我们在本文中解决的主要问题是如何扩展对看不见类（也称为零局学习）的视觉识别，以达到成千上万的类别，如Imagenet-21K基准中。在这个规模上，尤其是ImageNet-21K中包含许多细粒类别的规模，学习质量的视觉语义表示至关重要，它们具有足够的歧视性，足以识别看不见的类别并将其与见证的类别区分开来。我们提出了一个\ emph {h} ierarchical \ emph {g} raphical知识\ emph {r}基于置信度的分类方法（被称为HGR-net）的EPRESENTATION框架。我们的实验结果表明，HGR-NET可以利用层次结构概念知识来掌握类遗传关系。与Imagenet-21K基准的亚军方法相比，我们的方法大大优于所有现有技术，使性能提高了7 \％。我们表明，HGR-NET在几个场景中学习有效。我们还分析了较小的数据集（例如ImageNet-21K-P，2-s-s和3-shops）的方法，证明了其泛化能力。我们的基准和代码可在https://kaiyi.me/p/hgrnet.html上获得。

We propose a novel teacher-student model for semi-supervised multi-organ segmentation. In teacher-student model, data augmentation is usually adopted on unlabeled data to regularize the consistent training between teacher and student. We start from a key perspective that fixed relative locations and variable sizes of different organs can provide distribution information where a multi-organ CT scan is drawn. Thus, we treat the prior anatomy as a strong tool to guide the data augmentation and reduce the mismatch between labeled and unlabeled images for semi-supervised learning. More specifically, we propose a data augmentation strategy based on partition-and-recovery N$^3$ cubes cross- and within- labeled and unlabeled images. Our strategy encourages unlabeled images to learn organ semantics in relative locations from the labeled images (cross-branch) and enhances the learning ability for small organs (within-branch). For within-branch, we further propose to refine the quality of pseudo labels by blending the learned representations from small cubes to incorporate local attributes. Our method is termed as MagicNet, since it treats the CT volume as a magic-cube and $N^3$-cube partition-and-recovery process matches with the rule of playing a magic-cube. Extensive experiments on two public CT multi-organ datasets demonstrate the effectiveness of MagicNet, and noticeably outperforms state-of-the-art semi-supervised medical image segmentation approaches, with +7% DSC improvement on MACT dataset with 10% labeled images.

Machine learning approaches are widely studied in the production prediction of CBM wells after hydraulic fracturing, but merely used in practice due to the low generalization ability and the lack of interpretability. A novel methodology is proposed in this article to discover the latent causality from observed data, which is aimed at finding an indirect way to interpret the machine learning results. Based on the theory of causal discovery, a causal graph is derived with explicit input, output, treatment and confounding variables. Then, SHAP is employed to analyze the influence of the factors on the production capability, which indirectly interprets the machine learning models. The proposed method can capture the underlying nonlinear relationship between the factors and the output, which remedies the limitation of the traditional machine learning routines based on the correlation analysis of factors. The experiment on the data of CBM shows that the detected relationship between the production and the geological/engineering factors by the presented method, is coincident with the actual physical mechanism. Meanwhile, compared with traditional methods, the interpretable machine learning models have better performance in forecasting production capability, averaging 20% improvement in accuracy.

As the basis for prehensile manipulation, it is vital to enable robots to grasp as robustly as humans. In daily manipulation, our grasping system is prompt, accurate, flexible and continuous across spatial and temporal domains. Few existing methods cover all these properties for robot grasping. In this paper, we propose a new methodology for grasp perception to enable robots these abilities. Specifically, we develop a dense supervision strategy with real perception and analytic labels in the spatial-temporal domain. Additional awareness of objects' center-of-mass is incorporated into the learning process to help improve grasping stability. Utilization of grasp correspondence across observations enables dynamic grasp tracking. Our model, AnyGrasp, can generate accurate, full-DoF, dense and temporally-smooth grasp poses efficiently, and works robustly against large depth sensing noise. Embedded with AnyGrasp, we achieve a 93.3% success rate when clearing bins with over 300 unseen objects, which is comparable with human subjects under controlled conditions. Over 900 MPPH is reported on a single-arm system. For dynamic grasping, we demonstrate catching swimming robot fish in the water.

We propose EM-PASTE: an Expectation Maximization(EM) guided Cut-Paste compositional dataset augmentation approach for weakly-supervised instance segmentation using only image-level supervision. The proposed method consists of three main components. The first component generates high-quality foreground object masks. To this end, an EM-like approach is proposed that iteratively refines an initial set of object mask proposals generated by a generic region proposal method. Next, in the second component, high-quality context-aware background images are generated using a text-to-image compositional synthesis method like DALL-E. Finally, the third component creates a large-scale pseudo-labeled instance segmentation training dataset by compositing the foreground object masks onto the original and generated background images. The proposed approach achieves state-of-the-art weakly-supervised instance segmentation results on both the PASCAL VOC 2012 and MS COCO datasets by using only image-level, weak label information. In particular, it outperforms the best baseline by +7.4 and +2.8 mAP0.50 on PASCAL and COCO, respectively. Further, the method provides a new solution to the long-tail weakly-supervised instance segmentation problem (when many classes may only have few training samples), by selectively augmenting under-represented classes.

In this paper, we study two challenging but less-touched problems in image restoration, namely, i) how to quantify the relationship between different image degradations and ii) how to improve the performance of a specific restoration task using the quantified relationship. To tackle the first challenge, Degradation Relationship Index (DRI) is proposed to measure the degradation relationship, which is defined as the drop rate difference in the validation loss between two models, i.e., one is trained using the anchor task only and another is trained using the anchor and the auxiliary tasks. Through quantifying the relationship between different degradations using DRI, we empirically observe that i) the degradation combination proportion is crucial to the image restoration performance. In other words, the combinations with only appropriate degradation proportions could improve the performance of the anchor restoration; ii) a positive DRI always predicts the performance improvement of image restoration. Based on the observations, we propose an adaptive Degradation Proportion Determination strategy (DPD) which could improve the performance of the anchor restoration task by using another restoration task as auxiliary. Extensive experimental results verify the effective of our method by taking image dehazing as the anchor task and denoising, desnowing, and deraining as the auxiliary tasks. The code will be released after acceptance.

We study the learning dynamics of self-predictive learning for reinforcement learning, a family of algorithms that learn representations by minimizing the prediction error of their own future latent representations. Despite its recent empirical success, such algorithms have an apparent defect: trivial representations (such as constants) minimize the prediction error, yet it is obviously undesirable to converge to such solutions. Our central insight is that careful designs of the optimization dynamics are critical to learning meaningful representations. We identify that a faster paced optimization of the predictor and semi-gradient updates on the representation, are crucial to preventing the representation collapse. Then in an idealized setup, we show self-predictive learning dynamics carries out spectral decomposition on the state transition matrix, effectively capturing information of the transition dynamics. Building on the theoretical insights, we propose bidirectional self-predictive learning, a novel self-predictive algorithm that learns two representations simultaneously. We examine the robustness of our theoretical insights with a number of small-scale experiments and showcase the promise of the novel representation learning algorithm with large-scale experiments.

Automata-based representations play an important role in control and planning in sequential decision-making, but obtaining high-level task knowledge for building automata is often difficult. Although large-scale generative language models (GLMs) can help automatically distill task knowledge, the textual outputs from GLMs are not directly utilizable in sequential decision-making. We resolve this problem by proposing a novel algorithm named GLM2FSA, which obtains high-level task knowledge, represented in a finite state automaton (FSA), from a given brief description of the task goal. GLM2FSA sends queries to a GLM for task knowledge in textual form and then builds a FSA to represent the textual knowledge. This algorithm fills the gap between text and automata-based representations, and the constructed FSA can be directly utilized in sequential decision-making. We provide examples to demonstrate how GLM2FSA constructs FSAs to represent knowledge encoded in the texts generated by the large-scale GLMs.

Multi-modal image-text models such as CLIP and LiT have demonstrated impressive performance on image classification benchmarks and their zero-shot generalization ability is particularly exciting. While the top-5 zero-shot accuracies of these models are very high, the top-1 accuracies are much lower (over 25% gap in some cases). We investigate the reasons for this performance gap and find that many of the failure cases are caused by ambiguity in the text prompts. First, we develop a simple and efficient zero-shot post-hoc method to identify images whose top-1 prediction is likely to be incorrect, by measuring consistency of the predictions w.r.t. multiple prompts and image transformations. We show that our procedure better predicts mistakes, outperforming the popular max logit baseline on selective prediction tasks. Next, we propose a simple and efficient way to improve accuracy on such uncertain images by making use of the WordNet hierarchy; specifically we augment the original class by incorporating its parent and children from the semantic label hierarchy, and plug the augmentation into text promts. We conduct experiments on both CLIP and LiT models with five different ImageNet-based datasets. For CLIP, our method improves the top-1 accuracy by 17.13% on the uncertain subset and 3.6% on the entire ImageNet validation set. We also show that our method improves across ImageNet shifted datasets and other model architectures such as LiT. Our proposed method is hyperparameter-free, requires no additional model training and can be easily scaled to other large multi-modal architectures.

Recently, massive architectures based on Convolutional Neural Network (CNN) and self-attention mechanisms have become necessary for audio classification. While these techniques are state-of-the-art, these works' effectiveness can only be guaranteed with huge computational costs and parameters, large amounts of data augmentation, transfer from large datasets and some other tricks. By utilizing the lightweight nature of audio, we propose an efficient network structure called Paired Inverse Pyramid Structure (PIP) and a network called Paired Inverse Pyramid Structure MLP Network (PIPMN). The PIPMN reaches 96\% of Environmental Sound Classification (ESC) accuracy on the UrbanSound8K dataset and 93.2\% of Music Genre Classification (MGC) on the GTAZN dataset, with only 1 million parameters. Both of the results are achieved without data augmentation or model transfer. Public code is available at: https://github.com/JNAIC/PIPMN