Our work focuses on tackling the problem of fine-grained recognition with incomplete multi-modal data, which is overlooked by previous work in the literature. It is desirable to not only capture fine-grained patterns of objects but also alleviate the challenges of missing modalities for such a practical problem. In this paper, we propose to leverage a meta-learning strategy to learn model abilities of both fast modal adaptation and more importantly missing modality completion across a variety of incomplete multi-modality learning tasks. Based on that, we develop a meta-completion method, termed as MECOM, to perform multimodal fusion and explicit missing modality completion by our proposals of cross-modal attention and decoupling reconstruction. To further improve fine-grained recognition accuracy, an additional partial stream (as a counterpart of the main stream of MECOM, i.e., holistic) and the part-level features (corresponding to fine-grained objects' parts) selection are designed, which are tailored for fine-grained nature to capture discriminative but subtle part-level patterns. Comprehensive experiments from quantitative and qualitative aspects, as well as various ablation studies, on two fine-grained multimodal datasets and one generic multimodal dataset show our superiority over competing methods. Our code is open-source and available at https://github.com/SEU-VIPGroup/MECOM.

Learning fine-grained embeddings from coarse labels is a challenging task due to limited label granularity supervision, i.e., lacking the detailed distinctions required for fine-grained tasks. The task becomes even more demanding when attempting few-shot fine-grained recognition, which holds practical significance in various applications. To address these challenges, we propose a novel method that embeds visual embeddings into a hyperbolic space and enhances their discriminative ability with a hierarchical cosine margins manner. Specifically, the hyperbolic space offers distinct advantages, including the ability to capture hierarchical relationships and increased expressive power, which favors modeling fine-grained objects. Based on the hyperbolic space, we further enforce relatively large/small similarity margins between coarse/fine classes, respectively, yielding the so-called hierarchical cosine margins manner. While enforcing similarity margins in the regular Euclidean space has become popular for deep embedding learning, applying it to the hyperbolic space is non-trivial and validating the benefit for coarse-to-fine generalization is valuable. Extensive experiments conducted on five benchmark datasets showcase the effectiveness of our proposed method, yielding state-of-the-art results surpassing competing methods.

The task of few-shot fine-grained recognition is to classify images belonging to subordinate categories merely depending on few examples. Due to the fine-grained nature, it is desirable to capture subtle but discriminative part-level patterns from limited training data, which makes it a challenging problem. In this paper, to generate fine-grained tailored representations for few-shot recognition, we propose a Dual Attention Network (Dual Att-Net) consisting of two dual branches of both hard- and soft-attentions. Specifically, by producing attention guidance from deep activations of input images, our hard-attention is realized by keeping a few useful deep descriptors and forming them as a bag of multi-instance learning. Since these deep descriptors could correspond to objects' parts, the advantage of modeling as a multi-instance bag is able to exploit inherent correlation of these fine-grained parts. On the other side, a soft attended activation representation can be obtained by applying attention guidance upon original activations, which brings comprehensive attention information as the counterpart of hard-attention. After that, both outputs of dual branches are aggregated as a holistic image embedding w.r.t. input images. By performing meta-learning, we can learn a powerful image embedding in such a metric space to generalize to novel classes. Experiments on three popular fine-grained benchmark datasets show that our Dual Att-Net obviously outperforms other existing state-of-the-art methods.

Semi-supervised few-shot learning consists in training a classifier to adapt to new tasks with limited labeled data and a fixed quantity of unlabeled data. Many sophisticated methods have been developed to address the challenges this problem comprises. In this paper, we propose a simple but quite effective approach to predict accurate negative pseudo-labels of unlabeled data from an indirect learning perspective, and then augment the extremely label-constrained support set in few-shot classification tasks. Our approach can be implemented in just few lines of code by only using off-the-shelf operations, yet it is able to outperform state-of-the-art methods on four benchmark datasets.

Deep learning has significantly improved the precision of instance segmentation with abundant labeled data. However, in many areas like medical and manufacturing, collecting sufficient data is extremely hard and labeling this data requires high professional skills. We follow this motivation and propose a new task set named zero-shot instance segmentation (ZSI). In the training phase of ZSI, the model is trained with seen data, while in the testing phase, it is used to segment all seen and unseen instances. We first formulate the ZSI task and propose a method to tackle the challenge, which consists of Zero-shot Detector, Semantic Mask Head, Background Aware RPN and Synchronized Background Strategy. We present a new benchmark for zero-shot instance segmentation based on the MS-COCO dataset. The extensive empirical results in this benchmark show that our method not only surpasses the state-of-the-art results in zero-shot object detection task but also achieves promising performance on ZSI. Our approach will serve as a solid baseline and facilitate future research in zero-shot instance segmentation. Code available at $\color{Magenta}{\text{ZSI}}$.

Mobile vision systems powered by the recent advancement in Deep Neural Networks (DNNs) are enabling a wide range of on-device video analytics applications. Considering mobile systems are constrained with limited resources, reducing resource demands of DNNs is crucial to realizing the full potential of these applications. In this paper, we present FlexDNN, an input-adaptive DNN-based framework for efficient on-device video analytics. To achieve this, FlexDNN takes the intrinsic dynamics of mobile videos into consideration, and dynamically adapts its model complexity to the difficulty levels of input video frames to achieve computation efficiency. FlexDNN addresses the key drawbacks of existing systems and pushes the state-of-the-art forward. We use FlexDNN to build three representative on-device video analytics applications, and evaluate its performance on both mobile CPU and GPU platforms. Our results show that FlexDNN significantly outperforms status quo approaches in accuracy, average CPU/GPU processing time per frame, frame drop rate, and energy consumption.

Although deep neural networks (DNNs) have achieved great success in semantic segmentation tasks, it is still challenging for real-time applications. A large number of feature channels, parameters, and floating-point operations make the network sluggish and computationally heavy, which is not desirable for real-time tasks such as robotics and autonomous driving. Most approaches, however, usually sacrifice spatial resolution to achieve inference speed in real time, resulting in poor performance. In this paper, we propose a light-weight stage-pooling semantic segmentation network (SPSSN), which can efficiently reuse the paramount features from early layers at multiple stages, at different spatial resolutions. SPSSN takes input of full resolution 2048×1024 pixels, uses only 1.42 × 10 6 parameters, yields 69.4% mIoU accuracy without pre-training, and obtains an inference speed of 59 frames/s on the Cityscapes dataset. SPSSN can run directly on mobile devices in real time, due to its light-weight architecture. To demonstrate the effectiveness of the proposed network, we compare our results with those of state-of-the-art networks.

Non-volatile Random-Access Memories (NVRAM) have emerged in recent years to bridge the performance gap between the main memory and external storage devices. To utilize the non-volatility of NVRAMs, programs should allow durable stores, meaning consistency must be maintained during a power loss event. GPUs are designed with high throughput, leveraging high degrees of parallelism. However, with lower NVRAM write bandwidths compared to that of DRAMs, using NVRAM as is may yield suboptimal overall system performance. To address this problem, we propose using Helper Warps to move persistence out of the critical path of transaction execution, alleviating the impact of latencies. Our mechanism achieves a speedup of 4.4 and 1.5 under bandwidth limits of 1.6 GB/s and 12 GB/s and is projected to maintain speed advantage even when NVRAM bandwidth gets as high as hundreds of GB/s in certain cases.

Efficiently discovering services in terms of diversified service constraints in a dense MANET is a challenging issue. This paper proposes to build a distributed suffix tree on backbone nodes as XML-based services¿ index to provide a concise profile for service descriptions. Moreover, a content-addressable P2P overlay and corresponding fault-tolerance mechanisms are introduced to support the distributed suffix tree and deal with the changes in network topology. In such a way, the precision and recall for service discovery are guaranteed and can also be degraded gracefully in the face of node failures. Experimental results show that our approach can increase at least 30% precision in comparison with existing distributed index solutions, and our newly-added messages for every 100 queries are only 22% as many as the ones of the compared solutions.