Wenchao Zhang

Wenchao Zhang, Jiahe Tian, Runze He et al.

Recent text-to-image (T2I) generation models have advanced significantly, enabling the creation of high-fidelity images from textual prompts. However, existing evaluation benchmarks primarily focus on the explicit alignment between generated images and prompts, neglecting the alignment with real-world knowledge beyond prompts. To address this gap, we introduce Align Beyond Prompts (ABP), a comprehensive benchmark designed to measure the alignment of generated images with real-world knowledge that extends beyond the explicit user prompts. ABP comprises over 2,000 meticulously crafted prompts, covering real-world knowledge across six distinct scenarios. We further introduce ABPScore, a metric that utilizes existing Multimodal Large Language Models (MLLMs) to assess the alignment between generated images and world knowledge beyond prompts, which demonstrates strong correlations with human judgments. Through a comprehensive evaluation of 8 popular T2I models using ABP, we find that even state-of-the-art models, such as GPT-4o, face limitations in integrating simple real-world knowledge into generated images. To mitigate this issue, we introduce a training-free strategy within ABP, named Inference-Time Knowledge Injection (ITKI). By applying this strategy to optimize 200 challenging samples, we achieved an improvement of approximately 43% in ABPScore. The dataset and code are available in https://github.com/smile365317/ABP.

Cory Fan, Wenchao Zhang

In digital imaging, image demosaicing is a crucial first step which recovers the RGB information from a color filter array (CFA). Oftentimes, deep learning is utilized to perform image demosaicing. Given that most modern digital imaging applications occur on mobile platforms, applying deep learning to demosaicing requires lightweight and efficient networks. Isotropic networks, also known as residual-in-residual networks, have been often employed for image demosaicing and joint-demosaicing-and-denoising (JDD). Most demosaicing isotropic networks avoid spatial downsampling entirely, and thus are often prohibitively expensive computationally for mobile applications. Contrary to previous isotropic network designs, this paper claims that spatial downsampling to a signficant degree can improve the efficiency and performance of isotropic networks. To validate this claim, we design simple fully convolutional networks with and without downsampling using a mathematical architecture design technique adapted from DeepMAD, and find that downsampling improves empirical performance. Additionally, empirical testing of the downsampled variant, JD3Net, of our fully convolutional networks reveals strong empirical performance on a variety of image demosaicing and JDD tasks.

Tong Lu, Ke Xu, Zimo Zhang et al.

Reliable seizure detection in mouse models is essential for preclinical epilepsy research, yet manual review of synchronized video-EEG recordings is labor-intensive and single-modality systems fail for complementary reasons: video-based methods are easily confounded by benign behaviors, whereas EEG-based methods are vulnerable to ictal motion artifacts. We present EEGVFusion, a multimodal framework that combines self-supervised EEG representation learning, spatio-temporal video encoding, optimal-transport alignment, and bidirectional cross-attention to integrate neural and behavioral evidence. We also curate an expert-annotated dataset of synchronized EEG and video recordings comprising 93 sessions from 15 mice for training and evaluation. In the random-session split, EEGVFusion achieved a Balanced Accuracy of 0.9957 with perfect event sensitivity and an Event FAR of 0.6250 FP/h, indicating strong seizure detection performance with a low false-alarm burden. In a single held-out-subject evaluation with Subject 110 reserved for testing, EEGVFusion achieved a Balanced Accuracy of 0.9718 and reduced Event FAR from 2.7250 FP/h for the EEG-only counterpart to 0.4833 FP/h while preserving perfect event sensitivity. Targeted ablations further showed that EEG pre-training and OT alignment help reduce false alarms while preserving event sensitivity.

Xinyue Huang, Ziqi Lin, Fang Sun et al.

This paper presents a novel Retrieval-Augmented Generation (RAG) framework tailored for complex question answering tasks, addressing challenges in multi-hop reasoning and contextual understanding across lengthy documents. Built upon LLaMA 3, the framework integrates a dense retrieval module with advanced context fusion and multi-hop reasoning mechanisms, enabling more accurate and coherent response generation. A joint optimization strategy combining retrieval likelihood and generation cross-entropy improves the model's robustness and adaptability. Experimental results show that the proposed system outperforms existing retrieval-augmented and generative baselines, confirming its effectiveness in delivering precise, contextually grounded answers.

Wenchao Zhang, Chong Fu, Xiangshi Chang et al.

Modeling implicit feature interaction patterns is of significant importance to object detection tasks. However, in the two-stage detectors, due to the excessive use of hand-crafted components, it is very difficult to reason about the implicit relationship of the instance features. To tackle this problem, we analyze three different levels of feature interaction relationships, namely, the dependency relationship between the cropped local features and global features, the feature autocorrelation within the instance, and the cross-correlation relationship between the instances. To this end, we propose a more compact object detector head network (CODH), which can not only preserve global context information and condense the information density, but also allows instance-wise feature enhancement and relational reasoning in a larger matrix space. Without bells and whistles, our method can effectively improve the detection performance while significantly reducing the parameters of the model, e.g., with our method, the parameters of the head network is 0.6 times smaller than the state-of-the-art Cascade R-CNN, yet the performance boost is 1.3% on COCO test-dev. Without losing generality, we can also build a more lighter head network for other multi-stage detectors by assembling our method.

Wenchao Zhang, Chong Fu, Haoyu Xie et al.

RoIPool/RoIAlign is an indispensable process for the typical two-stage object detection algorithm, it is used to rescale the object proposal cropped from the feature pyramid to generate a fixed size feature map. However, these cropped feature maps of local receptive fields will heavily lose global context information. To tackle this problem, we propose a novel end-to-end trainable framework, called Global Context Aware (GCA) RCNN, aiming at assisting the neural network in strengthening the spatial correlation between the background and the foreground by fusing global context information. The core component of our GCA framework is a context aware mechanism, in which both global feature pyramid and attention strategies are used for feature extraction and feature refinement, respectively. Specifically, we leverage the dense connection to improve the information flow of the global context at different stages in the top-down process of FPN, and further use the attention mechanism to refine the global context at each level in the feature pyramid. In the end, we also present a lightweight version of our method, which only slightly increases model complexity and computational burden. Experimental results on COCO benchmark dataset demonstrate the significant advantages of our approach.

Wenchao Zhang, Chong Fu, Mai Zhu

The attributes of object contours has great significance for instance segmentation task. However, most of the current popular deep neural networks do not pay much attention to the object edge information. Inspired by the human annotation process when making instance segmentation datasets, in this paper, we propose Mask Point R-CNN aiming at promoting the neural network's attention to the object boundary. Specifically, we innovatively extend the original human keypoint detection task to the contour point detection of any object. Based on this analogy, we present an contour point detection auxiliary task to Mask R-CNN, which can boost the gradient flow between different tasks by effectively using feature fusion strategies and multi-task joint training. As a consequence, the model will be more sensitive to the edges of the object and can capture more geometric features. Quantitatively, the experimental results show that our approach outperforms vanilla Mask R-CNN by 3.8\% on Cityscapes dataset and 0.8\% on COCO dataset.