Zhonghua Wu

Yicheng Wu, Zhonghua Wu, Qianyi Wu et al. · ibm-research

Semi-supervised segmentation remains challenging in medical imaging since the amount of annotated medical data is often scarce and there are many blurred pixels near the adhesive edges or in the low-contrast regions. To address the issues, we advocate to firstly constrain the consistency of pixels with and without strong perturbations to apply a sufficient smoothness constraint and further encourage the class-level separation to exploit the low-entropy regularization for the model training. Particularly, in this paper, we propose the SS-Net for semi-supervised medical image segmentation tasks, via exploring the pixel-level smoothness and inter-class separation at the same time. The pixel-level smoothness forces the model to generate invariant results under adversarial perturbations. Meanwhile, the inter-class separation encourages individual class features should approach their corresponding high-quality prototypes, in order to make each class distribution compact and separate different classes. We evaluated our SS-Net against five recent methods on the public LA and ACDC datasets. Extensive experimental results under two semi-supervised settings demonstrate the superiority of our proposed SS-Net model, achieving new state-of-the-art (SOTA) performance on both datasets. The code is available at https://github.com/ycwu1997/SS-Net.

Xiao-Ming Wu, Bin Fan, Kang Liao et al.

Following the rise of large foundation models, Vision-Language-Action models (VLAs) emerged, leveraging strong visual and language understanding from Vision-Language Models for general-purpose policy learning. Yet, the current VLA landscape remains fragmented and exploratory. Although many groups have proposed their own VLA models, inconsistencies in training protocols and evaluation settings make it difficult to identify which design choices truly matter. To bring structure to this evolving space, we reexamine the VLA design space under a unified framework and evaluation setup. Starting from a simple VLA baseline similar to RT-2, which is the origin of VLA, we systematically dissect design choices along three dimensions: foundational components, perception essentials, and action modelling perspectives. From this study, we distill 12 key findings that together form a practical recipe for building strong VLA models. The outcome of this exploration is a simple yet effective model, VLANeXt. It outperforms the state-of-the-art methods on the LIBERO and LIBERO-plus benchmarks and demonstrates strong performance in real-world experiments. We release a unified and easy-to-use codebase to reproduce our findings, explore the design space, and develop new VLA variants on top of a shared foundation. The codebase is available at https://github.com/DravenALG/VLANeXt.

Zhonghua Wu, Yicheng Wu, Guosheng Lin et al.

Weakly-supervised point cloud segmentation with extremely limited labels is highly desirable to alleviate the expensive costs of collecting densely annotated 3D points. This paper explores applying the consistency regularization that is commonly used in weakly-supervised learning, for its point cloud counterpart with multiple data-specific augmentations, which has not been well studied. We observe that the straightforward way of applying consistency constraints to weakly-supervised point cloud segmentation has two major limitations: noisy pseudo labels due to the conventional confidence-based selection and insufficient consistency constraints due to discarding unreliable pseudo labels. Therefore, we propose a novel Reliability-Adaptive Consistency Network (RAC-Net) to use both prediction confidence and model uncertainty to measure the reliability of pseudo labels and apply consistency training on all unlabeled points while with different consistency constraints for different points based on the reliability of corresponding pseudo labels. Experimental results on the S3DIS and ScanNet-v2 benchmark datasets show that our model achieves superior performance in weakly-supervised point cloud segmentation. The code will be released publicly at https://github.com/wu-zhonghua/RAC-Net.

Yicheng Wu, Zhonghua Wu, Hengcan Shi et al.

New lesion segmentation is essential to estimate the disease progression and therapeutic effects during multiple sclerosis (MS) clinical treatments. However, the expensive data acquisition and expert annotation restrict the feasibility of applying large-scale deep learning models. Since single-time-point samples with all-lesion labels are relatively easy to collect, exploiting them to train deep models is highly desirable to improve new lesion segmentation. Therefore, we proposed a coaction segmentation (CoactSeg) framework to exploit the heterogeneous data (i.e., new-lesion annotated two-time-point data and all-lesion annotated single-time-point data) for new MS lesion segmentation. The CoactSeg model is designed as a unified model, with the same three inputs (the baseline, follow-up, and their longitudinal brain differences) and the same three outputs (the corresponding all-lesion and new-lesion predictions), no matter which type of heterogeneous data is being used. Moreover, a simple and effective relation regularization is proposed to ensure the longitudinal relations among the three outputs to improve the model learning. Extensive experiments demonstrate that utilizing the heterogeneous data and the proposed longitudinal relation constraint can significantly improve the performance for both new-lesion and all-lesion segmentation tasks. Meanwhile, we also introduce an in-house MS-23v1 dataset, including 38 Oceania single-time-point samples with all-lesion labels. Codes and the dataset are released at https://github.com/ycwu1997/CoactSeg.

Zhonghua Wu, Yicheng Wu, Guosheng Lin et al.

Weakly supervised point cloud segmentation, i.e. semantically segmenting a point cloud with only a few labeled points in the whole 3D scene, is highly desirable due to the heavy burden of collecting abundant dense annotations for the model training. However, existing methods remain challenging to accurately segment 3D point clouds since limited annotated data may lead to insufficient guidance for label propagation to unlabeled data. Considering the smoothness-based methods have achieved promising progress, in this paper, we advocate applying the consistency constraint under various perturbations to effectively regularize unlabeled 3D points. Specifically, we propose a novel DAT (\textbf{D}ual \textbf{A}daptive \textbf{T}ransformations) model for weakly supervised point cloud segmentation, where the dual adaptive transformations are performed via an adversarial strategy at both point-level and region-level, aiming at enforcing the local and structural smoothness constraints on 3D point clouds. We evaluate our proposed DAT model with two popular backbones on the large-scale S3DIS and ScanNet-V2 datasets. Extensive experiments demonstrate that our model can effectively leverage the unlabeled 3D points and achieve significant performance gains on both datasets, setting new state-of-the-art performance for weakly supervised point cloud segmentation.

Weide Liu, Zhonghua Wu, Yiming Wang et al.

In this work, we tackle the challenging problem of long-tailed image recognition. Previous long-tailed recognition approaches mainly focus on data augmentation or re-balancing strategies for the tail classes to give them more attention during model training. However, these methods are limited by the small number of training images for the tail classes, which results in poor feature representations. To address this issue, we propose the Latent Categories based long-tail Recognition (LCReg) method. Our hypothesis is that common latent features shared by head and tail classes can be used to improve feature representation. Specifically, we learn a set of class-agnostic latent features shared by both head and tail classes, and then use semantic data augmentation on the latent features to implicitly increase the diversity of the training sample. We conduct extensive experiments on five long-tailed image recognition datasets, and the results show that our proposed method significantly improves the baselines.

Weide Liu, Zhonghua Wu, Yang Zhao et al.

Current methods for few-shot segmentation (FSSeg) have mainly focused on improving the performance of novel classes while neglecting the performance of base classes. To overcome this limitation, the task of generalized few-shot semantic segmentation (GFSSeg) has been introduced, aiming to predict segmentation masks for both base and novel classes. However, the current prototype-based methods do not explicitly consider the relationship between base and novel classes when updating prototypes, leading to a limited performance in identifying true categories. To address this challenge, we propose a class contrastive loss and a class relationship loss to regulate prototype updates and encourage a large distance between prototypes from different classes, thus distinguishing the classes from each other while maintaining the performance of the base classes. Our proposed approach achieves new state-of-the-art performance for the generalized few-shot segmentation task on PASCAL VOC and MS COCO datasets.

Zhipeng Luo, Gongjie Zhang, Changqing Zhou et al.

The task of 3D single object tracking (SOT) with LiDAR point clouds is crucial for various applications, such as autonomous driving and robotics. However, existing approaches have primarily relied on appearance matching or motion modeling within only two successive frames, thereby overlooking the long-range continuous motion property of objects in 3D space. To address this issue, this paper presents a novel approach that views each tracklet as a continuous stream: at each timestamp, only the current frame is fed into the network to interact with multi-frame historical features stored in a memory bank, enabling efficient exploitation of sequential information. To achieve effective cross-frame message passing, a hybrid attention mechanism is designed to account for both long-range relation modeling and local geometric feature extraction. Furthermore, to enhance the utilization of multi-frame features for robust tracking, a contrastive sequence enhancement strategy is proposed, which uses ground truth tracklets to augment training sequences and promote discrimination against false positives in a contrastive manner. Extensive experiments demonstrate that the proposed method outperforms the state-of-the-art method by significant margins on multiple benchmarks.

Weide Liu, Zhonghua Wu, Yiming Wang et al.

In this work, we address the challenging task of long-tailed image recognition. Previous long-tailed recognition methods commonly focus on the data augmentation or re-balancing strategy of the tail classes to give more attention to tail classes during the model training. However, due to the limited training images for tail classes, the diversity of tail class images is still restricted, which results in poor feature representations. In this work, we hypothesize that common latent features among the head and tail classes can be used to give better feature representation. Motivated by this, we introduce a Latent Categories based long-tail Recognition (LCReg) method. Specifically, we propose to learn a set of class-agnostic latent features shared among the head and tail classes. Then, we implicitly enrich the training sample diversity via applying semantic data augmentation to the latent features. Extensive experiments on five long-tailed image recognition datasets demonstrate that our proposed LCReg is able to significantly outperform previous methods and achieve state-of-the-art results.

Size Wu, Wenwei Zhang, Lumin Xu et al.

Unifying visual understanding and generation within a single multimodal framework remains a significant challenge, as the two inherently heterogeneous tasks require representations at different levels of granularity. Current approaches that utilize vector quantization (VQ) or variational autoencoders (VAE) for unified visual representation prioritize intrinsic imagery features over semantics, compromising understanding performance. In this work, we take inspiration from masked image modelling (MIM) that learns rich semantics via a mask-and-reconstruct pre-training and its successful extension to masked autoregressive (MAR) image generation. A preliminary study on the MAR encoder's representation reveals exceptional linear probing accuracy and precise feature response to visual concepts, which indicates MAR's potential for visual understanding tasks beyond its original generation role. Based on these insights, we present \emph{Harmon}, a unified autoregressive framework that harmonizes understanding and generation tasks with a shared MAR encoder. Through a three-stage training procedure that progressively optimizes understanding and generation capabilities, Harmon achieves state-of-the-art image generation results on the GenEval, MJHQ30K and WISE benchmarks while matching the performance of methods with dedicated semantic encoders (e.g., Janus) on image understanding benchmarks. Our code and models will be available at https://github.com/wusize/Harmon.

Xiaojing Zhong, Xinyi Huang, Zhonghua Wu et al.

Makeup transfer is a process of transferring the makeup style from a reference image to the source images, while preserving the source images' identities. This technique is highly desirable and finds many applications. However, existing methods lack fine-level control of the makeup style, making it challenging to achieve high-quality results when dealing with large spatial misalignments. To address this problem, we propose a novel Spatial Alignment and Region-Adaptive normalization method (SARA) in this paper. Our method generates detailed makeup transfer results that can handle large spatial misalignments and achieve part-specific and shade-controllable makeup transfer. Specifically, SARA comprises three modules: Firstly, a spatial alignment module that preserves the spatial context of makeup and provides a target semantic map for guiding the shape-independent style codes. Secondly, a region-adaptive normalization module that decouples shape and makeup style using per-region encoding and normalization, which facilitates the elimination of spatial misalignments. Lastly, a makeup fusion module blends identity features and makeup style by injecting learned scale and bias parameters. Experimental results show that our SARA method outperforms existing methods and achieves state-of-the-art performance on two public datasets.

Size Wu, Zhonghua Wu, Zerui Gong et al.

In this report, we present OpenUni, a simple, lightweight, and fully open-source baseline for unifying multimodal understanding and generation. Inspired by prevailing practices in unified model learning, we adopt an efficient training strategy that minimizes the training complexity and overhead by bridging the off-the-shelf multimodal large language models (LLMs) and diffusion models through a set of learnable queries and a light-weight transformer-based connector. With a minimalist choice of architecture, we demonstrate that OpenUni can: 1) generate high-quality and instruction-aligned images, and 2) achieve exceptional performance on standard benchmarks such as GenEval, DPG- Bench, and WISE, with only 1.1B and 3.1B activated parameters. To support open research and community advancement, we release all model weights, training code, and our curated training datasets (including 23M image-text pairs) at https://github.com/wusize/OpenUni.

Hui EnPang, Zhongang Cai, Lei Yang et al.

Whole-body pose and shape estimation aims to jointly predict different behaviors (e.g., pose, hand gesture, facial expression) of the entire human body from a monocular image. Existing methods often exhibit degraded performance under the complexity of in-the-wild scenarios. We argue that the accuracy and reliability of these models are significantly affected by the quality of the predicted \textit{bounding box}, e.g., the scale and alignment of body parts. The natural discrepancy between the ideal bounding box annotations and model detection results is particularly detrimental to the performance of whole-body pose and shape estimation. In this paper, we propose a novel framework to enhance the robustness of whole-body pose and shape estimation. Our framework incorporates three new modules to address the above challenges from three perspectives: \textbf{1) Localization Module} enhances the model's awareness of the subject's location and semantics within the image space. \textbf{2) Contrastive Feature Extraction Module} encourages the model to be invariant to robust augmentations by incorporating contrastive loss with dedicated positive samples. \textbf{3) Pixel Alignment Module} ensures the reprojected mesh from the predicted camera and body model parameters are accurate and pixel-aligned. We perform comprehensive experiments to demonstrate the effectiveness of our proposed framework on body, hands, face and whole-body benchmarks. Codebase is available at \url{https://github.com/robosmplx/robosmplx}.

Xiaojing Zhong, Yukun Su, Zhonghua Wu et al.

3D virtual try-on enjoys many potential applications and hence has attracted wide attention. However, it remains a challenging task that has not been adequately solved. Existing 2D virtual try-on methods cannot be directly extended to 3D since they lack the ability to perceive the depth of each pixel. Besides, 3D virtual try-on approaches are mostly built on the fixed topological structure and with heavy computation. To deal with these problems, we propose a Decomposed Implicit garment transfer network (DI-Net), which can effortlessly reconstruct a 3D human mesh with the newly try-on result and preserve the texture from an arbitrary perspective. Specifically, DI-Net consists of two modules: 1) A complementary warping module that warps the reference image to have the same pose as the source image through dense correspondence learning and sparse flow learning; 2) A geometry-aware decomposed transfer module that decomposes the garment transfer into image layout based transfer and texture based transfer, achieving surface and texture reconstruction by constructing pixel-aligned implicit functions. Experimental results show the effectiveness and superiority of our method in the 3D virtual try-on task, which can yield more high-quality results over other existing methods.

Zerui Gong, Zhonghua Wu, Qingyi Tao et al.

Photorealistic style transfer (PST) enables real-world color grading by adapting reference image colors while preserving content structure. Existing methods mainly follow either approaches: generation-based methods that prioritize stylistic fidelity at the cost of content integrity and efficiency, or global color transformation methods such as LUT, which preserve structure but lack local adaptability. To bridge this gap, we propose Spatial Adaptive 4D Look-Up Table (SA-LUT), combining LUT efficiency with neural network adaptability. SA-LUT features: (1) a Style-guided 4D LUT Generator that extracts multi-scale features from the style image to predict a 4D LUT, and (2) a Context Generator using content-style cross-attention to produce a context map. This context map enables spatially-adaptive adjustments, allowing our 4D LUT to apply precise color transformations while preserving structural integrity. To establish a rigorous evaluation framework for photorealistic style transfer, we introduce PST50, the first benchmark specifically designed for PST assessment. Experiments demonstrate that SA-LUT substantially outperforms state-of-the-art methods, achieving a 66.7% reduction in LPIPS score compared to 3D LUT approaches, while maintaining real-time performance at 16 FPS for video stylization. Our code and benchmark are available at https://github.com/Ry3nG/SA-LUT

Yikai Wang, Zhouxia Wang, Zhonghua Wu et al.

We propose a novel approach to image generation by decomposing an image into a structured sequence, where each element in the sequence shares the same spatial resolution but differs in the number of unique tokens used, capturing different level of visual granularity. Image generation is carried out through our newly introduced Next Visual Granularity (NVG) generation framework, which generates a visual granularity sequence beginning from an empty image and progressively refines it, from global layout to fine details, in a structured manner. This iterative process encodes a hierarchical, layered representation that offers fine-grained control over the generation process across multiple granularity levels. We train a series of NVG models for class-conditional image generation on the ImageNet dataset and observe clear scaling behavior. Compared to the VAR series, NVG consistently outperforms it in terms of FID scores (3.30 -> 3.03, 2.57 ->2.44, 2.09 -> 2.06). We also conduct extensive analysis to showcase the capability and potential of the NVG framework. Our code and models will be released.

Yicheng Wu, Tao Song, Zhonghua Wu et al.

Unified MRI imputation, which can adapt to diverse imputation scenarios, is highly desirable as it reduces scanning costs and provides comprehensive MRI information for improved clinical diagnosis. Existing unified MRI imputation methods either rely on specific prompts to guide their transformation network or require multiple modality-specific modules. However, these approaches struggle to capture large modality and instance variations or become too complex to generalize effectively. To address these limitations, we propose CodeBrain, a fundamentally different pipeline for unified brain MRI imputation. Our key idea is to reframe various inter-modality transformations as a full-modality code prediction task via a two-stage framework. In the first stage, CodeBrain reconstructs a target modality from any other modalities by learning a compact scalar-quantized code for each instance and modality. Any target modality can then be reconstructed with high fidelity by combining the corresponding code with shared features extracted from any available modality. In the second stage, a projection encoder is trained to predict full-modality compact codes from any incomplete MRI samples, effectively simulating various imputation scenarios. We evaluate our CodeBrain on two public brain MRI datasets (i.e., IXI and BraTS 2023). Extensive experiments demonstrate that CodeBrain outperforms state-of-the-art methods, setting a new benchmark for unified brain MRI imputation. Our code will be released.

Zhengyuan Fan, Zhonghua Wu, Yuxuan Du et al.

Reference-free preference optimization has emerged as an efficient alternative to reinforcement learning from human feedback, with Simple Preference Optimization(SimPO) demonstrating strong performance by eliminating the explicit reference model through a simple objective. However, the joint tuning of the hyperparameters $β$ and $γ$ in SimPO remains a central challenge. We argue that this difficulty arises because the margin formulation in SimPO is not easily interpretable across datasets with different reward gap structures. To better understand this issue, we conduct a comprehensive analysis of SimPO and find that $β$ implicitly controls sample filtering, while the effect of $γ$ depends on the reward gap structure of the dataset. Motivated by these observations, we propose $ξ$-DPO: Direct preference optimization via ratio reward margin. We first reformulate the preference objective through an equivalent transformation, changing the optimization target from maximizing the likelihood of reward gaps to minimizing the distance between reward gaps and optimal margins. Then, we redefine the reward in a ratio form between the chosen and rejected, which effectively cancels the effect of $β$ and yields a bounded and interpretable margin. This margin is called the ratio reward margin and is denoted by $ξ$. Unlike the margin $γ$ in SimPO, $ξ$ explicitly represents the desired relative separation between chosen and rejected responses and can be determined from the initial reward gap distribution, avoiding repeated trial-and-error tuning. ....

Kang Liao, Zongsheng Yue, Zhonghua Wu et al.

While recent image warping approaches achieved remarkable success on existing benchmarks, they still require training separate models for each specific task and cannot generalize well to different camera models or customized manipulations. To address diverse types of warping in practice, we propose a Multiple-in-One image WArping model (named MOWA) in this work. Specifically, we mitigate the difficulty of multi-task learning by disentangling the motion estimation at both the region level and pixel level. To further enable dynamic task-aware image warping, we introduce a lightweight point-based classifier that predicts the task type, serving as prompts to modulate the feature maps for more accurate estimation. To our knowledge, this is the first work that solves multiple practical warping tasks in one single model. Extensive experiments demonstrate that our MOWA, which is trained on six tasks for multiple-in-one image warping, outperforms state-of-the-art task-specific models across most tasks. Moreover, MOWA also exhibits promising potential to generalize into unseen scenes, as evidenced by cross-domain and zero-shot evaluations. The code and more visual results can be found on the project page: https://kangliao929.github.io/projects/mowa/.

Xiaojing Zhong, Zhonghua Wu, Xiaofeng Yang et al.

Given a pair of images depicting a person and a garment separately, image-based 3D virtual try-on methods aim to reconstruct a 3D human model that realistically portrays the person wearing the desired garment. In this paper, we present IPVTON, a novel image-based 3D virtual try-on framework. IPVTON employs score distillation sampling with image prompts to optimize a hybrid 3D human representation, integrating target garment features into diffusion priors through an image prompt adapter. To avoid interference with non-target areas, we leverage mask-guided image prompt embeddings to focus the image features on the try-on regions. Moreover, we impose geometric constraints on the 3D model with a pseudo silhouette generated by ControlNet, ensuring that the clothed 3D human model retains the shape of the source identity while accurately wearing the target garments. Extensive qualitative and quantitative experiments demonstrate that IPVTON outperforms previous methods in image-based 3D virtual try-on tasks, excelling in both geometry and texture.

Kang Liao, Size Wu, Zhonghua Wu et al.

Camera-centric understanding and generation are two cornerstones of spatial intelligence, yet they are typically studied in isolation. We present Puffin, a unified camera-centric multimodal model that extends spatial awareness along the camera dimension. Puffin integrates language regression and diffusion-based generation to interpret and create scenes from arbitrary viewpoints. To bridge the modality gap between cameras and vision-language, we introduce a novel paradigm that treats camera as language, enabling thinking with camera. This guides the model to align spatially grounded visual cues with photographic terminology while reasoning across geometric context. Puffin is trained on Puffin-4M, a large-scale dataset of 4 million vision-language-camera triplets. We incorporate both global camera parameters and pixel-wise camera maps, yielding flexible and reliable spatial generation. Experiments demonstrate Puffin superior performance over specialized models for camera-centric generation and understanding. With instruction tuning, Puffin generalizes to diverse cross-view tasks such as spatial imagination, world exploration, and photography guidance. We will release the code, models, dataset pipeline, and benchmark to advance multimodal spatial intelligence research.

Lechun You, Zhonghua Wu, Weide Liu et al.

Current methods for 3D semantic segmentation propose training models with limited annotations to address the difficulty of annotating large, irregular, and unordered 3D point cloud data. They usually focus on the 3D domain only, without leveraging the complementary nature of 2D and 3D data. Besides, some methods extend original labels or generate pseudo labels to guide the training, but they often fail to fully use these labels or address the noise within them. Meanwhile, the emergence of comprehensive and adaptable foundation models has offered effective solutions for segmenting 2D data. Leveraging this advancement, we present a novel approach that maximizes the utility of sparsely available 3D annotations by incorporating segmentation masks generated by 2D foundation models. We further propagate the 2D segmentation masks into the 3D space by establishing geometric correspondences between 3D scenes and 2D views. We extend the highly sparse annotations to encompass the areas delineated by 3D masks, thereby substantially augmenting the pool of available labels. Furthermore, we apply confidence- and uncertainty-based consistency regularization on augmentations of the 3D point cloud and select the reliable pseudo labels, which are further spread on the 3D masks to generate more labels. This innovative strategy bridges the gap between limited 3D annotations and the powerful capabilities of 2D foundation models, ultimately improving the performance of 3D weakly supervised segmentation.

Xiaojing Zhong, Zhonghua Wu, Taizhe Tan et al.

With the development of Generative Adversarial Network, image-based virtual try-on methods have made great progress. However, limited work has explored the task of video-based virtual try-on while it is important in real-world applications. Most existing video-based virtual try-on methods usually require clothing templates and they can only generate blurred and low-resolution results. To address these challenges, we propose a Memory-based Video virtual Try-On Network (MV-TON), which seamlessly transfers desired clothes to a target person without using any clothing templates and generates high-resolution realistic videos. Specifically, MV-TON consists of two modules: 1) a try-on module that transfers the desired clothes from model images to frame images by pose alignment and region-wise replacing of pixels; 2) a memory refinement module that learns to embed the existing generated frames into the latent space as external memory for the following frame generation. Experimental results show the effectiveness of our method in the video virtual try-on task and its superiority over other existing methods.

Weide Liu, Zhonghua Wu, Henghui Ding et al.

In this work, we address the challenging task of few-shot segmentation. Previous few-shot segmentation methods mainly employ the information of support images as guidance for query image segmentation. Although some works propose to build cross-reference between support and query images, their extraction of query information still depends on the support images. We here propose to extract the information from the query itself independently to benefit the few-shot segmentation task. To this end, we first propose a prior extractor to learn the query information from the unlabeled images with our proposed global-local contrastive learning. Then, we extract a set of predetermined priors via this prior extractor. With the obtained priors, we generate the prior region maps for query images, which locate the objects, as guidance to perform cross interaction with support features. In such a way, the extraction of query information is detached from the support branch, overcoming the limitation by support, and could obtain more informative query clues to achieve better interaction. Without bells and whistles, the proposed approach achieves new state-of-the-art performance for the few-shot segmentation task on PASCAL-5$^{i}$ and COCO datasets.

Zhonghua Wu, Xiangxi Shi, Guosheng lin et al.

Currently, the state-of-the-art methods treat few-shot semantic segmentation task as a conditional foreground-background segmentation problem, assuming each class is independent. In this paper, we introduce the concept of meta-class, which is the meta information (e.g. certain middle-level features) shareable among all classes. To explicitly learn meta-class representations in few-shot segmentation task, we propose a novel Meta-class Memory based few-shot segmentation method (MM-Net), where we introduce a set of learnable memory embeddings to memorize the meta-class information during the base class training and transfer to novel classes during the inference stage. Moreover, for the $k$-shot scenario, we propose a novel image quality measurement module to select images from the set of support images. A high-quality class prototype could be obtained with the weighted sum of support image features based on the quality measure. Experiments on both PASCAL-$5^i$ and COCO dataset shows that our proposed method is able to achieve state-of-the-art results in both 1-shot and 5-shot settings. Particularly, our proposed MM-Net achieves 37.5\% mIoU on the COCO dataset in 1-shot setting, which is 5.1\% higher than the previous state-of-the-art.

Xiangxi Shi, Zhonghua Wu, Guosheng Lin et al.

Image manipulation with natural language, which aims to manipulate images with the guidance of language descriptions, has been a challenging problem in the fields of computer vision and natural language processing (NLP). Currently, a number of efforts have been made for this task, but their performances are still distant away from generating realistic and text-conformed manipulated images. Therefore, in this paper, we propose a memory-based Image Manipulation Network (MIM-Net), where a set of memories learned from images is introduced to synthesize the texture information with the guidance of the textual description. We propose a two-stage network with an additional reconstruction stage to learn the latent memories efficiently. To avoid the unnecessary background changes, we propose a Target Localization Unit (TLU) to focus on the manipulation of the region mentioned by the text. Moreover, to learn a robust memory, we further propose a novel randomized memory training loss. Experiments on the four popular datasets show the better performance of our method compared to the existing ones.

Zhonghua Wu, Qingyi Tao, Guosheng Lin et al.

Fully supervised object detection has achieved great success in recent years. However, abundant bounding boxes annotations are needed for training a detector for novel classes. To reduce the human labeling effort, we propose a novel webly supervised object detection (WebSOD) method for novel classes which only requires the web images without further annotations. Our proposed method combines bottom-up and top-down cues for novel class detection. Within our approach, we introduce a bottom-up mechanism based on the well-trained fully supervised object detector (i.e. Faster RCNN) as an object region estimator for web images by recognizing the common objectiveness shared by base and novel classes. With the estimated regions on the web images, we then utilize the top-down attention cues as the guidance for region classification. Furthermore, we propose a residual feature refinement (RFR) block to tackle the domain mismatch between web domain and the target domain. We demonstrate our proposed method on PASCAL VOC dataset with three different novel/base splits. Without any target-domain novel-class images and annotations, our proposed webly supervised object detection model is able to achieve promising performance for novel classes. Moreover, we also conduct transfer learning experiments on large scale ILSVRC 2013 detection dataset and achieve state-of-the-art performance.

Zhonghua Wu, Guosheng Lin, Qingyi Tao et al.

Most existing virtual try-on applications require clean clothes images. Instead, we present a novel virtual Try-On network, M2E-Try On Net, which transfers the clothes from a model image to a person image without the need of any clean product images. To obtain a realistic image of person wearing the desired model clothes, we aim to solve the following challenges: 1) non-rigid nature of clothes - we need to align poses between the model and the user; 2) richness in textures of fashion items - preserving the fine details and characteristics of the clothes is critical for photo-realistic transfer; 3) variation of identity appearances - it is required to fit the desired model clothes to the person identity seamlessly. To tackle these challenges, we introduce three key components, including the pose alignment network (PAN), the texture refinement network (TRN) and the fitting network (FTN). Since it is unlikely to gather image pairs of input person image and desired output image (i.e. person wearing the desired clothes), our framework is trained in a self-supervised manner to gradually transfer the poses and textures of the model's clothes to the desired appearance. In the experiments, we verify on the Deep Fashion dataset and MVC dataset that our method can generate photo-realistic images for the person to try-on the model clothes. Furthermore, we explore the model capability for different fashion items, including both upper and lower garments.

Zhonghua Wu, Guosheng Lin, Jianfei Cai

Fully convolutional networks (FCN) have achieved great success in human parsing in recent years. In conventional human parsing tasks, pixel-level labeling is required for guiding the training, which usually involves enormous human labeling efforts. To ease the labeling efforts, we propose a novel weakly supervised human parsing method which only requires simple object keypoint annotations for learning. We develop an iterative learning method to generate pseudo part segmentation masks from keypoint labels. With these pseudo masks, we train an FCN network to output pixel-level human parsing predictions. Furthermore, we develop a correlation network to perform joint prediction of part and object segmentation masks and improve the segmentation performance. The experiment results show that our weakly supervised method is able to achieve very competitive human parsing results. Despite our method only uses simple keypoint annotations for learning, we are able to achieve comparable performance with fully supervised methods which use the expensive pixel-level annotations.