Recent trackers adopt the Transformer to combine or replace the widely used ResNet as their new backbone network. Although their trackers work well in regular scenarios, however, they simply flatten the 2D features into a sequence to better match the Transformer. We believe these operations ignore the spatial prior of the target object which may lead to sub-optimal results only. In addition, many works demonstrate that self-attention is actually a low-pass filter, which is independent of input features or key/queries. That is to say, it may suppress the high-frequency component of the input features and preserve or even amplify the low-frequency information. To handle these issues, in this paper, we propose a unified Spatial-Frequency Transformer that models the Gaussian spatial Prior and High-frequency emphasis Attention (GPHA) simultaneously. To be specific, Gaussian spatial prior is generated using dual Multi-Layer Perceptrons (MLPs) and injected into the similarity matrix produced by multiplying Query and Key features in self-attention. The output will be fed into a Softmax layer and then decomposed into two components, i.e., the direct signal and high-frequency signal. The low- and high-pass branches are rescaled and combined to achieve all-pass, therefore, the high-frequency features will be protected well in stacked self-attention layers. We further integrate the Spatial-Frequency Transformer into the Siamese tracking framework and propose a novel tracking algorithm, termed SFTransT. The cross-scale fusion based SwinTransformer is adopted as the backbone, and also a multi-head cross-attention module is used to boost the interaction between search and template features. The output will be fed into the tracking head for target localization. Extensive experiments on both short-term and long-term tracking benchmarks all demonstrate the effectiveness of our proposed framework.
Text-based person retrieval aims to find the query person based on a textual description. The key is to learn a common latent space mapping between visual-textual modalities. To achieve this goal, existing works employ segmentation to obtain explicitly cross-modal alignments or utilize attention to explore salient alignments. These methods have two shortcomings: 1) Labeling cross-modal alignments are time-consuming. 2) Attention methods can explore salient cross-modal alignments but may ignore some subtle and valuable pairs. To relieve these issues, we introduce an Implicit Visual-Textual (IVT) framework for text-based person retrieval. Different from previous models, IVT utilizes a single network to learn representation for both modalities, which contributes to the visual-textual interaction. To explore the fine-grained alignment, we further propose two implicit semantic alignment paradigms: multi-level alignment (MLA) and bidirectional mask modeling (BMM). The MLA module explores finer matching at sentence, phrase, and word levels, while the BMM module aims to mine \textbf{more} semantic alignments between visual and textual modalities. Extensive experiments are carried out to evaluate the proposed IVT on public datasets, i.e., CUHK-PEDES, RSTPReID, and ICFG-PEDES. Even without explicit body part alignment, our approach still achieves state-of-the-art performance. Code is available at: https://github.com/TencentYoutuResearch/PersonRetrieval-IVT.
Real-scene image super-resolution aims to restore real-world low-resolution images into their high-quality versions. A typical RealSR framework usually includes the optimization of multiple criteria which are designed for different image properties, by making the implicit assumption that the ground-truth images can provide a good trade-off between different criteria. However, this assumption could be easily violated in practice due to the inherent contrastive relationship between different image properties. Contrastive learning (CL) provides a promising recipe to relieve this problem by learning discriminative features using the triplet contrastive losses. Though CL has achieved significant success in many computer vision tasks, it is non-trivial to introduce CL to RealSR due to the difficulty in defining valid positive image pairs in this case. Inspired by the observation that the contrastive relationship could also exist between the criteria, in this work, we propose a novel training paradigm for RealSR, named Criteria Comparative Learning (Cria-CL), by developing contrastive losses defined on criteria instead of image patches. In addition, a spatial projector is proposed to obtain a good view for Cria-CL in RealSR. Our experiments demonstrate that compared with the typical weighted regression strategy, our method achieves a significant improvement under similar parameter settings.
Neuromorphic computing is an emerging research field that aims to develop new intelligent systems by integrating theories and technologies from multi-disciplines such as neuroscience and deep learning. Currently, there have been various software frameworks developed for the related fields, but there is a lack of an efficient framework dedicated for spike-based computing models and algorithms. In this work, we present a Python based spiking neural network (SNN) simulation and training framework, aka SPAIC that aims to support brain-inspired model and algorithm researches integrated with features from both deep learning and neuroscience. To integrate different methodologies from the two overwhelming disciplines, and balance between flexibility and efficiency, SPAIC is designed with neuroscience-style frontend and deep learning backend structure. We provide a wide range of examples including neural circuits Simulation, deep SNN learning and neuromorphic applications, demonstrating the concise coding style and wide usability of our framework. The SPAIC is a dedicated spike-based artificial intelligence computing platform, which will significantly facilitate the design, prototype and validation of new models, theories and applications. Being user-friendly, flexible and high-performance, it will help accelerate the rapid growth and wide applicability of neuromorphic computing research.
Unpaired Image Captioning (UIC) has been developed to learn image descriptions from unaligned vision-language sample pairs. Existing schemes usually adopt the visual concept reward of reinforcement learning to obtain the alignment between visual concepts and images. However, the cross-domain alignment is usually weak that severely constrains the overall performance of these existing schemes. Recent successes of Vision-Language Pre-Trained Models (VL-PTMs) have triggered the development of prompt-based learning from VL-PTMs. We present in this paper a novel scheme based on prompt to train the UIC model, making best use of the powerful generalization ability and abundant vision-language prior knowledge learned under VL-PTMs. We adopt the CLIP model for this research in unpaired image captioning. Specifically, the visual images are taken as input to the prompt generation module, which contains the pre-trained model as well as one feed-forward layer for prompt extraction. Then, the input images and generated prompts are aggregated for unpaired adversarial captioning learning. To further enhance the potential performance of the captioning, we designed a high-quality pseudo caption filter guided by the CLIP logits to measure correlations between predicted captions and the corresponding images. This allows us to improve the captioning model in a supervised learning manner. Extensive experiments on the COCO and Flickr30K datasets have been carried out to validate the superiority of the proposed model. We have achieved the state-of-the-art performance on the COCO dataset, which outperforms the best UIC model by 1.9% on the BLEU-4 metric. We expect that the proposed prompt-based UIC model will inspire a new line of research for the VL-PTMs based captioning.
The idea of robustness is central and critical to modern statistical analysis. However, despite the recent advances of deep neural networks (DNNs), many studies have shown that DNNs are vulnerable to adversarial attacks. Making imperceptible changes to an image can cause DNN models to make the wrong classification with high confidence, such as classifying a benign mole as a malignant tumor and a stop sign as a speed limit sign. The trade-off between robustness and standard accuracy is common for DNN models. In this paper, we introduce sensible adversarial learning and demonstrate the synergistic effect between pursuits of standard natural accuracy and robustness. Specifically, we define a sensible adversary which is useful for learning a robust model while keeping high natural accuracy. We theoretically establish that the Bayes classifier is the most robust multi-class classifier with the 0-1 loss under sensible adversarial learning. We propose a novel and efficient algorithm that trains a robust model using implicit loss truncation. We apply sensible adversarial learning for large-scale image classification to a handwritten digital image dataset called MNIST and an object recognition colored image dataset called CIFAR10. We have performed an extensive comparative study to compare our method with other competitive methods. Our experiments empirically demonstrate that our method is not sensitive to its hyperparameter and does not collapse even with a small model capacity while promoting robustness against various attacks and keeping high natural accuracy.
Existing trackers usually select a location or proposal with the maximum score as tracking result for each frame. However, such greedy search scheme maybe not the optimal choice, especially when encountering challenging tracking scenarios like heavy occlusions and fast motion. Since the accumulated errors would make response scores not reliable anymore. In this paper, we propose a novel multi-agent reinforcement learning based beam search strategy (termed BeamTracking) to address this issue. Specifically, we formulate the tracking as a sample selection problem fulfilled by multiple parallel decision-making processes, each of which aims at picking out one sample as their tracking result in each frame. We take the target feature, proposal feature, and its response score as state, and also consider actions predicted by nearby agent, to train multi-agents to select their actions. When all the frames are processed, we select the trajectory with the maximum accumulated score as the tracking result. Extensive experiments on seven popular tracking benchmark datasets validated the effectiveness of the proposed algorithm.
Ensuring safety of reinforcement learning (RL) algorithms is crucial for many real-world tasks. However, vanilla RL does not guarantee safety for an agent. In recent years, several methods have been proposed to provide safety guarantees for RL. To the best of our knowledge, there is no comprehensive comparison of these provably safe RL methods. We therefore introduce a categorization for existing provably safe RL methods, and present the theoretical foundations for both continuous and discrete action spaces. Additionally, we evaluate provably safe RL on an inverted pendulum. In the experiments, it is shown that indeed only provably safe RL methods guarantee safety.
Ptychography is a popular microscopic imaging modality for many scientific discoveries and sets the record for highest image resolution. Unfortunately, the high image resolution for ptychographic reconstruction requires significant amount of memory and computations, forcing many applications to compromise their image resolution in exchange for a smaller memory footprint and a shorter reconstruction time. In this paper, we propose a novel image gradient decomposition method that significantly reduces the memory footprint for ptychographic reconstruction by tessellating image gradients and diffraction measurements into tiles. In addition, we propose a parallel image gradient decomposition method that enables asynchronous point-to-point communications and parallel pipelining with minimal overhead on a large number of GPUs. Our experiments on a Titanate material dataset (PbTiO3) with 16632 probe locations show that our Gradient Decomposition algorithm reduces memory footprint by 51 times. In addition, it achieves time-to-solution within 2.2 minutes by scaling to 4158 GPUs with a super-linear speedup at 364% efficiency. This performance is 2.7 times more memory efficient, 9 times more scalable and 86 times faster than the state-of-the-art algorithm.
Combining simple architectures with large-scale pre-training has led to massive improvements in image classification. For object detection, pre-training and scaling approaches are less well established, especially in the long-tailed and open-vocabulary setting, where training data is relatively scarce. In this paper, we propose a strong recipe for transferring image-text models to open-vocabulary object detection. We use a standard Vision Transformer architecture with minimal modifications, contrastive image-text pre-training, and end-to-end detection fine-tuning. Our analysis of the scaling properties of this setup shows that increasing image-level pre-training and model size yield consistent improvements on the downstream detection task. We provide the adaptation strategies and regularizations needed to attain very strong performance on zero-shot text-conditioned and one-shot image-conditioned object detection. Code and models are available on GitHub.