a vision-positioning mapping, addressing the lack of visual references, while effectively denoising noisy sensor data in an unsupervised manner. Through extensive evaluations on the Vi-Fi and JRDB datasets, our approach achieves state-of-the-art performance in both trajectory denoising and prediction, significantly surpassing previous baselines. Additionally, we introduce comparisons with traditional denoising methods, such as Kalman filtering, and adapt recent trajectory prediction models to our task, providing a comprehensive benchmark. This work represents the first initiative to integrate vision-positioning projection for denoising noisy sensor trajectories of out-of-sight agents, paving the way for future advances. The code and preprocessed datasets are available at github.com/Hai-chao-Zhang/OST

Haichao Zhang, Haonan Yu, Le Zhao et al.

We present a low-cost legged mobile manipulation system that solves long-horizon real-world tasks, trained by reinforcement learning purely in simulation. This system is made possible by 1) a hierarchical design of a high-level policy for visual-mobile manipulation following task instructions, and a low-level quadruped locomotion policy, 2) a teacher and student training pipeline for the high level, which trains a teacher to tackle long-horizon tasks using privileged task decomposition and target object information, and further trains a student for visual-mobile manipulation via RL guided by the teacher's behavior, and 3) a suite of techniques for minimizing the sim-to-real gap. In contrast to many previous works that use high-end equipments, our system demonstrates effective performance with more accessible hardware -- specifically, a Unitree Go1 quadruped, a WidowX-250S arm, and a single wrist-mounted RGB camera -- despite the increased challenges of sim-to-real transfer. Trained fully in simulation, a single policy autonomously solves long-horizon tasks involving search, move to, grasp, transport, and drop into, achieving nearly 80% real-world success. This performance is comparable to that of expert human teleoperation on the same tasks while the robot is more efficient, operating at about 1.5x the speed of the teleoperation. Finally, we perform extensive ablations on key techniques for efficient RL training and effective sim-to-real transfer, and demonstrate effective deployment across diverse indoor and outdoor scenes under various lighting conditions.

Haichao Zhang, Kuangrong Hao, Lei Gao et al.

In recent years, neural architecture search (NAS) methods have been proposed for the automatic generation of task-oriented network architecture in image classification. However, the architectures obtained by existing NAS approaches are optimized only for classification performance and do not adapt to devices with limited computational resources. To address this challenge, we propose a neural network architecture search algorithm aiming to simultaneously improve network performance (e.g., classification accuracy) and reduce network complexity. The proposed framework automatically builds the network architecture at two stages: block-level search and network-level search. At the stage of block-level search, a relaxation method based on the gradient is proposed, using an enhanced gradient to design high-performance and low-complexity blocks. At the stage of network-level search, we apply an evolutionary multi-objective algorithm to complete the automatic design from blocks to the target network. The experiment results demonstrate that our method outperforms all evaluated hand-crafted networks in image classification, with an error rate of on CIFAR10 and an error rate of on CIFAR100, both at network parameter size less than one megabit. Moreover, compared with other neural architecture search methods, our method offers a tremendous reduction in designed network architecture parameters.

Haichao Zhang, Kuangrong Hao, Lei Gao et al.

Deep neural networks (DNNs) have achieved remarkable success in computer vision; however, training DNNs for satisfactory performance remains challenging and suffers from sensitivity to empirical selections of an optimization algorithm for training. Stochastic gradient descent (SGD) is dominant in training a DNN by adjusting neural network weights to minimize the DNNs loss function. As an alternative approach, neuroevolution is more in line with an evolutionary process and provides some key capabilities that are often unavailable in SGD, such as the heuristic black-box search strategy based on individual collaboration in neuroevolution. This paper proposes a novel approach that combines the merits of both neuroevolution and SGD, enabling evolutionary search, parallel exploration, and an effective probe for optimal DNNs. A hierarchical cluster-based suppression algorithm is also developed to overcome similar weight updates among individuals for improving population diversity. We implement the proposed approach in four representative DNNs based on four publicly-available datasets. Experiment results demonstrate that the four DNNs optimized by the proposed approach all outperform corresponding ones optimized by only SGD on all datasets. The performance of DNNs optimized by the proposed approach also outperforms state-of-the-art deep networks. This work also presents a meaningful attempt for pursuing artificial general intelligence.