Neural networks have achieved success in a wide array of perceptual tasks but often fail at tasks involving both perception and higher-level reasoning. On these more challenging tasks, bespoke approaches (such as modular symbolic components, independent dynamics models or semantic parsers) targeted towards that specific type of task have typically performed better. The downside to these targeted approaches, however, is that they can be more brittle than general-purpose neural networks, requiring significant modification or even redesign according to the particular task at hand. Here, we propose a more general neural-network-based approach to dynamic visual reasoning problems that obtains state-of-the-art performance on three different domains, in each case outperforming bespoke modular approaches tailored specifically to the task. Our method relies on learned object-centric representations, self-attention and self-supervised dynamics learning, and all three elements together are required for strong performance to emerge. The success of this combination suggests that there may be no need to trade off flexibility for performance on problems involving spatio-temporal or causal-style reasoning. With the right soft biases and learning objectives in a neural network we may be able to attain the best of both worlds.
Reasoning Guided Embeddings: Leveraging MLLM Reasoning for Improved Multimodal Retrieval
State Key Laboratory for Novel Software Technology, Nanjing University（南京大学新型软件技术国家重点实验室）；Sensetime Research（商汤科技研究院）；Beijing Institute of Technology（北京理工大学）；Shanghai AI Lab（上海人工智能实验室）
School of Informatics, Xiamen University, China（厦门大学信息学院）；WeChat AI, Tencent Inc, China（腾讯公司微信AI部门）；Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan (Xiamen University), Ministry of Culture and Tourism, China（福建省和台湾非物质文化遗产数字化保护与智能处理重点实验室）；Shanghai Artificial Intelligence Laboratory, China（上海人工智能实验室）
Compositional Generalization from Learned Skills via CoT Training: A Theoretical and Structural Analysis for Reasoning
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学人工智能学院）；Beijing Key Laboratory of Research on Large Models and Intelligent Governance（北京大型模型与智能治理研究重点实验室）；Engineering Research Center of Next-Generation Intelligent Search and Recommendation, MOE（下一代智能搜索与推荐工程研究中心，教育部）；Tianjin University of Science and Technology（天津科技大学）；Beijing Institute of Technology（北京理工大学）
SeLaR: Selective Latent Reasoning in Large Language Models
Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology（广东省超高清沉浸式媒体技术重点实验室）；Shenzhen Graduate School, Peking University（北京大学深圳研究生院）
Probabilistic Aggregation and Targeted Embedding Optimization for Collective Moral Reasoning in Large Language Models
School of Computation, Information and Technology, Technical University of Munich（计算、信息与技术学院，慕尼黑技术大学）；School of Social Sciences and Technology, Technical University of Munich（社会科学与技术学院，慕尼黑技术大学）
Automatic instance segmentation is a problem that occurs in many biomedical applications. State-of-the-art approaches either perform semantic segmentation or refine object bounding boxes obtained from detection methods. Both suffer from crowded objects to varying degrees, merging adjacent objects or suppressing a valid object. In this work, we assign an embedding vector to each pixel through a deep neural network. The network is trained to output embedding vectors of similar directions for pixels from the same object, while adjacent objects are orthogonal in the embedding space, which effectiv…
LIX（巴黎综合理工学院计算机实验室）；Ecole Polytechnique, IP Paris（巴黎综合理工学院（巴黎理工学院））
Many innovative applications require establishing correspondences among 3D geometric objects. However, the countless possible deformations of smooth surfaces make shape matching a challenging task. Finding an embedding to represent the different shapes in high-dimensional space where the matching is easier to solve is a well-trodden path that has given many outstanding solutions. Recently, a new trend has shown advantages in learning such representations. This novel idea motivated us to investigate which properties differentiate these data-driven embeddings and which ones promote state-of-the-…
Carnegie Mellon University（卡内基梅隆大学）；Facebook AI Research（Facebook人工智能研究院）；Google, Inc.（谷歌公司）；New York University（纽约大学）
Modern deep transfer learning approaches have mainly focused on learning generic feature vectors from one task that are transferable to other tasks, such as word embeddings in language and pretrained convolutional features in vision. However, these approaches usually transfer unary features and largely ignore more structured graphical representations. This work explores the possibility of learning generic latent relational graphs that capture dependencies between pairs of data units (e.g., words or pixels) from large-scale unlabeled data and transferring the graphs to downstream tasks. Our pro…
We revisit two popular convolutional neural networks (CNN) in person re-identification (re-ID), i.e, verification and classification models. The two models have their respective advantages and limitations due to different loss functions. In this paper, we shed light on how to combine the two models to learn more discriminative pedestrian descriptors. Specifically, we propose a new siamese network that simultaneously computes identification loss and verification loss. Given a pair of training images, the network predicts the identities of the two images and whether they belong to the same ident…
We propose a method, called Label Embedding Network, which can learn label representation (label embedding) during the training process of deep networks. With the proposed method, the label embedding is adaptively and automatically learned through back propagation. The original one-hot represented loss function is converted into a new loss function with soft distributions, such that the originally unrelated labels have continuous interactions with each other during the training process. As a result, the trained model can achieve substantially higher accuracy and with faster convergence speed. …
Massachusetts Institute of Technology（麻省理工学院）；Toyota Technological Institute at Chicago（芝加哥丰田技术研究所）
We propose a vision-based method that localizes a ground vehicle using publicly available satellite imagery as the only prior knowledge of the environment. Our approach takes as input a sequence of ground-level images acquired by the vehicle as it navigates, and outputs an estimate of the vehicle's pose relative to a georeferenced satellite image. We overcome the significant viewpoint and appearance variations between the images through a neural multi-view model that learns location-discriminative embeddings in which ground-level images are matched with their corresponding satellite view of th…
University of Electronic Science and Technology of China（电子科技大学）；Leshan Normal University（乐山师范学院）
In this work, a discriminatively learned CNN embedding is proposed for remote sensing image scene classification. Our proposed siamese network simultaneously computes the classification loss function and the metric learning loss function of the two input images. Specifically, for the classification loss, we use the standard cross-entropy loss function to predict the classes of the images. For the metric learning loss, our siamese network learns to map the intra-class and inter-class input pairs to a feature space where intra-class inputs are close and inter-class inputs are separated by a marg…
Logic reasoning is a significant ability of human intelligence and also an important task in artificial intelligence. The existing logic reasoning methods, quite often, need to design some reasoning patterns beforehand. This has led to an interesting question: can logic reasoning patterns be directly learned from given data? The problem is termed as a data concept logic. In this study, a learning logic task from images, called a LiLi task, first is proposed. This task is to learn and reason the logic relation from images, without presetting any reasoning patterns. As a preliminary exploration,…
Hohai University（河海大学）；Singapore University of Technology and Design（新加坡科技设计大学）；University of Electronic Science and Technology of China（电子科技大学）；Shanghai AI Laboratory（上海人工智能实验室）；Nanjing University（南京大学）
Incremental few-shot semantic segmentation (IFSS) targets at incrementally expanding model's capacity to segment new class of images supervised by only a few samples. However, features learned on old classes could significantly drift, causing catastrophic forgetting. Moreover, few samples for pixel-level segmentation on new classes lead to notorious overfitting issues in each learning session. In this paper, we explicitly represent class-based knowledge for semantic segmentation as a category embedding and a hyper-class embedding, where the former describes exclusive semantical properties, and…
Existing manifold learning methods are not appropriate for image retrieval task, because most of them are unable to process query image and they have much additional computational cost especially for large scale database. Therefore, we propose the iterative manifold embedding (IME) layer, of which the weights are learned off-line by unsupervised strategy, to explore the intrinsic manifolds by incomplete data. On the large scale database that contains 27000 images, IME layer is more than 120 times faster than other manifold learning methods to embed the original representations at query time. W…
National University of Sciences and Technology（国立科技大学）；University of Insubria（因苏布里亚大学）
Majority of the current dimensionality reduction or retrieval techniques rely on embedding the learned feature representations onto a computable metric space. Once the learned features are mapped, a distance metric aids the bridging of gaps between similar instances. Since the scaled projection is not exploited in these methods, discriminative embedding onto a hyperspace becomes a challenge. In this paper, we propose to inwardly scale feature representations in proportional to projecting them onto a hypersphere manifold for discriminative analysis. We further propose a novel, yet simpler, conv…
