Dong Zhang

Xixi Jiang, Dong Zhang, Xiang Li et al.

Partially-supervised multi-organ medical image segmentation aims to develop a unified semantic segmentation model by utilizing multiple partially-labeled datasets, with each dataset providing labels for a single class of organs. However, the limited availability of labeled foreground organs and the absence of supervision to distinguish unlabeled foreground organs from the background pose a significant challenge, which leads to a distribution mismatch between labeled and unlabeled pixels. Although existing pseudo-labeling methods can be employed to learn from both labeled and unlabeled pixels, they are prone to performance degradation in this task, as they rely on the assumption that labeled and unlabeled pixels have the same distribution. In this paper, to address the problem of distribution mismatch, we propose a labeled-to-unlabeled distribution alignment (LTUDA) framework that aligns feature distributions and enhances discriminative capability. Specifically, we introduce a cross-set data augmentation strategy, which performs region-level mixing between labeled and unlabeled organs to reduce distribution discrepancy and enrich the training set. Besides, we propose a prototype-based distribution alignment method that implicitly reduces intra-class variation and increases the separation between the unlabeled foreground and background. This can be achieved by encouraging consistency between the outputs of two prototype classifiers and a linear classifier. Extensive experimental results on the AbdomenCT-1K dataset and a union of four benchmark datasets (including LiTS, MSD-Spleen, KiTS, and NIH82) demonstrate that our method outperforms the state-of-the-art partially-supervised methods by a considerable margin, and even surpasses the fully-supervised methods. The source code is publicly available at https://github.com/xjiangmed/LTUDA.

Yi Lin, Zeyu Wang, Dong Zhang et al.

Nuclei segmentation is a fundamental prerequisite in the digital pathology workflow. The development of automated methods for nuclei segmentation enables quantitative analysis of the wide existence and large variances in nuclei morphometry in histopathology images. However, manual annotation of tens of thousands of nuclei is tedious and time-consuming, which requires significant amount of human effort and domain-specific expertise. To alleviate this problem, in this paper, we propose a weakly-supervised nuclei segmentation method that only requires partial point labels of nuclei. Specifically, we propose a novel boundary mining framework for nuclei segmentation, named BoNuS, which simultaneously learns nuclei interior and boundary information from the point labels. To achieve this goal, we propose a novel boundary mining loss, which guides the model to learn the boundary information by exploring the pairwise pixel affinity in a multiple-instance learning manner. Then, we consider a more challenging problem, i.e., partial point label, where we propose a nuclei detection module with curriculum learning to detect the missing nuclei with prior morphological knowledge. The proposed method is validated on three public datasets, MoNuSeg, CPM, and CoNIC datasets. Experimental results demonstrate the superior performance of our method to the state-of-the-art weakly-supervised nuclei segmentation methods. Code: https://github.com/hust-linyi/bonus.

Chunyan Wang, Dong Zhang, Jinhui Tang

Weakly-supervised semantic segmentation aims to assign category labels to each pixel using weak annotations, significantly reducing manual annotation costs. Although existing methods have achieved remarkable progress in well-lit scenarios, their performance significantly degrades in low-light environments due to two fundamental limitations: severe image quality degradation (e.g., low contrast, noise, and color distortion) and the inherent constraints of weak supervision. These factors collectively lead to unreliable class activation maps and semantically ambiguous pseudo-labels, ultimately compromising the model's ability to learn discriminative feature representations. To address these problems, we propose Diffusion-Guided Knowledge Distillation for Weakly-Supervised Low-light Semantic Segmentation (DGKD-WLSS), a novel framework that synergistically combines Diffusion-Guided Knowledge Distillation (DGKD) with Depth-Guided Feature Fusion (DGF2). DGKD aligns normal-light and low-light features via diffusion-based denoising and knowledge distillation, while DGF2 integrates depth maps as illumination-invariant geometric priors to enhance structural feature learning. Extensive experiments demonstrate the effectiveness of DGKD-WLSS, which achieves state-of-the-art performance in weakly supervised semantic segmentation tasks under low-light conditions. The source codes have been released at:https://github.com/ChunyanWang1/DGKD-WLSS.

Dong Zhang, Rui Yan, Pingcheng Dong et al.

While current Vision Transformer (ViT) adapter methods have shown promising accuracy, their inference speed is implicitly hindered by inefficient memory access operations, e.g., standard normalization and frequent reshaping. In this work, we propose META, a simple and fast ViT adapter that can improve the model's memory efficiency and decrease memory time consumption by reducing the inefficient memory access operations. Our method features a memory-efficient adapter block that enables the common sharing of layer normalization between the self-attention and feed-forward network layers, thereby reducing the model's reliance on normalization operations. Within the proposed block, the cross-shaped self-attention is employed to reduce the model's frequent reshaping operations. Moreover, we augment the adapter block with a lightweight convolutional branch that can enhance local inductive biases, particularly beneficial for the dense prediction tasks, e.g., object detection, instance segmentation, and semantic segmentation. The adapter block is finally formulated in a cascaded manner to compute diverse head features, thereby enriching the variety of feature representations. Empirically, extensive evaluations on multiple representative datasets validate that META substantially enhances the predicted quality, while achieving a new state-of-the-art accuracy-efficiency trade-off. Theoretically, we demonstrate that META exhibits superior generalization capability and stronger adaptability.

Dingwei Zhang, Dong Zhang, Jinhui Tang

Recently, query-based methods have achieved remarkable performance in Referring Video Object Segmentation (RVOS) by using textual static object queries to drive cross-modal alignment. However, these static queries are easily misled by distractors with similar appearance or motion, resulting in \emph{query selection bias}. To address this issue, we propose Triple Query Former (TQF), which factorizes the referring query into three specialized components: an appearance query for static attributes, an intra-frame interaction query for spatial relations, and an inter-frame motion query for temporal association. Instead of relying solely on textual embeddings, our queries are dynamically constructed by integrating both linguistic cues and visual guidance. Furthermore, we introduce two motion-aware aggregation modules that enhance object token representations: Intra-frame Interaction Aggregation incorporates position-aware interactions among objects within a single frame, while Inter-frame Motion Aggregation leverages trajectory-guided alignment across frames to ensure temporal coherence. Extensive experiments on multiple RVOS benchmarks demonstrate the advantages of TQF and the effectiveness of our structured query design and motion-aware aggregation modules.

Zhang Dong, Zhang Hanwang, Tang Jinhui et al.

In this paper, we seek reasons for the two major failure cases in Semantic Segmentation (SS): 1) missing small objects or minor object parts, and 2) mislabeling minor parts of large objects as wrong classes. We have an interesting finding that Failure-1 is due to the underuse of detailed features and Failure-2 is due to the underuse of visual contexts. To help the model learn a better trade-off, we introduce several Self-Regulation (SR) losses for training SS neural networks. By "self", we mean that the losses are from the model per se without using any additional data or supervision. By applying the SR losses, the deep layer features are regulated by the shallow ones to preserve more details; meanwhile, shallow layer classification logits are regulated by the deep ones to capture more semantics. We conduct extensive experiments on both weakly and fully supervised SS tasks, and the results show that our approach consistently surpasses the baselines. We also validate that SR losses are easy to implement in various state-of-the-art SS models, e.g., SPGNet and OCRNet, incurring little computational overhead during training and none for testing.

Dong Zhang, Hanwang Zhang, Jinhui Tang et al.

We present a causal inference framework to improve Weakly-Supervised Semantic Segmentation (WSSS). Specifically, we aim to generate better pixel-level pseudo-masks by using only image-level labels -- the most crucial step in WSSS. We attribute the cause of the ambiguous boundaries of pseudo-masks to the confounding context, e.g., the correct image-level classification of "horse" and "person" may be not only due to the recognition of each instance, but also their co-occurrence context, making the model inspection (e.g., CAM) hard to distinguish between the boundaries. Inspired by this, we propose a structural causal model to analyze the causalities among images, contexts, and class labels. Based on it, we develop a new method: Context Adjustment (CONTA), to remove the confounding bias in image-level classification and thus provide better pseudo-masks as ground-truth for the subsequent segmentation model. On PASCAL VOC 2012 and MS-COCO, we show that CONTA boosts various popular WSSS methods to new state-of-the-arts.

Dong Zhang, Hanwang Zhang, Jinhui Tang et al.

Feature interactions across space and scales underpin modern visual recognition systems because they introduce beneficial visual contexts. Conventionally, spatial contexts are passively hidden in the CNN's increasing receptive fields or actively encoded by non-local convolution. Yet, the non-local spatial interactions are not across scales, and thus they fail to capture the non-local contexts of objects (or parts) residing in different scales. To this end, we propose a fully active feature interaction across both space and scales, called Feature Pyramid Transformer (FPT). It transforms any feature pyramid into another feature pyramid of the same size but with richer contexts, by using three specially designed transformers in self-level, top-down, and bottom-up interaction fashion. FPT serves as a generic visual backbone with fair computational overhead. We conduct extensive experiments in both instance-level (i.e., object detection and instance segmentation) and pixel-level segmentation tasks, using various backbones and head networks, and observe consistent improvement over all the baselines and the state-of-the-art methods.

Haroon Idrees, Muhmmad Tayyab, Kishan Athrey et al.

With multiple crowd gatherings of millions of people every year in events ranging from pilgrimages to protests, concerts to marathons, and festivals to funerals; visual crowd analysis is emerging as a new frontier in computer vision. In particular, counting in highly dense crowds is a challenging problem with far-reaching applicability in crowd safety and management, as well as gauging political significance of protests and demonstrations. In this paper, we propose a novel approach that simultaneously solves the problems of counting, density map estimation and localization of people in a given dense crowd image. Our formulation is based on an important observation that the three problems are inherently related to each other making the loss function for optimizing a deep CNN decomposable. Since localization requires high-quality images and annotations, we introduce UCF-QNRF dataset that overcomes the shortcomings of previous datasets, and contains 1.25 million humans manually marked with dot annotations. Finally, we present evaluation measures and comparison with recent deep CNN networks, including those developed specifically for crowd counting. Our approach significantly outperforms state-of-the-art on the new dataset, which is the most challenging dataset with the largest number of crowd annotations in the most diverse set of scenes.

Amir Mazaheri, Dong Zhang, Mubarak Shah

Given a video and a description sentence with one missing word (we call it the "source sentence"), Video-Fill-In-the-Blank (VFIB) problem is to find the missing word automatically. The contextual information of the sentence, as well as visual cues from the video, are important to infer the missing word accurately. Since the source sentence is broken into two fragments: the sentence's left fragment (before the blank) and the sentence's right fragment (after the blank), traditional Recurrent Neural Networks cannot encode this structure accurately because of many possible variations of the missing word in terms of the location and type of the word in the source sentence. For example, a missing word can be the first word or be in the middle of the sentence and it can be a verb or an adjective. In this paper, we propose a framework to tackle the textual encoding: Two separate LSTMs (the LR and RL LSTMs) are employed to encode the left and right sentence fragments and a novel structure is introduced to combine each fragment with an "external memory" corresponding the opposite fragments. For the visual encoding, end-to-end spatial and temporal attention models are employed to select discriminative visual representations to find the missing word. In the experiments, we demonstrate the superior performance of the proposed method on challenging VFIB problem. Furthermore, we introduce an extended and more generalized version of VFIB, which is not limited to a single blank. Our experiments indicate the generalization capability of our method in dealing with such more realistic scenarios.

Rodney LaLonde, Dong Zhang, Mubarak Shah

Object detection in wide area motion imagery (WAMI) has drawn the attention of the computer vision research community for a number of years. WAMI proposes a number of unique challenges including extremely small object sizes, both sparse and densely-packed objects, and extremely large search spaces (large video frames). Nearly all state-of-the-art methods in WAMI object detection report that appearance-based classifiers fail in this challenging data and instead rely almost entirely on motion information in the form of background subtraction or frame-differencing. In this work, we experimentally verify the failure of appearance-based classifiers in WAMI, such as Faster R-CNN and a heatmap-based fully convolutional neural network (CNN), and propose a novel two-stage spatio-temporal CNN which effectively and efficiently combines both appearance and motion information to significantly surpass the state-of-the-art in WAMI object detection. To reduce the large search space, the first stage (ClusterNet) takes in a set of extremely large video frames, combines the motion and appearance information within the convolutional architecture, and proposes regions of objects of interest (ROOBI). These ROOBI can contain from one to clusters of several hundred objects due to the large video frame size and varying object density in WAMI. The second stage (FoveaNet) then estimates the centroid location of all objects in that given ROOBI simultaneously via heatmap estimation. The proposed method exceeds state-of-the-art results on the WPAFB 2009 dataset by 5-16% for moving objects and nearly 50% for stopped objects, as well as being the first proposed method in wide area motion imagery to detect completely stationary objects.

Amir Mazaheri, Dong Zhang, Mubarak Shah

Given a video and its incomplete textural description with missing words, the Video-Fill-in-the-Blank (ViFitB) task is to automatically find the missing word. The contextual information of the sentences are important to infer the missing words; the visual cues are even more crucial to get a more accurate inference. In this paper, we presents a new method which intuitively takes advantage of the structure of the sentences and employs merging LSTMs (to merge two LSTMs) to tackle the problem with embedded textural and visual cues. In the experiments, we have demonstrated the superior performance of the proposed method on the challenging "Movie Fill-in-the-Blank" dataset.

Xiaoyue Jiang, Dong Zhang, Xiaoyi Feng

Even though face recognition in frontal view and normal lighting condition works very well, the performance degenerates sharply in extreme conditions. Recently there are many work dealing with pose and illumination problems, respectively. However both the lighting and pose variation will always be encountered at the same time. Accordingly we propose an end-to-end face recognition method to deal with pose and illumination simultaneously based on convolutional networks where the discriminative nonlinear features that are invariant to pose and illumination are extracted. Normally the global structure for images taken in different views is quite diverse. Therefore we propose to use the 1*1 convolutional kernel to extract the local features. Furthermore the parallel multi-stream multi-layer 1*1 convolution network is developed to extract multi-hierarchy features. In the experiments we obtained the average face recognition rate of 96.9% on multiPIE dataset,which improves the state-of-the-art of face recognition across poses and illumination by 7.5%. Especially for profile-wise positions, the average recognition rate of our proposed network is 97.8%, which increases the state-of-the-art recognition rate by 19%.

Da-Han Wang, Hanzi Wang, Dong Zhang et al.

In this paper, we propose an effective scene text recognition method using sparse coding based features, called Histograms of Sparse Codes (HSC) features. For character detection, we use the HSC features instead of using the Histograms of Oriented Gradients (HOG) features. The HSC features are extracted by computing sparse codes with dictionaries that are learned from data using K-SVD, and aggregating per-pixel sparse codes to form local histograms. For word recognition, we integrate multiple cues including character detection scores and geometric contexts in an objective function. The final recognition results are obtained by searching for the words which correspond to the maximum value of the objective function. The parameters in the objective function are learned using the Minimum Classification Error (MCE) training method. Experiments on several challenging datasets demonstrate that the proposed HSC-based scene text recognition method outperforms HOG-based methods significantly and outperforms most state-of-the-art methods.

Dong Zhang, Omar Oreifej, Mubarak Shah

This paper proposes a new approach for face verification, where a pair of images needs to be classified as belonging to the same person or not. This problem is relatively new and not well-explored in the literature. Current methods mostly adopt techniques borrowed from face recognition, and process each of the images in the pair independently, which is counter intuitive. In contrast, we propose to extract cross-image features, i.e. features across the pair of images, which, as we demonstrate, is more discriminative to the similarity and the dissimilarity of faces. Our features are derived from the popular Haar-like features, however, extended to handle the face verification problem instead of face detection. We collect a large bank of cross-image features using filters of different sizes, locations, and orientations. Consequently, we use AdaBoost to select and weight the most discriminative features. We carried out extensive experiments on the proposed ideas using three standard face verification datasets, and obtained promising results outperforming state-of-the-art.