Fine-grained visual parsing, including fine-grained part segmentation and fine-grained object recognition, has attracted considerable critical attention due to its importance in many real-world applications, e.g., agriculture, remote sensing, and space technologies. Predominant research efforts tackle these fine-grained sub-tasks following different paradigms, while the inherent relations between these tasks are neglected. Moreover, given most of the research remains fragmented, we conduct an in-depth study of the advanced work from a new perspective of learning the part relationship. In this perspective, we first consolidate recent research and benchmark syntheses with new taxonomies. Based on this consolidation, we revisit the universal challenges in fine-grained part segmentation and recognition tasks and propose new solutions by part relationship learning for these important challenges. Furthermore, we conclude several promising lines of research in fine-grained visual parsing for future research.

Fine-grained visual recognition is to classify objects with visually similar appearances into subcategories, which has made great progress with the development of deep CNNs. However, handling subtle differences between different subcategories still remains a challenge. In this paper, we propose to solve this issue in one unified framework from two aspects, i.e., constructing feature-level interrelationships, and capturing part-level discriminative features. This framework, namely PArt-guided Relational Transformers (PART), is proposed to learn the discriminative part features with an automatic part discovery module, and to explore the intrinsic correlations with a feature transformation module by adapting the Transformer models from the field of natural language processing. The part discovery module efficiently discovers the discriminative regions which are highly-corresponded to the gradient descent procedure. Then the second feature transformation module builds correlations within the global embedding and multiple part embedding, enhancing spatial interactions among semantic pixels. Moreover, our proposed approach does not rely on additional part branches in the inference time and reaches state-of-the-art performance on 3 widely-used fine-grained object recognition benchmarks. Experimental results and explainable visualizations demonstrate the effectiveness of our proposed approach. The code can be found at https://github.com/iCVTEAM/PART.

Weakly-supervised temporal action localization (WTAL) learns to detect and classify action instances with only category labels. Most methods widely adopt the off-the-shelf Classification-Based Pre-training (CBP) to generate video features for action localization. However, the different optimization objectives between classification and localization, make temporally localized results suffer from the serious incomplete issue. To tackle this issue without additional annotations, this paper considers to distill free action knowledge from Vision-Language Pre-training (VLP), since we surprisingly observe that the localization results of vanilla VLP have an over-complete issue, which is just complementary to the CBP results. To fuse such complementarity, we propose a novel distillation-collaboration framework with two branches acting as CBP and VLP respectively. The framework is optimized through a dual-branch alternate training strategy. Specifically, during the B step, we distill the confident background pseudo-labels from the CBP branch; while during the F step, the confident foreground pseudo-labels are distilled from the VLP branch. And as a result, the dual-branch complementarity is effectively fused to promote a strong alliance. Extensive experiments and ablation studies on THUMOS14 and ActivityNet1.2 reveal that our method significantly outperforms state-of-the-art methods.

The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known about the common practice as well as bottlenecks faced by the community in tackling the research questions posed. To shed light on the status quo of algorithm development in the specific field of biomedical imaging analysis, we designed an international survey that was issued to all participants of challenges conducted in conjunction with the IEEE ISBI 2021 and MICCAI 2021 conferences (80 competitions in total). The survey covered participants' expertise and working environments, their chosen strategies, as well as algorithm characteristics. A median of 72% challenge participants took part in the survey. According to our results, knowledge exchange was the primary incentive (70%) for participation, while the reception of prize money played only a minor role (16%). While a median of 80 working hours was spent on method development, a large portion of participants stated that they did not have enough time for method development (32%). 25% perceived the infrastructure to be a bottleneck. Overall, 94% of all solutions were deep learning-based. Of these, 84% were based on standard architectures. 43% of the respondents reported that the data samples (e.g., images) were too large to be processed at once. This was most commonly addressed by patch-based training (69%), downsampling (37%), and solving 3D analysis tasks as a series of 2D tasks. K-fold cross-validation on the training set was performed by only 37% of the participants and only 50% of the participants performed ensembling based on multiple identical models (61%) or heterogeneous models (39%). 48% of the respondents applied postprocessing steps.

Recently, the success of pre-training in text domain has been fully extended to vision, audio, and cross-modal scenarios. The proposed pre-training models of different modalities are showing a rising trend of homogeneity in their model structures, which brings the opportunity to implement different pre-training models within a uniform framework. In this paper, we present TencentPretrain, a toolkit supporting pre-training models of different modalities. The core feature of TencentPretrain is the modular design. The toolkit uniformly divides pre-training models into 5 components: embedding, encoder, target embedding, decoder, and target. As almost all of common modules are provided in each component, users can choose the desired modules from different components to build a complete pre-training model. The modular design enables users to efficiently reproduce existing pre-training models or build brand-new one. We test the toolkit on text, vision, and audio benchmarks and show that it can match the performance of the original implementations.

Ego-pose estimation and dynamic object tracking are two critical problems for autonomous driving systems. The solutions to these problems are generally based on their respective assumptions, \ie{the static world assumption for simultaneous localization and mapping (SLAM) and the accurate ego-pose assumption for object tracking}. However, these assumptions are challenging to hold in dynamic road scenarios, where SLAM and object tracking become closely correlated. Therefore, we propose DL-SLOT, a dynamic LiDAR SLAM and object tracking method, to simultaneously address these two coupled problems. This method integrates the state estimations of both the autonomous vehicle and the stationary and dynamic objects in the environment into a unified optimization framework. First, we used object detection to identify all points belonging to potentially dynamic objects. Subsequently, a LiDAR odometry was conducted using the filtered point cloud. Simultaneously, we proposed a sliding window-based object association method that accurately associates objects according to the historical trajectories of tracked objects. The ego-states and those of the stationary and dynamic objects are integrated into the sliding window-based collaborative graph optimization. The stationary objects are subsequently restored from the potentially dynamic object set. Finally, a global pose-graph is implemented to eliminate the accumulated error. Experiments on KITTI datasets demonstrate that our method achieves better accuracy than SLAM and object tracking baseline methods. This confirms that solving SLAM and object tracking simultaneously is mutually advantageous, dramatically improving the robustness and accuracy of SLAM and object tracking in dynamic road scenarios.

With the growth of high-dimensional sparse data in web-scale recommender systems, the computational cost to learn high-order feature interaction in CTR prediction task largely increases, which limits the use of high-order interaction models in real industrial applications. Some recent knowledge distillation based methods transfer knowledge from complex teacher models to shallow student models for accelerating the online model inference. However, they suffer from the degradation of model accuracy in knowledge distillation process. It is challenging to balance the efficiency and effectiveness of the shallow student models. To address this problem, we propose a Directed Acyclic Graph Factorization Machine (KD-DAGFM) to learn the high-order feature interactions from existing complex interaction models for CTR prediction via Knowledge Distillation. The proposed lightweight student model DAGFM can learn arbitrary explicit feature interactions from teacher networks, which achieves approximately lossless performance and is proved by a dynamic programming algorithm. Besides, an improved general model KD-DAGFM+ is shown to be effective in distilling both explicit and implicit feature interactions from any complex teacher model. Extensive experiments are conducted on four real-world datasets, including a large-scale industrial dataset from WeChat platform with billions of feature dimensions. KD-DAGFM achieves the best performance with less than 21.5% FLOPs of the state-of-the-art method on both online and offline experiments, showing the superiority of DAGFM to deal with the industrial scale data in CTR prediction task. Our implementation code is available at: https://github.com/RUCAIBox/DAGFM.

Modern retrieval system often requires recomputing the representation of every piece of data in the gallery when updating to a better representation model. This process is known as backfilling and can be especially costly in the real world where the gallery often contains billions of samples. Recently, researchers have proposed the idea of Backward Compatible Training (BCT) where the new representation model can be trained with an auxiliary loss to make it backward compatible with the old representation. In this way, the new representation can be directly compared with the old representation, in principle avoiding the need for any backfilling. However, followup work shows that there is an inherent tradeoff where a backward compatible representation model cannot simultaneously maintain the performance of the new model itself. This paper reports our ``not-so-surprising'' finding that adding extra dimensions to the representation can help here. However, we also found that naively increasing the dimension of the representation did not work. To deal with this, we propose Backward-compatible Training with a novel Basis Transformation ($BT^2$). A basis transformation (BT) is basically a learnable set of parameters that applies an orthonormal transformation. Such a transformation possesses an important property whereby the original information contained in its input is retained in its output. We show in this paper how a BT can be utilized to add only the necessary amount of additional dimensions. We empirically verify the advantage of $BT^2$ over other state-of-the-art methods in a wide range of settings. We then further extend $BT^2$ to other challenging yet more practical settings, including significant change in model architecture (CNN to Transformers), modality change, and even a series of updates in the model architecture mimicking the evolution of deep learning models.

从大脑的事件驱动和稀疏的尖峰特征中受益，尖峰神经网络（SNN）已成为人工神经网络（ANN）的一种节能替代品。但是，SNNS和ANN之间的性能差距很长一段时间以来一直在延伸SNNS。为了利用SNN的全部潜力，我们研究了SNN中注意机制的影响。我们首先使用插件套件提出了我们的注意力，称为多维关注（MA）。然后，提出了一种新的注意力SNN体系结构，并提出了端到端训练，称为“ ma-snn”，该体系结构分别或同时或同时延伸了沿时间，通道以及空间维度的注意力重量。基于现有的神经科学理论，我们利用注意力重量来优化膜电位，进而以数据依赖性方式调节尖峰响应。 MA以可忽略的其他参数为代价，促进了香草SNN，以实现更稀疏的尖峰活动，更好的性能和能源效率。实验是在基于事件的DVS128手势/步态动作识别和Imagenet-1K图像分类中进行的。在手势/步态上，尖峰计数减少了84.9％/81.6％，任务准确性和能源效率提高了5.9％/4.7％和3.4 $ \ times $/3.2 $ \ times $。在ImagEnet-1K上，我们在单个/4步res-SNN-104上获得了75.92％和77.08％的TOP-1精度，这是SNN的最新结果。据我们所知，这是SNN社区与大规模数据集中的ANN相比，SNN社区取得了可比甚至更好的性能。我们的工作阐明了SNN作为支持SNN的各种应用程序的一般骨干的潜力，在有效性和效率之间取得了巨大平衡。

最新的工业推理引擎（例如FASTRASTRANSFORMER1和TURBOTTRANSFORMER）已验证了半精度的浮点（FP16）和8位整数（INT8）量化可以极大地提高模型推断速度。但是，现有的FP16或INT8量化方法太复杂了，使用不当将大大导致性能损害。在本文中，我们开发了一个工具包，供用户轻松量化其模型以进行推理，其中提出了自适应混合精液（SAMP），以通过混合精确体系结构自动控制量化率，以平衡效率和性能。实验结果表明，我们的SAMP工具包比Pytorch和Fertransformer具有更高的速度，同时确保了所需的性能。此外，SAMP基于模块化设计，将令牌，嵌入，编码器和目标层解耦，该层允许用户处理各种下游任务，并且可以将其无缝集成到Pytorch中。