Ke Zhang

Xuefeng Hu, Ke Zhang, Lu Xia et al.

Large-scale Pre-Training Vision-Language Model such as CLIP has demonstrated outstanding performance in zero-shot classification, e.g. achieving 76.3% top-1 accuracy on ImageNet without seeing any example, which leads to potential benefits to many tasks that have no labeled data. However, while applying CLIP to a downstream target domain, the presence of visual and text domain gaps and cross-modality misalignment can greatly impact the model performance. To address such challenges, we propose ReCLIP, the first source-free domain adaptation method for vision-language models, which does not require any source data or target labeled data. ReCLIP first learns a projection space to mitigate the misaligned visual-text embeddings and learns pseudo labels, and then deploys cross-modality self-training with the pseudo labels, to update visual and text encoders, refine labels and reduce domain gaps and misalignments iteratively. With extensive experiments, we demonstrate ReCLIP reduces the average error rate of CLIP from 30.17% to 25.06% on 22 image classification benchmarks. Code available at https://github.com/michiganleon/ReCLIP_WACV.

Jiale Xu, Rui Zhang, Cong Guo et al.

Large Language Models (LLMs) are widely used across various domains, processing millions of daily requests. This surge in demand poses significant challenges in optimizing throughput and latency while keeping costs manageable. The Key-Value (KV) cache, a standard method for retaining previous computations, makes LLM inference highly bounded by memory. While batching strategies can enhance performance, they frequently lead to significant memory fragmentation. Even though cutting-edge systems like vLLM mitigate KV cache fragmentation using paged Attention mechanisms, they still suffer from inefficient memory and computational operations due to the tightly coupled page management and computation kernels. This study introduces the vTensor, an innovative tensor structure for LLM inference based on GPU virtual memory management (VMM). vTensor addresses existing limitations by decoupling computation from memory defragmentation and offering dynamic extensibility. Our framework employs a CPU-GPU heterogeneous approach, ensuring efficient, fragmentation-free memory management while accommodating various computation kernels across different LLM architectures. Experimental results indicate that vTensor achieves an average speedup of 1.86x across different models, with up to 2.42x in multi-turn chat scenarios. Additionally, vTensor provides average speedups of 2.12x and 3.15x in kernel evaluation, reaching up to 3.92x and 3.27x compared to SGLang Triton prefix-prefilling kernels and vLLM paged Attention kernel, respectively. Furthermore, it frees approximately 71.25% (57GB) of memory on the NVIDIA A100 GPU compared to vLLM, enabling more memory-intensive workloads.

Jinming Su, Chao Chen, Ke Zhang et al.

Recently, lane detection has made great progress with the rapid development of deep neural networks and autonomous driving. However, there exist three mainly problems including characterizing lanes, modeling the structural relationship between scenes and lanes, and supporting more attributes (e.g., instance and type) of lanes. In this paper, we propose a novel structure guided framework to solve these problems simultaneously. In the framework, we first introduce a new lane representation to characterize each instance. Then a topdown vanishing point guided anchoring mechanism is proposed to produce intensive anchors, which efficiently capture various lanes. Next, multi-level structural constraints are used to improve the perception of lanes. In the process, pixel-level perception with binary segmentation is introduced to promote features around anchors and restore lane details from bottom up, a lane-level relation is put forward to model structures (i.e., parallel) around lanes, and an image-level attention is used to adaptively attend different regions of the image from the perspective of scenes. With the help of structural guidance, anchors are effectively classified and regressed to obtain precise locations and shapes. Extensive experiments on public benchmark datasets show that the proposed approach outperforms state-of-the-art methods with 117 FPS on a single GPU.

Eleftheria Briakou, Di Lu, Ke Zhang et al.

We take the first step towards multilingual style transfer by creating and releasing XFORMAL, a benchmark of multiple formal reformulations of informal text in Brazilian Portuguese, French, and Italian. Results on XFORMAL suggest that state-of-the-art style transfer approaches perform close to simple baselines, indicating that style transfer is even more challenging when moving multilingual.

Ke Zhang, Yukun Su, Xiwang Guo et al.

Facial attribute editing has mainly two objectives: 1) translating image from a source domain to a target one, and 2) only changing the facial regions related to a target attribute and preserving the attribute-excluding details. In this work, we propose a Multi-attention U-Net-based Generative Adversarial Network (MU-GAN). First, we replace a classic convolutional encoder-decoder with a symmetric U-Net-like structure in a generator, and then apply an additive attention mechanism to build attention-based U-Net connections for adaptively transferring encoder representations to complement a decoder with attribute-excluding detail and enhance attribute editing ability. Second, a self-attention mechanism is incorporated into convolutional layers for modeling long-range and multi-level dependencies across image regions. experimental results indicate that our method is capable of balancing attribute editing ability and details preservation ability, and can decouple the correlation among attributes. It outperforms the state-of-the-art methods in terms of attribute manipulation accuracy and image quality.

Zhenbing Zhao, Hongyu Qi, Yincheng Qi et al.

Bolts are the most numerous fasteners in transmission lines and are prone to losing their split pins. How to realize the automatic pin-missing defect detection for bolts in transmission lines so as to achieve timely and efficient trouble shooting is a difficult problem and the long-term research target of power systems. In this paper, an automatic detection model called Automatic Visual Shape Clustering Network (AVSCNet) for pin-missing defect is constructed. Firstly, an unsupervised clustering method for the visual shapes of bolts is proposed and applied to construct a defect detection model which can learn the difference of visual shape. Next, three deep convolutional neural network optimization methods are used in the model: the feature enhancement, feature fusion and region feature extraction. The defect detection results are obtained by applying the regression calculation and classification to the regional features. In this paper, the object detection model of different networks is used to test the dataset of pin-missing defect constructed by the aerial images of transmission lines from multiple locations, and it is evaluated by various indicators and is fully verified. The results show that our method can achieve considerably satisfactory detection effect.

Ke Zhang, Xinsheng Wang, Yurong Guo et al.

The development of deep convolutional neural network architecture is critical to the improvement of image classification task performance. A lot of studies of image classification based on deep convolutional neural network focus on the network structure to improve the image classification performance. Contrary to these studies, we focus on the loss function. Cross-entropy Loss (CEL) is widely used for training a multi-class classification deep convolutional neural network. While CEL has been successfully implemented in image classification tasks, it only focuses on the posterior probability of correct class when the labels of training images are one-hot. It cannot be discriminated against the classes not belong to correct class (wrong classes) directly. In order to solve the problem of CEL, we propose Competing Ratio Loss (CRL), which calculates the posterior probability ratio between the correct class and competing wrong classes to better discriminate the correct class from competing wrong classes, increasing the difference between the negative log likelihood of the correct class and the negative log likelihood of competing wrong classes, widening the difference between the probability of the correct class and the probabilities of wrong classes. To demonstrate the effectiveness of our loss function, we perform some sets of experiments on different types of image classification datasets, including CIFAR, SVHN, CUB200- 2011, Adience and ImageNet datasets. The experimental results show the effectiveness and robustness of our loss function on different deep convolutional neural network architectures and different image classification tasks, such as fine-grained image classification, hard face age estimation and large-scale image classification.