Recent video-to-audio (V2A) generation relies on extracting semantic and temporal features from video to condition generative models. Training these models from scratch is resource-intensive. Consequently, leveraging foundation models (FMs) has gained traction due to their cross-modal knowledge transfer and generalization capabilities. One prior work has explored fine-tuning a lightweight mapper network to connect a pre-trained visual encoder with a text-to-audio generation model for V2A. Inspired by this, we introduce the Multiple Foundation Model Mapper (MFM-Mapper). Compared to the previous mapper approach, MFM-Mapper benefits from richer semantic and temporal information by fusing features from dual visual encoders. Furthermore, by replacing a linear mapper with GPT-2, MFM-Mapper improves feature alignment, drawing parallels between cross-modal features mapping and autoregressive translation tasks. Our MFM-Mapper demonstrates high efficiency in terms of both data requirements and training costs. Compared to prior linear mapper-based work, it achieves superior performance in semantic and temporal consistency with only about 40% of the training data and 40% of the training epochs.

Recently, unsupervised cross-dataset person reidentification (Re-ID) has attracted more and more attention, which aims to transfer knowledge of a labeled source domain to an unlabeled target domain. There are two common frameworks: one is pixel-alignment of transferring low-level knowledge, and the other is feature-alignment of transferring high-level knowledge. In this article, we propose a novel recurrent autoencoder (RAE) framework to unify these two kinds of methods and inherit their merits. Specifically, the proposed RAE includes three modules, i.e., a feature-transfer (FT) module, a pixel-transfer (PT) module, and a fusion module. The FT module utilizes an encoder to map source and target images to a shared feature space. In the space, not only features are identity-discriminative but also the gap between source and target features is reduced. The PT module takes a decoder to reconstruct original images with its features. Here, we hope that the images reconstructed from target features are in the source style. Thus, the low-level knowledge can be propagated to the target domain. After transferring both high-and low-level knowledge with the two proposed modules above, we design another bilinear pooling layer to fuse both kinds of knowledge. Extensive experiments on Market-1501, DukeMTMC-ReID, and MSMT17 datasets show that our method significantly outperforms either pixel-alignment or feature-alignment Re-ID methods and achieves new state-of-the-art results.

The denoising model has been proven a powerful generative model but has little exploration of discriminative tasks. Representation learning is important in discriminative tasks, which is defined as *"learning representations (or features) of the data that make it easier to extract useful information when building classifiers or other predictors"*. In this paper, we propose a novel Denoising Model for Representation Learning (*DenoiseRep*) to improve feature discrimination with joint feature extraction and denoising. *DenoiseRep* views each embedding layer in a backbone as a denoising layer, processing the cascaded embedding layers as if we are recursively denoise features step-by-step. This unifies the frameworks of feature extraction and denoising, where the former progressively embeds features from low-level to high-level, and the latter recursively denoises features step-by-step. After that, *DenoiseRep* fuses the parameters of feature extraction and denoising layers, and *theoretically demonstrates* its equivalence before and after the fusion, thus making feature denoising computation-free. *DenoiseRep* is a label-free algorithm that incrementally improves features but also complementary to the label if available. Experimental results on various discriminative vision tasks, including re-identification (Market-1501, DukeMTMC-reID, MSMT17, CUHK-03, vehicleID), image classification (ImageNet, UB200, Oxford-Pet, Flowers), object detection (COCO), image segmentation (ADE20K) show stability and impressive improvements. We also validate its effectiveness on the CNN (ResNet) and Transformer (ViT, Swin, Vmamda) architectures.

Fast person re-identification (ReID) aims to search person images quickly and accurately. The main idea of recent fast ReID methods is the hashing algorithm, which learns compact binary codes and performs fast Hamming distance and counting sort. However, a very long code is needed for high accuracy (e.g.2048), which compromises search speed. In this work, we introduce a new solution for fast ReID by formulating a novel Coarse-to-Fine (CtF) hashing code search strategy, which complementarily uses short and long codes, achieving both faster speed and better accuracy. It uses shorter codes to coarsely rank broad matching similarities and longer codes to refine only a few top candidates for more accurate instance ReID. Specifically, we design an All-in-One (AiO) module together with a Distance Threshold Optimization (DTO) algorithm. In AiO, we simultaneously learn and enhance multiple codes of different lengths in a single model. It learns multiple codes in a pyramid structure, and encourage shorter codes to mimic longer codes by self-distillation. DTO solves a complex threshold search problem by a simple optimization process, and the balance between accuracy and speed is easily controlled by a single parameter. It formulates the optimization target as a$F_{\beta }$score that can be optimised by Gaussian cumulative distribution functions. Besides, we find even short code (e.g.32) still takes a long time under large-scale gallery due to the$O(n)$time complexity. To solve the problem, we propose a gallery-size-free latent-attributes-based One-Shot-Filter (OSF) strategy, that is always$O(1)$time complexity, to quickly filter major easy negative gallery images, Specifically, we design a Latent-Attribute-Learning (LAL) module supervised a Single-Direction-Metric (SDM) Loss. LAL is derived from principal component analysis (PCA) that keeps largest variance using shortest feature vector, meanwhile enabling batch and end-to-end learning. Every logit of a feature vector represents a meaningful attribute. SDM is carefully designed for fine-grained attribute supervision, outperforming common metrics such as Euclidean and Cosine metrics. Experimental results on 2 datasets show that CtF+OSF is not only$2\%$more accurate but also$5\times$faster than contemporary hashing ReID methods. Compared with non-hashing ReID methods, CtF is$50\times$faster with comparable accuracy. OSF further speeds CtF by$2\times$again and upto$10\times$in total with almost no accuracy drop.

Magnetic Resonance Imaging (MRI) has been proven to be an efficient way to diagnose Alzheimer's disease (AD). Recent dramatic progress on deep learning greatly promotes the MRI analysis based on data-driven CNN methods using a large-scale longitudinal MRI dataset. However, most of the existing MRI datasets are fragmented due to unexpected quits of volunteers. To tackle this problem, we propose a novel Temporal Recurrent Generative Adversarial Network (TR-GAN) to complete missing sessions of MRI datasets. Unlike existing GAN-based methods, which either fail to generate future sessions or only generate fixed-length sessions, TR-GAN takes all past sessions to recurrently and smoothly generate future ones with variant length. Specifically, TR-GAN adopts recurrent connection to deal with variant input sequence length and flexibly generate future variant sessions. Besides, we also design a multiple scale & location (MSL) module and a SWAP module to encourage the model to better focus on detailed information, which helps to generate high-quality MRI data. Compared with other popular GAN architectures, TR-GAN achieved the best performance in all evaluation metrics of two datasets. After expanding the Whole MRI dataset, the balanced accuracy of AD vs. cognitively normal (CN) vs. mild cognitive impairment (MCI) and stable MCI vs. progressive MCI classification can be increased by 3.61% and 4.00%, respectively.

Hashing is a popular search algorithm for its compact binary representation and efficient Hamming distance calculation. Benefited from the advance of deep learning, deep hashing methods have achieved promising performance. However, those methods usually learn with expensive labeled data but fail to utilize unlabeled data. Furthermore, the traditional pairwise loss used by those methods cannot explicitly force similar/dissimilar pairs to small/large distances. Both weaknesses limit existing methods’ performance. To solve the first problem, we propose a novel semi-supervised deep hashing model named adversarial binary mutual learning (ABML). Specifically, our ABML consists of a generative model$G_{H}$and a discriminative model$D_{H}$, where$D_{H}$learns labeled data in a supervised way and$G_{H}$learns unlabeled data by synthesizing real images. We adopt an adversarial learning (AL) strategy to transfer the knowledge of unlabeled data to$D_{H}$by making$G_{H}$and$D_{H}$mutually learn from each other. To solve the second problem, we propose a novel Weibull cross-entropy loss (WCE) by using the Weibull distribution, which can distinguish tiny differences of distances and explicitly force similar/dissimilar distances as small/large as possible. Thus, the learned features are more discriminative. Finally, by incorporating ABML with WCE loss, our model can acquire more semantic and discriminative features. Extensive experiments on four common data sets (CIFAR-10, large database of handwritten digits (MNIST), ImageNet-10, and NUS-WIDE) and a large-scale data set ImageNet demonstrate that our approach successfully overcomes the two difficulties above and significantly outperforms state-of-the-art hashing methods.

In this paper, we propose an efficient human pose estimation network (DANet) by learning deeply aggregated representations. Most existing models explore multi-scale infonnation mainly from features with different spatial sizes. Powerful multi-scale representations usually rely on the cascaded pyramid framework. This framework largely boosts the performance but in the meanwhile makes networks very deep and complex. Instead, we focus on exploiting multi-scale information from layers with different receptive-field sizes and then making full of use this infonnation by improving the fusion method. Specifically, we propose an orthogonal attention block (OAB) and a second-order fusion unit (SFU). The OAB learns multi-scale infonnation from different layers and enhances them by encouraging them to be diverse. The SFU adaptively selects and fuses diverse multi-scale infonnation and suppress the redundant ones. With the help of OAB and SFU, our networks could achieve comparable or even better accuracy with much smaller model complexity. Specifically, our DANet-72 achieves 71.0 in AP score on COCO val2017 with only 1.0G FLOPS. Its speed on a CPU platfonn achieves 58 Persons-Per-Second (PPS).

Medical diagnostic robot systems have been paid more and more attention due to its objectivity and accuracy. The diagnosis of mild cognitive impairment (MCI) is considered an effective means to prevent Alzheimer's disease (AD). Doctors diagnose MCI based on various clinical examinations, which are expensive and the diagnosis results rely on the knowledge of doctors. Therefore, it is necessary to develop a robot diagnostic system to eliminate the influence of human factors and obtain a higher accuracy rate. In this paper, we propose a novel Group Feature Domain Adversarial Neural Network (GF- DANN) for amnestic MCI (aMCI) diagnosis, which involves two important modules. A Group Feature Extraction (GFE) module is proposed to reduce individual differences by learning group- level features through adversarial learning. A Dual Branch Domain Adaptation (DBDA) module is carefully designed to reduce the distribution difference between the source and target domain in a domain adaption way. On three types of data set, GF-DANN achieves the best accuracy compared with classic machine learning and deep learning methods. On the DMS data set, GF-DANN has obtained an accuracy rate of 89.47%, and the sensitivity and specificity are 90% and 89%. In addition, by comparing three EEG data collection paradigms, our results demonstrate that the DMS paradigm has the potential to build an aMCI diagnose robot system.

Real-time guidewire segmentation and endpoint localization play a pivotal role in robot-assisted minimally invasive surgery, which is helpful to reduce radiation dose and procedure time. Nevertheless, the tasks often come with the challenge of limited computational resources. For this purpose, a real-time multi-task framework with two stages is developed. In the first stage, a Fast Attention-fused Network (FAD-Net) is proposed to obtain accurate guidewire segmentation masks. In the second stage, a lightweight localization network and a post-processing algorithm are designed to robustly predict the guidewire endpoint position. Quantitative and qualitative evaluations on intraoperative X-ray sequences from 30 patients demonstrate that the developed framework outperforms the previously-published results for the tasks, achieving state-of-the-art performance. Moreover, the inference rate of the developed framework is approximately 10.6 FPS, which meets the real-time requirement of X-ray fluoroscopy. These results indicate the proposed approach has the potential to be integrated into the robotic navigation framework for endovascular interventions, enabling robotic-assisted minimally invasive surgery.

Person re-identification (ReID) aims to match pedestrian images across disjoint cameras. Existing supervised ReID methods utilize deep networks and train them with identity-labeled images, which suffer from limited annotations. Recently, clustering-based unsupervised ReID attracts more and more attention. It first clusters unlabeled images and assigns cluster index to the pseudo-identity-labels, then trains a ReID model with the pseudo-identity-labels. However, considering the slight inter-class variations and significant intra-class variations, pseudo-identity-labels learned from clustering algorithms are usually noisy and coarse. To alleviate the problems above, besides clustering pseudo-identity-labels, we propose to learn pseudo-patch-labels, which brings two advantages: (1) Patch naturally alleviates the effect of backgrounds, occlusions, and carryings since they usually occupy small parts in images, thus overcome noisy labels. (2) It is plausible that patches from different pedestrians belong to the same pseudo-identity-label. For example, pedestrians have a high probability of wearing either the same shoes or pants but a low possibility of wearing both. The experiments demonstrate our proposed method achieves the best performance by a large margin on both image- and video-based datasets.

Semantic segmentation of surgical instruments plays a critical role in computer-assisted surgery. However, specular reflection and scale variation of instruments are likely to occur in the surgical environment, undesirably altering visual features of instruments, such as color and shape. These issues make semantic segmentation of surgical instruments more challenging. In this paper, a novel network, Pyramid Attention Aggregation Network, is proposed to aggregate multi-scale attentive features for surgical instruments. It contains two critical modules: Double Attention Module and Pyramid Upsampling Module. Specifically, the Double Attention Module includes two attention blocks (i.e., position attention block and channel attention block), which model semantic dependencies between positions and channels by capturing joint semantic information and global contexts, respectively. The attentive features generated by the Double Attention Module can distinguish target regions, contributing to solving the specular reflection issue. Moreover, the Pyramid Upsampling Module extracts local details and global contexts by aggregating multi-scale attentive features. It learns the shape and size features of surgical instruments in different receptive fields and thus addresses the scale variation issue. The proposed network achieves state-of-the-art performance on various datasets. It achieves a new record of 97.10% mean IOU on Cata7. Besides, it comes first in the MICCAI EndoVis Challenge 2017 with 9.90% increase on mean IOU.

RGB-Infrared (IR) person re-identification is very challenging due to the large cross-modality variations between RGB and IR images. The key solution is to learn aligned features to the bridge RGB and IR modalities. However, due to the lack of correspondence labels between every pair of RGB and IR images, most methods try to alleviate the variations with set-level alignment by reducing the distance between the entire RGB and IR sets. However, this set-level alignment may lead to misalignment of some instances, which limits the performance for RGB-IR Re-ID. Different from existing methods, in this paper, we propose to generate cross-modality paired-images and perform both global set-level and fine-grained instance-level alignments. Our proposed method enjoys several merits. First, our method can perform set-level alignment by disentangling modality-specific and modality-invariant features. Compared with conventional methods, ours can explicitly remove the modality-specific features and the modality variation can be better reduced. Second, given cross-modality unpaired-images of a person, our method can generate cross-modality paired images from exchanged images. With them, we can directly perform instance-level alignment by minimizing distances of every pair of images. Extensive experimental results on two standard benchmarks demonstrate that the proposed model favourably against state-of-the-art methods. Especially, on SYSU-MM01 dataset, our model can achieve a gain of 9.2% and 7.7% in terms of Rank-1 and mAP. Code is available at https://github.com/wangguanan/JSIA-ReID.

Occluded person re-identification (ReID) aims to match occluded person images to holistic ones across dis-joint cameras. In this paper, we propose a novel framework by learning high-order relation and topology information for discriminative features and robust alignment. At first, we use a CNN backbone to learn feature maps and key-points estimation model to extract semantic local features. Even so, occluded images still suffer from occlusion and outliers. Then, we view the extracted local features of an image as nodes of a graph and propose an adaptive direction graph convolutional (ADGC) layer to pass relation information between nodes. The proposed ADGC layer can automatically suppress the message passing of meaningless features by dynamically learning direction and degree of linkage. When aligning two groups of local features, we view it as a graph matching problem and propose a cross-graph embedded-alignment (CGEA) layer to joint learn and embed topology information to local features, and straightly predict similarity score. The proposed CGEA layer can both take full use of alignment learned by graph matching and replace sensitive one-to-one alignment with a robust soft one. Finally, extensive experiments on occluded, partial, and holistic ReID tasks show the effectiveness of our proposed method. Specifically, our framework significantly outperforms state-of-the-art by $6.5\%$ mAP scores on Occluded-Duke dataset.

Surgical instrument segmentation is crucial for computer-assisted surgery. Different from common object segmentation, it is more challenging due to the large illumination variation and scale variation in the surgical scenes. In this paper, we propose a bilinear attention network with adaptive receptive fields to address these two issues. To deal with the illumination variation, the bilinear attention module models global contexts and semantic dependencies between pixels by capturing second-order statistics. With them, semantic features in challenging areas can be inferred from their neighbors, and the distinction of various semantics can be boosted. To adapt to the scale variation, our adaptive receptive field module aggregates multi-scale features and selects receptive fields adaptively. Specifically, it models the semantic relationships between channels to choose feature maps with appropriate scales, changing the receptive field of subsequent convolutions. The proposed network achieves the best performance 97.47% mean IoU on Cata7. It also takes the first place on EndoVis 2017, exceeding the second place by 10.10% mean IoU.

RGB-Infrared (IR) person re-identification is an important and challenging task due to large cross-modality variations between RGB and IR images. Most conventional approaches aim to bridge the cross-modality gap with feature alignment by feature representation learning. Different from existing methods, in this paper, we propose a novel and end-to-end Alignment Generative Adversarial Network (AlignGAN) for the RGB-IR RE-ID task. The proposed model enjoys several merits. First, it can exploit pixel alignment and feature alignment jointly. To the best of our knowledge, this is the first work to model the two alignment strategies jointly for the RGB-IR RE-ID problem. Second, the proposed model consists of a pixel generator, a feature generator and a joint discriminator. By playing a min-max game among the three components, our model is able to not only alleviate the cross-modality and intra-modality variations, but also learn identity-consistent features. Extensive experimental results on two standard benchmarks demonstrate that the proposed model performs favourably against state-of-the-art methods. Especially, on SYSU-MM01 dataset, our model can achieve an absolute gain of 15.4% and 12.9% in terms of Rank-1 and mAP.

Recent deep Re-ID models mainly focus on learning high-level semantic features, while failing to explicitly explore color information which is one of the most important cues for person Re-ID. In this paper, we propose a novel Color-Sensitive Re-ID to take full advantage of color information. On one hand, we train our model with real and fake images. By using the extra fake images, more color information can be exploited and it can avoid overfitting during training. On the other hand, we also train our model with images of the same person with different colors. By doing so, features can be forced to focus on the color difference in regions. To generate fake images with specified colors, we propose a novel Color Translation GAN (CTGAN) to learn mappings between different clothing colors and preserve identity consistency among the same clothing color. Extensive evaluations on two benchmark datasets show that our approach significantly outperforms state-of-the-art Re-ID models.